From 27aa9d9ebe4c21ac8737a47e19535f082e82cd7d Mon Sep 17 00:00:00 2001 From: Ashutosh Chauhan Date: Sun, 19 Aug 2018 13:42:40 -0700 Subject: [PATCH] HIVE-17084 : Turn on hive.stats.fetch.column.stats configuration flag --- .../positive/accumulo_predicate_pushdown.q.out | 64 +- .../test/results/positive/accumulo_queries.q.out | 88 +- .../accumulo_single_sourced_multi_insert.q.out | 24 +- .../java/org/apache/hadoop/hive/conf/HiveConf.java | 2 +- .../results/clientpositive/serde_typedbytes.q.out | 20 +- .../results/clientpositive/serde_typedbytes2.q.out | 18 +- .../results/clientpositive/serde_typedbytes3.q.out | 18 +- .../results/clientpositive/serde_typedbytes4.q.out | 22 +- .../results/clientpositive/serde_typedbytes5.q.out | 20 +- .../results/clientpositive/udaf_example_avg.q.out | 12 +- .../clientpositive/udaf_example_group_concat.q.out | 12 +- .../results/clientpositive/udaf_example_max.q.out | 12 +- .../clientpositive/udaf_example_max_n.q.out | 12 +- .../results/clientpositive/udaf_example_min.q.out | 12 +- .../clientpositive/udaf_example_min_n.q.out | 12 +- .../udf_example_arraymapstruct.q.out | 6 +- .../results/clientpositive/udf_row_sequence.q.out | 10 +- .../vector_udf_example_arraymapstruct.q.out | 6 +- .../test/results/clientpositive/acid_mapjoin.q.out | 14 +- .../results/clientpositive/acid_nullscan.q.out | 12 +- .../results/clientpositive/acid_table_stats.q.out | 12 +- .../clientpositive/alias_casted_column.q.out | 12 +- .../results/clientpositive/allcolref_in_udf.q.out | 50 +- .../clientpositive/alterColumnStatsPart.q.out | 48 +- .../clientpositive/alter_partition_coltype.q.out | 12 +- .../results/clientpositive/ambiguous_col.q.out | 66 +- .../analyze_table_null_partition.q.out | 4 +- .../results/clientpositive/analyze_tbl_date.q.out | 8 +- .../clientpositive/ansi_sql_arithmetic.q.out | 16 +- .../array_map_access_nonconstant.q.out | 8 +- .../results/clientpositive/autoColumnStats_4.q.out | 28 +- .../results/clientpositive/autoColumnStats_6.q.out | 18 +- .../results/clientpositive/autoColumnStats_7.q.out | 28 +- .../results/clientpositive/autoColumnStats_8.q.out | 38 +- .../results/clientpositive/autoColumnStats_9.q.out | 40 +- .../test/results/clientpositive/auto_join0.q.out | 42 +- .../test/results/clientpositive/auto_join1.q.out | 28 +- .../test/results/clientpositive/auto_join10.q.out | 24 +- .../test/results/clientpositive/auto_join11.q.out | 24 +- .../test/results/clientpositive/auto_join12.q.out | 30 +- .../test/results/clientpositive/auto_join13.q.out | 32 +- .../test/results/clientpositive/auto_join14.q.out | 28 +- .../test/results/clientpositive/auto_join15.q.out | 20 +- .../test/results/clientpositive/auto_join16.q.out | 24 +- .../test/results/clientpositive/auto_join17.q.out | 28 +- .../test/results/clientpositive/auto_join18.q.out | 36 +- .../auto_join18_multi_distinct.q.out | 36 +- .../test/results/clientpositive/auto_join19.q.out | 28 +- .../clientpositive/auto_join19_inclause.q.out | 28 +- .../test/results/clientpositive/auto_join2.q.out | 36 +- .../test/results/clientpositive/auto_join20.q.out | 44 +- .../test/results/clientpositive/auto_join21.q.out | 18 +- .../test/results/clientpositive/auto_join22.q.out | 32 +- .../test/results/clientpositive/auto_join23.q.out | 18 +- .../test/results/clientpositive/auto_join24.q.out | 22 +- .../test/results/clientpositive/auto_join26.q.out | 34 +- .../test/results/clientpositive/auto_join27.q.out | 42 +- .../test/results/clientpositive/auto_join28.q.out | 76 +- .../test/results/clientpositive/auto_join29.q.out | 182 +-- .../test/results/clientpositive/auto_join3.q.out | 34 +- .../test/results/clientpositive/auto_join31.q.out | 22 +- .../test/results/clientpositive/auto_join32.q.out | 40 +- .../test/results/clientpositive/auto_join33.q.out | 16 +- .../test/results/clientpositive/auto_join4.q.out | 28 +- .../test/results/clientpositive/auto_join5.q.out | 28 +- .../test/results/clientpositive/auto_join6.q.out | 32 +- .../test/results/clientpositive/auto_join7.q.out | 40 +- .../test/results/clientpositive/auto_join8.q.out | 30 +- .../test/results/clientpositive/auto_join9.q.out | 28 +- .../auto_join_reordering_values.q.out | 60 +- .../results/clientpositive/auto_join_stats.q.out | 120 +- .../results/clientpositive/auto_join_stats2.q.out | 60 +- .../auto_join_without_localtask.q.out | 218 +-- .../avro_schema_evolution_native.q.out | 10 +- .../clientpositive/beeline/explain_outputs.q.out | 78 +- .../beeline/materialized_view_create_rewrite.q.out | 62 +- .../clientpositive/beeline/smb_mapjoin_1.q.out | 20 +- .../clientpositive/beeline/smb_mapjoin_10.q.out | 4 +- .../clientpositive/beeline/smb_mapjoin_11.q.out | 20 +- .../clientpositive/beeline/smb_mapjoin_12.q.out | 8 +- .../clientpositive/beeline/smb_mapjoin_13.q.out | 24 +- .../clientpositive/beeline/smb_mapjoin_16.q.out | 4 +- .../clientpositive/beeline/smb_mapjoin_2.q.out | 20 +- .../clientpositive/beeline/smb_mapjoin_3.q.out | 20 +- .../clientpositive/beeline/smb_mapjoin_7.q.out | 2 +- .../clientpositive/binary_output_format.q.out | 18 +- .../results/clientpositive/binarysortable_1.q.out | 14 +- ql/src/test/results/clientpositive/bucket1.q.out | 20 +- ql/src/test/results/clientpositive/bucket2.q.out | 26 +- ql/src/test/results/clientpositive/bucket3.q.out | 30 +- .../results/clientpositive/bucket_map_join_1.q.out | 10 +- .../results/clientpositive/bucket_map_join_2.q.out | 10 +- .../clientpositive/bucket_map_join_spark1.q.out | 40 +- .../clientpositive/bucket_map_join_spark2.q.out | 40 +- .../clientpositive/bucket_map_join_spark3.q.out | 40 +- .../clientpositive/bucket_map_join_spark4.q.out | 52 +- .../results/clientpositive/bucketcontext_1.q.out | 14 +- .../results/clientpositive/bucketcontext_2.q.out | 14 +- .../results/clientpositive/bucketcontext_3.q.out | 14 +- .../results/clientpositive/bucketcontext_4.q.out | 14 +- .../results/clientpositive/bucketcontext_5.q.out | 14 +- .../results/clientpositive/bucketcontext_6.q.out | 14 +- .../results/clientpositive/bucketcontext_7.q.out | 14 +- .../results/clientpositive/bucketcontext_8.q.out | 14 +- .../results/clientpositive/bucketmapjoin10.q.out | 10 +- .../results/clientpositive/bucketmapjoin11.q.out | 20 +- .../results/clientpositive/bucketmapjoin12.q.out | 20 +- .../results/clientpositive/bucketmapjoin13.q.out | 40 +- .../results/clientpositive/bucketmapjoin5.q.out | 32 +- .../results/clientpositive/bucketmapjoin8.q.out | 20 +- .../results/clientpositive/bucketmapjoin9.q.out | 20 +- .../clientpositive/bucketmapjoin_negative.q.out | 16 +- .../clientpositive/bucketmapjoin_negative2.q.out | 16 +- .../clientpositive/bucketmapjoin_negative3.q.out | 126 +- .../bucketsortoptimize_insert_1.q.out | 46 +- .../bucketsortoptimize_insert_3.q.out | 28 +- .../bucketsortoptimize_insert_4.q.out | 12 +- .../bucketsortoptimize_insert_5.q.out | 12 +- .../bucketsortoptimize_insert_8.q.out | 12 +- .../results/clientpositive/case_sensitivity.q.out | 18 +- ql/src/test/results/clientpositive/cast1.q.out | 18 +- .../results/clientpositive/cast_on_constant.q.out | 40 +- .../cbo_SortUnionTransposeRule.q.out | 328 ++-- ql/src/test/results/clientpositive/cbo_const.q.out | 42 +- .../test/results/clientpositive/cbo_input26.q.out | 158 +- .../clientpositive/cbo_ppd_non_deterministic.q.out | 24 +- .../clientpositive/cbo_rp_auto_join17.q.out | 30 +- .../cbo_rp_cross_product_check_2.q.out | 134 +- .../cbo_rp_gby2_map_multi_distinct.q.out | 52 +- .../cbo_rp_groupby3_noskew_multi_distinct.q.out | 20 +- .../test/results/clientpositive/cbo_rp_join1.q.out | 64 +- .../clientpositive/cbo_rp_outer_join_ppr.q.out | 44 +- .../cbo_rp_udaf_percentile_approx_23.q.out | 24 +- .../results/clientpositive/cbo_union_view.q.out | 72 +- .../column_pruner_multiple_children.q.out | 20 +- .../column_pruning_partitioned_view.q.out | 4 +- .../columnarserde_create_shortcut.q.out | 10 +- .../clientpositive/columnstats_partlvl.q.out | 98 +- .../clientpositive/columnstats_partlvl_dp.q.out | 56 +- .../clientpositive/columnstats_quoting.q.out | 24 +- .../clientpositive/columnstats_tbllvl.q.out | 84 +- ql/src/test/results/clientpositive/combine2.q.out | 16 +- ql/src/test/results/clientpositive/comments.q.out | 22 +- .../results/clientpositive/complex_alias.q.out | 50 +- .../clientpositive/compute_stats_date.q.out | 12 +- ql/src/test/results/clientpositive/concat_op.q.out | 6 +- .../results/clientpositive/constantPropWhen.q.out | 48 +- .../constantPropagateForSubQuery.q.out | 20 +- .../results/clientpositive/constant_prop_1.q.out | 68 +- .../results/clientpositive/constant_prop_2.q.out | 14 +- .../results/clientpositive/constant_prop_3.q.out | 72 +- .../test/results/clientpositive/constprog2.q.out | 44 +- .../test/results/clientpositive/constprog3.q.out | 12 +- .../test/results/clientpositive/constprog_dp.q.out | 18 +- .../clientpositive/constprog_partitioner.q.out | 46 +- .../clientpositive/constprog_when_case.q.out | 6 +- .../clientpositive/correlationoptimizer10.q.out | 234 +-- .../clientpositive/correlationoptimizer11.q.out | 104 +- .../clientpositive/correlationoptimizer12.q.out | 32 +- .../clientpositive/correlationoptimizer13.q.out | 42 +- .../clientpositive/correlationoptimizer14.q.out | 298 ++-- .../clientpositive/correlationoptimizer15.q.out | 86 +- .../clientpositive/correlationoptimizer5.q.out | 132 +- .../clientpositive/correlationoptimizer7.q.out | 144 +- .../clientpositive/correlationoptimizer8.q.out | 278 ++-- .../clientpositive/correlationoptimizer9.q.out | 140 +- .../clientpositive/count_dist_rewrite.q.out | 164 +- ql/src/test/results/clientpositive/cp_sel.q.out | 36 +- .../clientpositive/create_genericudaf.q.out | 12 +- .../test/results/clientpositive/create_view.q.out | 8 +- .../test/results/clientpositive/cross_join.q.out | 72 +- .../results/clientpositive/cross_join_merge.q.out | 140 +- .../clientpositive/cross_product_check_1.q.out | 150 +- .../clientpositive/cross_product_check_2.q.out | 128 +- ql/src/test/results/clientpositive/ctas.q.out | 90 +- .../test/results/clientpositive/ctas_colname.q.out | 92 +- .../ctas_uses_database_location.q.out | 6 +- ql/src/test/results/clientpositive/cte_1.q.out | 24 +- ql/src/test/results/clientpositive/cte_3.q.out | 44 +- ql/src/test/results/clientpositive/cte_5.q.out | 22 +- ql/src/test/results/clientpositive/cte_6.q.out | 16 +- ql/src/test/results/clientpositive/cte_mat_1.q.out | 22 +- ql/src/test/results/clientpositive/cte_mat_2.q.out | 22 +- ql/src/test/results/clientpositive/cte_mat_3.q.out | 28 +- ql/src/test/results/clientpositive/cte_mat_4.q.out | 56 +- ql/src/test/results/clientpositive/cte_mat_5.q.out | 28 +- .../results/clientpositive/decimal_join2.q.out | 44 +- .../results/clientpositive/decimal_precision.q.out | 14 +- .../test/results/clientpositive/decimal_udf.q.out | 214 +-- .../test/results/clientpositive/decimal_udf2.q.out | 16 +- .../clientpositive/display_colstats_tbllvl.q.out | 36 +- .../results/clientpositive/distinct_stats.q.out | 38 +- .../clientpositive/distinct_windowing.q.out | 60 +- .../clientpositive/distinct_windowing_no_cbo.q.out | 104 +- .../dynamic_partition_skip_default.q.out | 12 +- .../dynpart_sort_optimization_acid2.q.out | 10 +- .../test/results/clientpositive/empty_join.q.out | 22 +- .../encryption_join_unencrypted_tbl.q.out | 20 +- .../results/clientpositive/escape_clusterby1.q.out | 20 +- .../clientpositive/escape_distributeby1.q.out | 20 +- .../results/clientpositive/escape_orderby1.q.out | 20 +- .../results/clientpositive/escape_sortby1.q.out | 20 +- .../test/results/clientpositive/except_all.q.out | 232 +-- .../exec_parallel_column_stats.q.out | 12 +- .../test/results/clientpositive/explain_ddl.q.out | 40 +- .../results/clientpositive/explain_logical.q.out | 166 +- .../results/clientpositive/explain_outputs.q.out | 78 +- .../results/clientpositive/explain_rearrange.q.out | 48 +- ql/src/test/results/clientpositive/extract.q.out | 12 +- .../results/clientpositive/fetch_aggregation.q.out | 10 +- .../test/results/clientpositive/filter_aggr.q.out | 14 +- .../clientpositive/filter_cond_pushdown.q.out | 132 +- .../clientpositive/filter_cond_pushdown2.q.out | 42 +- .../filter_cond_pushdown_HIVE_15647.q.out | 88 +- .../results/clientpositive/filter_in_or_dup.q.out | 24 +- .../clientpositive/filter_join_breaktask.q.out | 34 +- .../results/clientpositive/filter_numeric.q.out | 22 +- .../test/results/clientpositive/filter_union.q.out | 74 +- .../results/clientpositive/flatten_and_or.q.out | 8 +- .../test/results/clientpositive/floor_time.q.out | 12 +- ql/src/test/results/clientpositive/fm-sketch.q.out | 24 +- ql/src/test/results/clientpositive/fold_case.q.out | 88 +- .../clientpositive/fold_eq_with_case_when.q.out | 48 +- ql/src/test/results/clientpositive/fold_when.q.out | 96 +- .../results/clientpositive/folder_predicate.q.out | 56 +- ql/src/test/results/clientpositive/foldts.q.out | 24 +- .../clientpositive/fp_literal_arithmetic.q.out | 56 +- ql/src/test/results/clientpositive/gby_star.q.out | 70 +- .../clientpositive/gen_udf_example_add10.q.out | 12 +- ql/src/test/results/clientpositive/groupby1.q.out | 16 +- ql/src/test/results/clientpositive/groupby10.q.out | 144 +- ql/src/test/results/clientpositive/groupby11.q.out | 58 +- ql/src/test/results/clientpositive/groupby12.q.out | 20 +- ql/src/test/results/clientpositive/groupby13.q.out | 14 +- .../results/clientpositive/groupby1_limit.q.out | 22 +- .../test/results/clientpositive/groupby1_map.q.out | 24 +- .../clientpositive/groupby1_map_nomap.q.out | 24 +- .../results/clientpositive/groupby1_map_skew.q.out | 28 +- .../results/clientpositive/groupby1_noskew.q.out | 20 +- .../results/clientpositive/groupby2_limit.q.out | 18 +- .../test/results/clientpositive/groupby2_map.q.out | 24 +- .../groupby2_map_multi_distinct.q.out | 48 +- .../results/clientpositive/groupby2_map_skew.q.out | 28 +- .../results/clientpositive/groupby2_noskew.q.out | 20 +- .../groupby2_noskew_multi_distinct.q.out | 20 +- ql/src/test/results/clientpositive/groupby3.q.out | 26 +- .../test/results/clientpositive/groupby3_map.q.out | 22 +- .../groupby3_map_multi_distinct.q.out | 22 +- .../results/clientpositive/groupby3_map_skew.q.out | 26 +- .../results/clientpositive/groupby3_noskew.q.out | 18 +- .../groupby3_noskew_multi_distinct.q.out | 18 +- ql/src/test/results/clientpositive/groupby4.q.out | 26 +- .../results/clientpositive/groupby4_noskew.q.out | 18 +- ql/src/test/results/clientpositive/groupby5.q.out | 28 +- .../test/results/clientpositive/groupby5_map.q.out | 22 +- .../results/clientpositive/groupby5_map_skew.q.out | 22 +- .../results/clientpositive/groupby5_noskew.q.out | 20 +- ql/src/test/results/clientpositive/groupby6.q.out | 26 +- .../test/results/clientpositive/groupby6_map.q.out | 22 +- .../results/clientpositive/groupby6_map_skew.q.out | 26 +- .../results/clientpositive/groupby6_noskew.q.out | 18 +- .../test/results/clientpositive/groupby7_map.q.out | 46 +- .../groupby7_map_multi_single_reducer.q.out | 40 +- .../results/clientpositive/groupby7_map_skew.q.out | 54 +- .../results/clientpositive/groupby7_noskew.q.out | 38 +- .../groupby7_noskew_multi_single_reducer.q.out | 48 +- ql/src/test/results/clientpositive/groupby8.q.out | 108 +- .../test/results/clientpositive/groupby8_map.q.out | 40 +- .../results/clientpositive/groupby8_map_skew.q.out | 54 +- .../results/clientpositive/groupby8_noskew.q.out | 36 +- ql/src/test/results/clientpositive/groupby9.q.out | 230 +-- .../clientpositive/groupby_complex_types.q.out | 32 +- ...roupby_complex_types_multi_single_reducer.q.out | 34 +- .../results/clientpositive/groupby_cube1.q.out | 146 +- .../clientpositive/groupby_cube_multi_gby.q.out | 44 +- .../clientpositive/groupby_distinct_samekey.q.out | 24 +- .../clientpositive/groupby_duplicate_key.q.out | 44 +- .../clientpositive/groupby_grouping_id3.q.out | 32 +- .../clientpositive/groupby_grouping_sets1.q.out | 94 +- .../clientpositive/groupby_grouping_sets2.q.out | 72 +- .../clientpositive/groupby_grouping_sets3.q.out | 46 +- .../clientpositive/groupby_grouping_sets4.q.out | 116 +- .../clientpositive/groupby_grouping_sets5.q.out | 64 +- .../clientpositive/groupby_grouping_sets6.q.out | 24 +- .../groupby_grouping_sets_grouping.q.out | 222 +-- .../groupby_grouping_sets_limit.q.out | 92 +- .../clientpositive/groupby_grouping_window.q.out | 22 +- .../clientpositive/groupby_join_pushdown.q.out | 414 ++--- .../results/clientpositive/groupby_map_ppr.q.out | 24 +- .../groupby_map_ppr_multi_distinct.q.out | 24 +- .../groupby_multi_insert_common_distinct.q.out | 46 +- .../groupby_multi_single_reducer.q.out | 88 +- .../groupby_multi_single_reducer2.q.out | 44 +- .../groupby_multi_single_reducer3.q.out | 176 +-- .../clientpositive/groupby_multialias.q.out | 12 +- .../results/clientpositive/groupby_position.q.out | 166 +- .../test/results/clientpositive/groupby_ppd.q.out | 30 +- .../test/results/clientpositive/groupby_ppr.q.out | 20 +- .../groupby_ppr_multi_distinct.q.out | 42 +- .../results/clientpositive/groupby_rollup1.q.out | 118 +- .../clientpositive/groupby_rollup_empty.q.out | 16 +- .../results/clientpositive/groupby_sort_10.q.out | 20 +- .../results/clientpositive/groupby_sort_11.q.out | 90 +- .../results/clientpositive/groupby_sort_1_23.q.out | 504 +++--- .../results/clientpositive/groupby_sort_2.q.out | 24 +- .../results/clientpositive/groupby_sort_3.q.out | 40 +- .../results/clientpositive/groupby_sort_4.q.out | 48 +- .../results/clientpositive/groupby_sort_5.q.out | 64 +- .../results/clientpositive/groupby_sort_6.q.out | 76 +- .../results/clientpositive/groupby_sort_7.q.out | 20 +- .../results/clientpositive/groupby_sort_8.q.out | 12 +- .../results/clientpositive/groupby_sort_9.q.out | 12 +- .../clientpositive/groupby_sort_skew_1_23.q.out | 540 +++---- .../clientpositive/groupby_sort_test_1.q.out | 20 +- ql/src/test/results/clientpositive/having.q.out | 90 +- ql/src/test/results/clientpositive/having2.q.out | 126 +- ql/src/test/results/clientpositive/hll.q.out | 24 +- .../identity_project_remove_skip.q.out | 18 +- .../results/clientpositive/implicit_cast1.q.out | 8 +- .../implicit_cast_during_insert.q.out | 20 +- .../results/clientpositive/implicit_decimal.q.out | 8 +- .../infer_bucket_sort_dyn_part.q.out | 26 +- .../infer_bucket_sort_grouping_operators.q.out | 78 +- .../infer_bucket_sort_map_operators.q.out | 66 +- .../infer_bucket_sort_num_buckets.q.out | 22 +- .../results/clientpositive/infer_const_type.q.out | 32 +- .../results/clientpositive/infer_join_preds.q.out | 164 +- ql/src/test/results/clientpositive/innerjoin.q.out | 48 +- .../test/results/clientpositive/innerjoin1.q.out | 40 +- ql/src/test/results/clientpositive/input.q.out | 4 +- ql/src/test/results/clientpositive/input0.q.out | 4 +- ql/src/test/results/clientpositive/input11.q.out | 18 +- .../results/clientpositive/input11_limit.q.out | 18 +- ql/src/test/results/clientpositive/input12.q.out | 52 +- ql/src/test/results/clientpositive/input13.q.out | 58 +- ql/src/test/results/clientpositive/input14.q.out | 24 +- .../results/clientpositive/input14_limit.q.out | 24 +- ql/src/test/results/clientpositive/input17.q.out | 22 +- ql/src/test/results/clientpositive/input18.q.out | 24 +- .../test/results/clientpositive/input1_limit.q.out | 54 +- ql/src/test/results/clientpositive/input20.q.out | 26 +- ql/src/test/results/clientpositive/input21.q.out | 10 +- ql/src/test/results/clientpositive/input22.q.out | 12 +- ql/src/test/results/clientpositive/input23.q.out | 22 +- ql/src/test/results/clientpositive/input25.q.out | 36 +- ql/src/test/results/clientpositive/input26.q.out | 40 +- .../test/results/clientpositive/input2_limit.q.out | 10 +- ql/src/test/results/clientpositive/input33.q.out | 26 +- ql/src/test/results/clientpositive/input34.q.out | 20 +- ql/src/test/results/clientpositive/input35.q.out | 20 +- ql/src/test/results/clientpositive/input36.q.out | 20 +- ql/src/test/results/clientpositive/input38.q.out | 18 +- ql/src/test/results/clientpositive/input39.q.out | 30 +- .../test/results/clientpositive/input3_limit.q.out | 26 +- ql/src/test/results/clientpositive/input4.q.out | 2 +- ql/src/test/results/clientpositive/input42.q.out | 20 +- .../test/results/clientpositive/input4_limit.q.out | 18 +- ql/src/test/results/clientpositive/input5.q.out | 22 +- ql/src/test/results/clientpositive/input6.q.out | 18 +- ql/src/test/results/clientpositive/input7.q.out | 16 +- ql/src/test/results/clientpositive/input8.q.out | 16 +- ql/src/test/results/clientpositive/input9.q.out | 18 +- .../clientpositive/input_columnarserde.q.out | 10 +- .../clientpositive/input_dynamicserde.q.out | 6 +- .../results/clientpositive/input_lazyserde.q.out | 10 +- .../results/clientpositive/input_lazyserde2.q.out | 10 +- .../test/results/clientpositive/input_limit.q.out | 6 +- .../test/results/clientpositive/input_part0.q.out | 4 +- .../test/results/clientpositive/input_part1.q.out | 18 +- .../test/results/clientpositive/input_part2.q.out | 34 +- .../test/results/clientpositive/input_part3.q.out | 4 +- .../test/results/clientpositive/input_part4.q.out | 6 +- .../test/results/clientpositive/input_part5.q.out | 18 +- .../test/results/clientpositive/input_part6.q.out | 6 +- .../test/results/clientpositive/input_part7.q.out | 28 +- .../test/results/clientpositive/input_part8.q.out | 6 +- .../test/results/clientpositive/input_part9.q.out | 8 +- .../clientpositive/input_testsequencefile.q.out | 16 +- .../results/clientpositive/input_testxpath.q.out | 16 +- .../results/clientpositive/input_testxpath2.q.out | 18 +- .../results/clientpositive/input_testxpath3.q.out | 6 +- .../results/clientpositive/input_testxpath4.q.out | 16 +- ql/src/test/results/clientpositive/insert1.q.out | 106 +- .../insert2_overwrite_partitions.q.out | 48 +- .../test/results/clientpositive/insert_into1.q.out | 72 +- .../test/results/clientpositive/insert_into2.q.out | 90 +- .../test/results/clientpositive/insert_into3.q.out | 96 +- .../test/results/clientpositive/insert_into4.q.out | 68 +- .../test/results/clientpositive/insert_into5.q.out | 52 +- .../test/results/clientpositive/insert_into6.q.out | 46 +- .../clientpositive/insertoverwrite_bucket.q.out | 40 +- .../test/results/clientpositive/interval_alt.q.out | 6 +- .../clientpositive/interval_arithmetic.q.out | 48 +- ql/src/test/results/clientpositive/join0.q.out | 26 +- ql/src/test/results/clientpositive/join10.q.out | 22 +- ql/src/test/results/clientpositive/join11.q.out | 22 +- ql/src/test/results/clientpositive/join12.q.out | 30 +- ql/src/test/results/clientpositive/join13.q.out | 34 +- ql/src/test/results/clientpositive/join14.q.out | 32 +- ql/src/test/results/clientpositive/join15.q.out | 22 +- ql/src/test/results/clientpositive/join16.q.out | 22 +- ql/src/test/results/clientpositive/join17.q.out | 32 +- ql/src/test/results/clientpositive/join18.q.out | 28 +- .../clientpositive/join18_multi_distinct.q.out | 28 +- ql/src/test/results/clientpositive/join19.q.out | 70 +- ql/src/test/results/clientpositive/join2.q.out | 34 +- ql/src/test/results/clientpositive/join20.q.out | 52 +- ql/src/test/results/clientpositive/join21.q.out | 24 +- ql/src/test/results/clientpositive/join22.q.out | 34 +- ql/src/test/results/clientpositive/join23.q.out | 22 +- ql/src/test/results/clientpositive/join25.q.out | 28 +- ql/src/test/results/clientpositive/join26.q.out | 34 +- ql/src/test/results/clientpositive/join27.q.out | 28 +- ql/src/test/results/clientpositive/join28.q.out | 34 +- ql/src/test/results/clientpositive/join29.q.out | 60 +- ql/src/test/results/clientpositive/join3.q.out | 40 +- ql/src/test/results/clientpositive/join30.q.out | 34 +- ql/src/test/results/clientpositive/join31.q.out | 40 +- ql/src/test/results/clientpositive/join32.q.out | 36 +- ql/src/test/results/clientpositive/join33.q.out | 36 +- ql/src/test/results/clientpositive/join34.q.out | 48 +- ql/src/test/results/clientpositive/join35.q.out | 56 +- ql/src/test/results/clientpositive/join36.q.out | 28 +- ql/src/test/results/clientpositive/join37.q.out | 28 +- ql/src/test/results/clientpositive/join38.q.out | 22 +- ql/src/test/results/clientpositive/join39.q.out | 24 +- ql/src/test/results/clientpositive/join4.q.out | 32 +- ql/src/test/results/clientpositive/join40.q.out | 128 +- ql/src/test/results/clientpositive/join41.q.out | 36 +- ql/src/test/results/clientpositive/join42.q.out | 34 +- ql/src/test/results/clientpositive/join43.q.out | 90 +- ql/src/test/results/clientpositive/join44.q.out | 20 +- ql/src/test/results/clientpositive/join45.q.out | 372 ++--- ql/src/test/results/clientpositive/join46.q.out | 330 ++-- ql/src/test/results/clientpositive/join47.q.out | 350 ++--- ql/src/test/results/clientpositive/join5.q.out | 32 +- ql/src/test/results/clientpositive/join6.q.out | 32 +- ql/src/test/results/clientpositive/join7.q.out | 40 +- ql/src/test/results/clientpositive/join8.q.out | 34 +- ql/src/test/results/clientpositive/join9.q.out | 32 +- .../results/clientpositive/join_alt_syntax.q.out | 198 +-- .../clientpositive/join_cond_pushdown_1.q.out | 122 +- .../clientpositive/join_cond_pushdown_2.q.out | 88 +- .../clientpositive/join_cond_pushdown_3.q.out | 122 +- .../clientpositive/join_cond_pushdown_4.q.out | 88 +- .../join_cond_pushdown_unqual1.q.out | 126 +- .../join_cond_pushdown_unqual2.q.out | 84 +- .../join_cond_pushdown_unqual3.q.out | 126 +- .../join_cond_pushdown_unqual4.q.out | 84 +- .../join_cond_pushdown_unqual5.q.out | 32 +- .../clientpositive/join_emit_interval.q.out | 32 +- .../clientpositive/join_filters_overlap.q.out | 144 +- .../clientpositive/join_grp_diff_keys.q.out | 42 +- .../results/clientpositive/join_hive_626.q.out | 34 +- .../test/results/clientpositive/join_map_ppr.q.out | 40 +- .../join_merge_multi_expressions.q.out | 34 +- .../test/results/clientpositive/join_merging.q.out | 54 +- .../results/clientpositive/join_on_varchar.q.out | 20 +- .../test/results/clientpositive/join_parse.q.out | 148 +- ql/src/test/results/clientpositive/join_rc.q.out | 22 +- .../test/results/clientpositive/join_reorder.q.out | 116 +- .../results/clientpositive/join_reorder2.q.out | 68 +- .../results/clientpositive/join_reorder3.q.out | 68 +- .../results/clientpositive/join_reorder4.q.out | 72 +- ql/src/test/results/clientpositive/join_star.q.out | 140 +- .../test/results/clientpositive/join_thrift.q.out | 18 +- ql/src/test/results/clientpositive/join_vc.q.out | 66 +- ql/src/test/results/clientpositive/join_view.q.out | 22 +- ql/src/test/results/clientpositive/keyword_1.q.out | 8 +- .../results/clientpositive/lateral_view_cp.q.out | 28 +- .../clientpositive/lateral_view_onview.q.out | 102 +- .../clientpositive/lateral_view_outer.q.out | 78 +- .../results/clientpositive/lateral_view_ppd.q.out | 158 +- .../test/results/clientpositive/leftsemijoin.q.out | 32 +- .../results/clientpositive/limit_pushdown2.q.out | 192 +-- .../clientpositive/limit_pushdown_negative.q.out | 114 +- ql/src/test/results/clientpositive/lineage1.q.out | 60 +- .../results/clientpositive/list_bucket_dml_1.q.out | 26 +- .../clientpositive/list_bucket_dml_11.q.out | 26 +- .../clientpositive/list_bucket_dml_12.q.out | 34 +- .../clientpositive/list_bucket_dml_13.q.out | 26 +- .../clientpositive/list_bucket_dml_14.q.out | 24 +- .../results/clientpositive/list_bucket_dml_2.q.out | 26 +- .../results/clientpositive/list_bucket_dml_3.q.out | 26 +- .../results/clientpositive/list_bucket_dml_4.q.out | 44 +- .../results/clientpositive/list_bucket_dml_5.q.out | 26 +- .../results/clientpositive/list_bucket_dml_6.q.out | 44 +- .../results/clientpositive/list_bucket_dml_7.q.out | 44 +- .../results/clientpositive/list_bucket_dml_8.q.out | 26 +- .../results/clientpositive/list_bucket_dml_9.q.out | 44 +- .../list_bucket_query_multiskew_1.q.out | 32 +- .../list_bucket_query_multiskew_2.q.out | 24 +- .../list_bucket_query_multiskew_3.q.out | 24 +- .../list_bucket_query_oneskew_1.q.out | 24 +- .../list_bucket_query_oneskew_2.q.out | 46 +- .../list_bucket_query_oneskew_3.q.out | 8 +- .../results/clientpositive/load_dyn_part1.q.out | 38 +- .../results/clientpositive/load_dyn_part10.q.out | 18 +- .../results/clientpositive/load_dyn_part13.q.out | 38 +- .../results/clientpositive/load_dyn_part2.q.out | 22 +- .../results/clientpositive/load_dyn_part3.q.out | 18 +- .../results/clientpositive/load_dyn_part4.q.out | 18 +- .../results/clientpositive/load_dyn_part8.q.out | 38 +- .../results/clientpositive/load_dyn_part9.q.out | 18 +- .../results/clientpositive/louter_join_ppr.q.out | 84 +- ql/src/test/results/clientpositive/mapjoin1.q.out | 84 +- ql/src/test/results/clientpositive/mapjoin3.q.out | 14 +- ql/src/test/results/clientpositive/mapjoin46.q.out | 252 +-- ql/src/test/results/clientpositive/mapjoin47.q.out | 284 ++-- .../results/clientpositive/mapjoin_distinct.q.out | 92 +- .../mapjoin_filter_on_outerjoin.q.out | 44 +- .../results/clientpositive/mapjoin_memcheck.q.out | 16 +- .../results/clientpositive/mapjoin_subquery.q.out | 48 +- .../results/clientpositive/mapjoin_subquery2.q.out | 24 +- .../clientpositive/mapjoin_test_outer.q.out | 32 +- .../test/results/clientpositive/mapreduce1.q.out | 22 +- .../test/results/clientpositive/mapreduce2.q.out | 22 +- .../test/results/clientpositive/mapreduce3.q.out | 22 +- .../test/results/clientpositive/mapreduce4.q.out | 22 +- .../test/results/clientpositive/mapreduce5.q.out | 20 +- .../test/results/clientpositive/mapreduce6.q.out | 20 +- .../test/results/clientpositive/mapreduce7.q.out | 22 +- .../test/results/clientpositive/mapreduce8.q.out | 22 +- ql/src/test/results/clientpositive/masking_1.q.out | 76 +- .../test/results/clientpositive/masking_10.q.out | 48 +- .../test/results/clientpositive/masking_12.q.out | 78 +- .../results/clientpositive/masking_1_newdb.q.out | 16 +- ql/src/test/results/clientpositive/masking_2.q.out | 84 +- ql/src/test/results/clientpositive/masking_3.q.out | 288 ++-- ql/src/test/results/clientpositive/masking_4.q.out | 62 +- ql/src/test/results/clientpositive/masking_5.q.out | 24 +- ql/src/test/results/clientpositive/masking_7.q.out | 32 +- ql/src/test/results/clientpositive/masking_8.q.out | 32 +- ql/src/test/results/clientpositive/masking_9.q.out | 8 +- .../clientpositive/masking_disablecbo_1.q.out | 76 +- .../clientpositive/masking_disablecbo_2.q.out | 84 +- .../clientpositive/masking_disablecbo_3.q.out | 162 +- .../clientpositive/masking_disablecbo_4.q.out | 44 +- ql/src/test/results/clientpositive/merge1.q.out | 56 +- ql/src/test/results/clientpositive/merge2.q.out | 56 +- ql/src/test/results/clientpositive/merge3.q.out | 42 +- ql/src/test/results/clientpositive/merge4.q.out | 70 +- .../clientpositive/merge_dynamic_partition.q.out | 54 +- .../clientpositive/merge_dynamic_partition2.q.out | 18 +- .../clientpositive/merge_dynamic_partition3.q.out | 18 +- .../clientpositive/merge_dynamic_partition4.q.out | 18 +- .../clientpositive/merge_dynamic_partition5.q.out | 18 +- .../test/results/clientpositive/merge_join_1.q.out | 34 +- ql/src/test/results/clientpositive/mergejoin.q.out | 374 ++--- .../test/results/clientpositive/mergejoins.q.out | 76 +- .../results/clientpositive/mergejoins_mixed.q.out | 452 +++--- .../clientpositive/metadata_only_queries.q.out | 68 +- ql/src/test/results/clientpositive/mm_all.q.out | 18 +- .../clientpositive/multi_insert_distinct.q.out | 76 +- .../results/clientpositive/multi_insert_gby.q.out | 86 +- .../results/clientpositive/multi_insert_gby2.q.out | 34 +- .../results/clientpositive/multi_insert_gby3.q.out | 204 +-- .../results/clientpositive/multi_insert_gby4.q.out | 64 +- .../clientpositive/multi_insert_mixed.q.out | 62 +- ...ulti_insert_move_tasks_share_dependencies.q.out | 928 +++++------ .../clientpositive/multi_insert_union_src.q.out | 54 +- .../clientpositive/multi_insert_with_join2.q.out | 344 ++--- .../results/clientpositive/multi_join_union.q.out | 34 +- .../clientpositive/multigroupby_singlemr.q.out | 246 +-- .../results/clientpositive/named_column_join.q.out | 22 +- .../clientpositive/nested_column_pruning.q.out | 352 ++--- ql/src/test/results/clientpositive/no_hooks.q.out | 22 +- .../results/clientpositive/noalias_subq1.q.out | 8 +- .../clientpositive/nonblock_op_deduplicate.q.out | 24 +- .../test/results/clientpositive/nonmr_fetch.q.out | 206 +-- .../clientpositive/nonmr_fetch_threshold.q.out | 66 +- .../nonreserved_keywords_insert_into1.q.out | 78 +- .../results/clientpositive/notable_alias1.q.out | 24 +- .../results/clientpositive/notable_alias2.q.out | 24 +- .../results/clientpositive/nullformatCTAS.q.out | 6 +- ql/src/test/results/clientpositive/nullgroup.q.out | 56 +- .../test/results/clientpositive/nullgroup2.q.out | 52 +- .../test/results/clientpositive/nullgroup3.q.out | 48 +- .../test/results/clientpositive/nullgroup4.q.out | 66 +- .../clientpositive/nullgroup4_multi_distinct.q.out | 26 +- .../test/results/clientpositive/nullgroup5.q.out | 18 +- .../test/results/clientpositive/nullscript.q.out | 8 +- .../offset_limit_global_optimizer.q.out | 96 +- .../results/clientpositive/optional_outer.q.out | 96 +- .../results/clientpositive/orc_createas1.q.out | 24 +- .../clientpositive/orc_int_type_promotion.q.out | 6 +- .../test/results/clientpositive/orc_merge1.q.out | 54 +- .../test/results/clientpositive/orc_merge10.q.out | 54 +- .../test/results/clientpositive/orc_merge2.q.out | 18 +- .../test/results/clientpositive/orc_merge3.q.out | 16 +- .../test/results/clientpositive/orc_merge4.q.out | 16 +- .../test/results/clientpositive/orc_merge5.q.out | 36 +- .../test/results/clientpositive/orc_merge6.q.out | 40 +- .../results/clientpositive/orc_merge_diff_fs.q.out | 54 +- .../clientpositive/orc_merge_incompat1.q.out | 18 +- .../clientpositive/orc_merge_incompat2.q.out | 18 +- .../clientpositive/orc_nested_column_pruning.q.out | 352 ++--- .../clientpositive/orc_ppd_str_conversion.q.out | 8 +- .../orc_struct_type_vectorization.q.out | 26 +- ql/src/test/results/clientpositive/order.q.out | 24 +- ql/src/test/results/clientpositive/order3.q.out | 116 +- .../results/clientpositive/order_by_expr_1.q.out | 20 +- .../results/clientpositive/outer_join_ppr.q.out | 40 +- .../clientpositive/outer_reference_windowed.q.out | 138 +- ql/src/test/results/clientpositive/parallel.q.out | 42 +- .../results/clientpositive/parallel_colstats.q.out | 42 +- .../results/clientpositive/parallel_join0.q.out | 26 +- .../results/clientpositive/parallel_join1.q.out | 32 +- .../results/clientpositive/parallel_orderby.q.out | 10 +- .../parquet_complex_types_vectorization.q.out | 90 +- .../test/results/clientpositive/parquet_join.q.out | 46 +- .../parquet_map_type_vectorization.q.out | 30 +- .../clientpositive/parquet_no_row_serde.q.out | 20 +- .../parquet_struct_type_vectorization.q.out | 26 +- ...pes_non_dictionary_encoding_vectorization.q.out | 96 +- .../parquet_types_vectorization.q.out | 112 +- .../clientpositive/parquet_vectorization_0.q.out | 222 +-- .../clientpositive/parquet_vectorization_1.q.out | 16 +- .../clientpositive/parquet_vectorization_10.q.out | 8 +- .../clientpositive/parquet_vectorization_11.q.out | 8 +- .../clientpositive/parquet_vectorization_12.q.out | 20 +- .../clientpositive/parquet_vectorization_13.q.out | 44 +- .../clientpositive/parquet_vectorization_14.q.out | 20 +- .../clientpositive/parquet_vectorization_15.q.out | 20 +- .../clientpositive/parquet_vectorization_16.q.out | 16 +- .../clientpositive/parquet_vectorization_17.q.out | 12 +- .../clientpositive/parquet_vectorization_2.q.out | 16 +- .../clientpositive/parquet_vectorization_3.q.out | 16 +- .../clientpositive/parquet_vectorization_4.q.out | 16 +- .../clientpositive/parquet_vectorization_5.q.out | 16 +- .../clientpositive/parquet_vectorization_6.q.out | 8 +- .../clientpositive/parquet_vectorization_7.q.out | 28 +- .../clientpositive/parquet_vectorization_8.q.out | 28 +- .../clientpositive/parquet_vectorization_9.q.out | 16 +- .../parquet_vectorization_decimal_date.q.out | 10 +- .../parquet_vectorization_div0.q.out | 36 +- .../parquet_vectorization_limit.q.out | 86 +- .../parquet_vectorization_offset_limit.q.out | 24 +- .../parquet_vectorization_part_project.q.out | 12 +- .../parquet_vectorization_pushdown.q.out | 16 +- .../clientpositive/partial_column_stats.q.out | 12 +- .../clientpositive/partition_boolexpr.q.out | 34 +- .../partition_condition_remover.q.out | 4 +- .../partition_wise_fileformat2.q.out | 12 +- ql/src/test/results/clientpositive/pcr.q.out | 304 ++-- ql/src/test/results/clientpositive/pcs.q.out | 124 +- .../results/clientpositive/perf/spark/query1.q.out | 380 ++--- .../clientpositive/perf/spark/query10.q.out | 451 +++--- .../clientpositive/perf/spark/query11.q.out | 596 +++---- .../clientpositive/perf/spark/query12.q.out | 54 +- .../clientpositive/perf/spark/query13.q.out | 288 ++-- .../clientpositive/perf/spark/query15.q.out | 140 +- .../clientpositive/perf/spark/query16.q.out | 104 +- .../clientpositive/perf/spark/query17.q.out | 362 ++--- .../clientpositive/perf/spark/query18.q.out | 294 ++-- .../clientpositive/perf/spark/query19.q.out | 215 ++- .../results/clientpositive/perf/spark/query2.q.out | 346 +++-- .../clientpositive/perf/spark/query20.q.out | 54 +- .../clientpositive/perf/spark/query21.q.out | 56 +- .../clientpositive/perf/spark/query22.q.out | 54 +- .../clientpositive/perf/spark/query23.q.out | 1634 +++++++++++--------- .../clientpositive/perf/spark/query24.q.out | 333 ++-- .../clientpositive/perf/spark/query25.q.out | 202 +-- .../clientpositive/perf/spark/query26.q.out | 273 ++-- .../clientpositive/perf/spark/query27.q.out | 222 ++- .../clientpositive/perf/spark/query28.q.out | 140 +- .../clientpositive/perf/spark/query29.q.out | 324 ++-- .../results/clientpositive/perf/spark/query3.q.out | 176 +-- .../clientpositive/perf/spark/query30.q.out | 438 +++--- .../clientpositive/perf/spark/query31.q.out | 1045 +++++++------ .../clientpositive/perf/spark/query32.q.out | 274 ++-- .../clientpositive/perf/spark/query33.q.out | 828 +++++----- .../clientpositive/perf/spark/query34.q.out | 186 ++- .../clientpositive/perf/spark/query35.q.out | 559 +++---- .../clientpositive/perf/spark/query36.q.out | 168 +- .../clientpositive/perf/spark/query37.q.out | 164 +- .../clientpositive/perf/spark/query38.q.out | 144 +- .../clientpositive/perf/spark/query39.q.out | 510 +++--- .../results/clientpositive/perf/spark/query4.q.out | 866 ++++++----- .../clientpositive/perf/spark/query40.q.out | 68 +- .../clientpositive/perf/spark/query42.q.out | 177 ++- .../clientpositive/perf/spark/query43.q.out | 153 +- .../clientpositive/perf/spark/query44.q.out | 545 ++++--- .../clientpositive/perf/spark/query45.q.out | 306 ++-- .../clientpositive/perf/spark/query46.q.out | 210 ++- .../clientpositive/perf/spark/query47.q.out | 525 +++---- .../clientpositive/perf/spark/query48.q.out | 253 ++- .../clientpositive/perf/spark/query49.q.out | 476 +++--- .../results/clientpositive/perf/spark/query5.q.out | 305 ++-- .../clientpositive/perf/spark/query50.q.out | 244 ++- .../clientpositive/perf/spark/query51.q.out | 80 +- .../clientpositive/perf/spark/query52.q.out | 177 ++- .../clientpositive/perf/spark/query53.q.out | 220 ++- .../clientpositive/perf/spark/query54.q.out | 906 +++++------ .../clientpositive/perf/spark/query55.q.out | 177 ++- .../clientpositive/perf/spark/query56.q.out | 830 +++++----- .../clientpositive/perf/spark/query57.q.out | 543 ++++--- .../clientpositive/perf/spark/query58.q.out | 1278 +++++++-------- .../clientpositive/perf/spark/query59.q.out | 482 +++--- .../results/clientpositive/perf/spark/query6.q.out | 544 +++---- .../clientpositive/perf/spark/query60.q.out | 830 +++++----- .../clientpositive/perf/spark/query61.q.out | 634 ++++---- .../clientpositive/perf/spark/query63.q.out | 220 ++- .../clientpositive/perf/spark/query65.q.out | 339 ++-- .../clientpositive/perf/spark/query66.q.out | 440 +++--- .../clientpositive/perf/spark/query67.q.out | 171 +- .../clientpositive/perf/spark/query68.q.out | 210 ++- .../clientpositive/perf/spark/query69.q.out | 511 +++--- .../results/clientpositive/perf/spark/query7.q.out | 273 ++-- .../clientpositive/perf/spark/query70.q.out | 375 +++-- .../clientpositive/perf/spark/query71.q.out | 391 ++--- .../clientpositive/perf/spark/query72.q.out | 472 +++--- .../clientpositive/perf/spark/query73.q.out | 288 ++-- .../clientpositive/perf/spark/query74.q.out | 580 +++---- .../clientpositive/perf/spark/query75.q.out | 1060 +++++++------ .../clientpositive/perf/spark/query76.q.out | 461 +++--- .../clientpositive/perf/spark/query77.q.out | 847 +++++----- .../clientpositive/perf/spark/query78.q.out | 476 +++--- .../clientpositive/perf/spark/query79.q.out | 186 ++- .../results/clientpositive/perf/spark/query8.q.out | 268 ++-- .../clientpositive/perf/spark/query80.q.out | 347 ++--- .../clientpositive/perf/spark/query81.q.out | 440 +++--- .../clientpositive/perf/spark/query82.q.out | 164 +- .../clientpositive/perf/spark/query83.q.out | 937 +++++------ .../clientpositive/perf/spark/query84.q.out | 242 ++- .../clientpositive/perf/spark/query85.q.out | 354 +++-- .../clientpositive/perf/spark/query86.q.out | 58 +- .../clientpositive/perf/spark/query87.q.out | 164 +- .../clientpositive/perf/spark/query88.q.out | 1256 ++++++++------- .../clientpositive/perf/spark/query89.q.out | 226 ++- .../results/clientpositive/perf/spark/query9.q.out | 240 +-- .../clientpositive/perf/spark/query90.q.out | 84 +- .../clientpositive/perf/spark/query91.q.out | 180 ++- .../clientpositive/perf/spark/query92.q.out | 280 ++-- .../clientpositive/perf/spark/query93.q.out | 46 +- .../clientpositive/perf/spark/query94.q.out | 104 +- .../clientpositive/perf/spark/query95.q.out | 148 +- .../clientpositive/perf/spark/query96.q.out | 168 +- .../clientpositive/perf/spark/query97.q.out | 64 +- .../clientpositive/perf/spark/query98.q.out | 52 +- .../clientpositive/perf/spark/query99.q.out | 58 +- .../results/clientpositive/perf/tez/query1.q.out | 70 +- .../results/clientpositive/perf/tez/query10.q.out | 283 ++-- .../results/clientpositive/perf/tez/query11.q.out | 210 ++- .../results/clientpositive/perf/tez/query12.q.out | 46 +- .../results/clientpositive/perf/tez/query13.q.out | 122 +- .../results/clientpositive/perf/tez/query14.q.out | 1172 +++++++------- .../results/clientpositive/perf/tez/query15.q.out | 54 +- .../results/clientpositive/perf/tez/query16.q.out | 175 ++- .../results/clientpositive/perf/tez/query17.q.out | 263 ++-- .../results/clientpositive/perf/tez/query18.q.out | 208 +-- .../results/clientpositive/perf/tez/query19.q.out | 182 +-- .../results/clientpositive/perf/tez/query2.q.out | 183 +-- .../results/clientpositive/perf/tez/query20.q.out | 46 +- .../results/clientpositive/perf/tez/query21.q.out | 44 +- .../results/clientpositive/perf/tez/query22.q.out | 42 +- .../results/clientpositive/perf/tez/query23.q.out | 645 ++++---- .../results/clientpositive/perf/tez/query24.q.out | 332 ++-- .../results/clientpositive/perf/tez/query25.q.out | 251 ++- .../results/clientpositive/perf/tez/query26.q.out | 112 +- .../results/clientpositive/perf/tez/query27.q.out | 96 +- .../results/clientpositive/perf/tez/query28.q.out | 94 +- .../results/clientpositive/perf/tez/query29.q.out | 276 ++-- .../results/clientpositive/perf/tez/query3.q.out | 40 +- .../results/clientpositive/perf/tez/query30.q.out | 84 +- .../results/clientpositive/perf/tez/query31.q.out | 358 ++--- .../results/clientpositive/perf/tez/query32.q.out | 159 +- .../results/clientpositive/perf/tez/query33.q.out | 400 +++-- .../results/clientpositive/perf/tez/query34.q.out | 178 +-- .../results/clientpositive/perf/tez/query35.q.out | 231 +-- .../results/clientpositive/perf/tez/query36.q.out | 90 +- .../results/clientpositive/perf/tez/query37.q.out | 54 +- .../results/clientpositive/perf/tez/query38.q.out | 190 +-- .../results/clientpositive/perf/tez/query39.q.out | 70 +- .../results/clientpositive/perf/tez/query4.q.out | 322 ++-- .../results/clientpositive/perf/tez/query40.q.out | 94 +- .../results/clientpositive/perf/tez/query42.q.out | 42 +- .../results/clientpositive/perf/tez/query43.q.out | 44 +- .../results/clientpositive/perf/tez/query44.q.out | 68 +- .../results/clientpositive/perf/tez/query45.q.out | 174 +-- .../results/clientpositive/perf/tez/query46.q.out | 212 ++- .../results/clientpositive/perf/tez/query47.q.out | 144 +- .../results/clientpositive/perf/tez/query48.q.out | 84 +- .../results/clientpositive/perf/tez/query49.q.out | 158 +- .../results/clientpositive/perf/tez/query5.q.out | 302 ++-- .../results/clientpositive/perf/tez/query50.q.out | 126 +- .../results/clientpositive/perf/tez/query51.q.out | 62 +- .../results/clientpositive/perf/tez/query52.q.out | 42 +- .../results/clientpositive/perf/tez/query53.q.out | 86 +- .../results/clientpositive/perf/tez/query54.q.out | 352 ++--- .../results/clientpositive/perf/tez/query55.q.out | 42 +- .../results/clientpositive/perf/tez/query56.q.out | 140 +- .../results/clientpositive/perf/tez/query57.q.out | 144 +- .../results/clientpositive/perf/tez/query58.q.out | 310 ++-- .../results/clientpositive/perf/tez/query59.q.out | 209 +-- .../results/clientpositive/perf/tez/query6.q.out | 288 ++-- .../results/clientpositive/perf/tez/query60.q.out | 146 +- .../results/clientpositive/perf/tez/query61.q.out | 180 +-- .../results/clientpositive/perf/tez/query63.q.out | 86 +- .../results/clientpositive/perf/tez/query64.q.out | 961 +++++------- .../results/clientpositive/perf/tez/query65.q.out | 227 ++- .../results/clientpositive/perf/tez/query66.q.out | 182 +-- .../results/clientpositive/perf/tez/query67.q.out | 110 +- .../results/clientpositive/perf/tez/query68.q.out | 212 ++- .../results/clientpositive/perf/tez/query69.q.out | 349 +++-- .../results/clientpositive/perf/tez/query7.q.out | 112 +- .../results/clientpositive/perf/tez/query70.q.out | 210 +-- .../results/clientpositive/perf/tez/query71.q.out | 98 +- .../results/clientpositive/perf/tez/query72.q.out | 290 ++-- .../results/clientpositive/perf/tez/query73.q.out | 178 +-- .../results/clientpositive/perf/tez/query74.q.out | 202 ++- .../results/clientpositive/perf/tez/query75.q.out | 212 +-- .../results/clientpositive/perf/tez/query76.q.out | 237 +-- .../results/clientpositive/perf/tez/query77.q.out | 286 ++-- .../results/clientpositive/perf/tez/query78.q.out | 292 ++-- .../results/clientpositive/perf/tez/query79.q.out | 178 +-- .../results/clientpositive/perf/tez/query8.q.out | 96 +- .../results/clientpositive/perf/tez/query80.q.out | 328 ++-- .../results/clientpositive/perf/tez/query81.q.out | 86 +- .../results/clientpositive/perf/tez/query82.q.out | 54 +- .../results/clientpositive/perf/tez/query83.q.out | 98 +- .../results/clientpositive/perf/tez/query84.q.out | 56 +- .../results/clientpositive/perf/tez/query85.q.out | 140 +- .../results/clientpositive/perf/tez/query86.q.out | 78 +- .../results/clientpositive/perf/tez/query87.q.out | 216 ++- .../results/clientpositive/perf/tez/query88.q.out | 216 +-- .../results/clientpositive/perf/tez/query89.q.out | 90 +- .../results/clientpositive/perf/tez/query9.q.out | 132 +- .../results/clientpositive/perf/tez/query90.q.out | 76 +- .../results/clientpositive/perf/tez/query91.q.out | 76 +- .../results/clientpositive/perf/tez/query92.q.out | 165 +- .../results/clientpositive/perf/tez/query93.q.out | 50 +- .../results/clientpositive/perf/tez/query94.q.out | 175 ++- .../results/clientpositive/perf/tez/query95.q.out | 305 ++-- .../results/clientpositive/perf/tez/query96.q.out | 50 +- .../results/clientpositive/perf/tez/query97.q.out | 44 +- .../results/clientpositive/perf/tez/query98.q.out | 44 +- .../results/clientpositive/perf/tez/query99.q.out | 126 +- .../test/results/clientpositive/pointlookup.q.out | 24 +- .../test/results/clientpositive/pointlookup2.q.out | 228 +-- .../test/results/clientpositive/pointlookup3.q.out | 200 +-- .../test/results/clientpositive/pointlookup4.q.out | 24 +- .../clientpositive/position_alias_test_1.q.out | 34 +- ql/src/test/results/clientpositive/ppd1.q.out | 16 +- ql/src/test/results/clientpositive/ppd2.q.out | 58 +- .../results/clientpositive/ppd_clusterby.q.out | 70 +- .../results/clientpositive/ppd_constant_expr.q.out | 32 +- ql/src/test/results/clientpositive/ppd_gby.q.out | 32 +- ql/src/test/results/clientpositive/ppd_gby2.q.out | 44 +- .../test/results/clientpositive/ppd_gby_join.q.out | 52 +- ql/src/test/results/clientpositive/ppd_join.q.out | 44 +- ql/src/test/results/clientpositive/ppd_join2.q.out | 72 +- ql/src/test/results/clientpositive/ppd_join3.q.out | 64 +- ql/src/test/results/clientpositive/ppd_join4.q.out | 20 +- ql/src/test/results/clientpositive/ppd_join5.q.out | 68 +- .../results/clientpositive/ppd_join_filter.q.out | 120 +- .../results/clientpositive/ppd_multi_insert.q.out | 140 +- .../results/clientpositive/ppd_outer_join1.q.out | 40 +- .../results/clientpositive/ppd_outer_join2.q.out | 40 +- .../results/clientpositive/ppd_outer_join3.q.out | 40 +- .../results/clientpositive/ppd_outer_join4.q.out | 60 +- .../results/clientpositive/ppd_outer_join5.q.out | 102 +- .../test/results/clientpositive/ppd_random.q.out | 48 +- .../clientpositive/ppd_repeated_alias.q.out | 100 +- .../results/clientpositive/ppd_transform.q.out | 42 +- .../test/results/clientpositive/ppd_udf_case.q.out | 52 +- .../test/results/clientpositive/ppd_udf_col.q.out | 166 +- ql/src/test/results/clientpositive/ppd_udtf.q.out | 14 +- ql/src/test/results/clientpositive/ppd_union.q.out | 16 +- ql/src/test/results/clientpositive/ppd_vc.q.out | 34 +- .../results/clientpositive/ppd_windowing1.q.out | 410 ++--- .../clientpositive/ppr_allchildsarenull.q.out | 16 +- .../results/clientpositive/ppr_pushdown3.q.out | 16 +- .../results/clientpositive/ptf_matchpath.q.out | 42 +- .../results/clientpositive/ptfgroupbyjoin.q.out | 86 +- ql/src/test/results/clientpositive/push_or.q.out | 12 +- .../clientpositive/query_result_fileformat.q.out | 16 +- ql/src/test/results/clientpositive/quote1.q.out | 26 +- .../results/clientpositive/quotedid_basic.q.out | 72 +- .../clientpositive/quotedid_partition.q.out | 16 +- .../results/clientpositive/quotedid_skew.q.out | 44 +- .../clientpositive/rand_partitionpruner1.q.out | 8 +- .../clientpositive/rand_partitionpruner2.q.out | 18 +- .../clientpositive/rand_partitionpruner3.q.out | 16 +- .../results/clientpositive/rcfile_null_value.q.out | 32 +- .../reduceSinkDeDuplication_pRS_key_empty.q.out | 26 +- .../reduce_deduplicate_exclude_join.q.out | 20 +- .../reduce_deduplicate_extended2.q.out | 230 +-- ql/src/test/results/clientpositive/regex_col.q.out | 84 +- .../results/clientpositive/regexp_extract.q.out | 28 +- ql/src/test/results/clientpositive/reloadJar.q.out | 8 +- .../results/clientpositive/router_join_ppr.q.out | 84 +- ql/src/test/results/clientpositive/row__id.q.out | 18 +- .../runtime_skewjoin_mapjoin_spark.q.out | 118 +- ql/src/test/results/clientpositive/sample1.q.out | 18 +- ql/src/test/results/clientpositive/sample3.q.out | 8 +- ql/src/test/results/clientpositive/sample5.q.out | 18 +- ql/src/test/results/clientpositive/sample6.q.out | 102 +- ql/src/test/results/clientpositive/sample7.q.out | 18 +- ql/src/test/results/clientpositive/sample8.q.out | 58 +- ql/src/test/results/clientpositive/sample9.q.out | 8 +- .../test/results/clientpositive/script_pipe.q.out | 24 +- .../results/clientpositive/select_as_omitted.q.out | 12 +- .../clientpositive/select_column_pruning.q.out | 36 +- .../clientpositive/select_transform_hint.q.out | 32 +- .../clientpositive/select_unquote_and.q.out | 8 +- .../clientpositive/select_unquote_not.q.out | 8 +- .../results/clientpositive/select_unquote_or.q.out | 8 +- ql/src/test/results/clientpositive/semijoin2.q.out | 56 +- ql/src/test/results/clientpositive/semijoin3.q.out | 18 +- ql/src/test/results/clientpositive/semijoin4.q.out | 60 +- ql/src/test/results/clientpositive/semijoin5.q.out | 64 +- .../clientpositive/serde_user_properties.q.out | 34 +- .../clientpositive/set_processor_namespaces.q.out | 8 +- .../results/clientpositive/set_variable_sub.q.out | 24 +- .../test/results/clientpositive/setop_subq.q.out | 164 +- ql/src/test/results/clientpositive/skewjoin.q.out | 214 +-- .../results/clientpositive/skewjoin_mapjoin1.q.out | 136 +- .../clientpositive/skewjoin_mapjoin10.q.out | 160 +- .../clientpositive/skewjoin_mapjoin11.q.out | 36 +- .../results/clientpositive/skewjoin_mapjoin2.q.out | 80 +- .../results/clientpositive/skewjoin_mapjoin3.q.out | 36 +- .../results/clientpositive/skewjoin_mapjoin4.q.out | 48 +- .../results/clientpositive/skewjoin_mapjoin5.q.out | 50 +- .../results/clientpositive/skewjoin_mapjoin6.q.out | 60 +- .../results/clientpositive/skewjoin_mapjoin7.q.out | 80 +- .../results/clientpositive/skewjoin_mapjoin8.q.out | 24 +- .../results/clientpositive/skewjoin_mapjoin9.q.out | 46 +- .../results/clientpositive/skewjoin_noskew.q.out | 26 +- .../clientpositive/skewjoin_onesideskew.q.out | 22 +- .../clientpositive/skewjoin_union_remove_1.q.out | 160 +- .../clientpositive/skewjoin_union_remove_2.q.out | 56 +- .../test/results/clientpositive/skewjoinopt1.q.out | 168 +- .../results/clientpositive/skewjoinopt10.q.out | 68 +- .../results/clientpositive/skewjoinopt11.q.out | 96 +- .../results/clientpositive/skewjoinopt12.q.out | 44 +- .../results/clientpositive/skewjoinopt13.q.out | 32 +- .../results/clientpositive/skewjoinopt14.q.out | 56 +- .../results/clientpositive/skewjoinopt16.q.out | 44 +- .../results/clientpositive/skewjoinopt17.q.out | 88 +- .../results/clientpositive/skewjoinopt18.q.out | 20 +- .../results/clientpositive/skewjoinopt19.q.out | 44 +- .../test/results/clientpositive/skewjoinopt2.q.out | 192 +-- .../results/clientpositive/skewjoinopt20.q.out | 44 +- .../results/clientpositive/skewjoinopt21.q.out | 44 +- .../test/results/clientpositive/skewjoinopt3.q.out | 88 +- .../test/results/clientpositive/skewjoinopt4.q.out | 88 +- .../test/results/clientpositive/skewjoinopt5.q.out | 44 +- .../test/results/clientpositive/skewjoinopt6.q.out | 44 +- .../test/results/clientpositive/skewjoinopt7.q.out | 60 +- .../test/results/clientpositive/skewjoinopt8.q.out | 60 +- .../test/results/clientpositive/skewjoinopt9.q.out | 56 +- .../test/results/clientpositive/smb_mapjoin9.q.out | 12 +- .../results/clientpositive/smb_mapjoin_1.q.out | 20 +- .../results/clientpositive/smb_mapjoin_10.q.out | 4 +- .../results/clientpositive/smb_mapjoin_11.q.out | 20 +- .../results/clientpositive/smb_mapjoin_12.q.out | 8 +- .../results/clientpositive/smb_mapjoin_13.q.out | 24 +- .../results/clientpositive/smb_mapjoin_16.q.out | 4 +- .../results/clientpositive/smb_mapjoin_2.q.out | 20 +- .../results/clientpositive/smb_mapjoin_20.q.out | 66 +- .../results/clientpositive/smb_mapjoin_21.q.out | 116 +- .../results/clientpositive/smb_mapjoin_22.q.out | 12 +- .../results/clientpositive/smb_mapjoin_25.q.out | 74 +- .../results/clientpositive/smb_mapjoin_3.q.out | 20 +- .../results/clientpositive/smb_mapjoin_46.q.out | 182 +-- .../results/clientpositive/smb_mapjoin_47.q.out | 198 +-- .../results/clientpositive/smb_mapjoin_7.q.out | 2 +- ql/src/test/results/clientpositive/sort.q.out | 10 +- .../clientpositive/sort_merge_join_desc_1.q.out | 4 +- .../clientpositive/sort_merge_join_desc_2.q.out | 4 +- .../clientpositive/sort_merge_join_desc_3.q.out | 4 +- .../clientpositive/sort_merge_join_desc_4.q.out | 10 +- .../clientpositive/sort_merge_join_desc_5.q.out | 4 +- .../clientpositive/sort_merge_join_desc_6.q.out | 10 +- .../clientpositive/sort_merge_join_desc_7.q.out | 10 +- .../clientpositive/sort_merge_join_desc_8.q.out | 14 +- ql/src/test/results/clientpositive/source.q.out | 8 +- .../clientpositive/spark/spark_local_queries.q.out | 12 +- .../special_character_in_tabnames_2.q.out | 8 +- ql/src/test/results/clientpositive/stats0.q.out | 68 +- ql/src/test/results/clientpositive/stats1.q.out | 28 +- ql/src/test/results/clientpositive/stats10.q.out | 24 +- ql/src/test/results/clientpositive/stats12.q.out | 2 +- ql/src/test/results/clientpositive/stats13.q.out | 2 +- ql/src/test/results/clientpositive/stats2.q.out | 8 +- ql/src/test/results/clientpositive/stats4.q.out | 38 +- ql/src/test/results/clientpositive/stats7.q.out | 2 +- ql/src/test/results/clientpositive/stats8.q.out | 10 +- .../clientpositive/stats_empty_dyn_part.q.out | 20 +- .../clientpositive/stats_empty_partition2.q.out | 20 +- .../results/clientpositive/stats_noscan_2.q.out | 12 +- ql/src/test/results/clientpositive/structin.q.out | 16 +- ql/src/test/results/clientpositive/subq.q.out | 8 +- ql/src/test/results/clientpositive/subq2.q.out | 12 +- .../clientpositive/subq_where_serialization.q.out | 18 +- .../results/clientpositive/subquery_alias.q.out | 12 +- .../results/clientpositive/subquery_exists.q.out | 136 +- .../clientpositive/subquery_exists_having.q.out | 60 +- .../clientpositive/subquery_multiinsert.q.out | 166 +- .../clientpositive/subquery_notexists.q.out | 150 +- .../clientpositive/subquery_notexists_having.q.out | 74 +- .../clientpositive/subquery_notin_having.q.out | 286 ++-- .../clientpositive/subquery_unqual_corr_expr.q.out | 62 +- .../clientpositive/subquery_unqualcolumnrefs.q.out | 130 +- .../clientpositive/symlink_text_input_format.q.out | 40 +- .../test/results/clientpositive/tablevalues.q.out | 56 +- .../temp_table_display_colstats_tbllvl.q.out | 36 +- .../results/clientpositive/temp_table_join1.q.out | 66 +- .../clientpositive/timestamp_ints_casts.q.out | 16 +- .../test/results/clientpositive/transform1.q.out | 8 +- .../results/clientpositive/transform_ppr1.q.out | 14 +- .../results/clientpositive/transform_ppr2.q.out | 14 +- .../truncate_column_list_bucket.q.out | 16 +- .../results/clientpositive/type_widening.q.out | 24 +- .../clientpositive/udaf_binarysetfunctions.q.out | 18 +- .../udaf_binarysetfunctions_no_cbo.q.out | 16 +- .../clientpositive/udaf_percentile_approx_23.q.out | 24 +- ql/src/test/results/clientpositive/udf1.q.out | 18 +- ql/src/test/results/clientpositive/udf2.q.out | 6 +- ql/src/test/results/clientpositive/udf8.q.out | 14 +- ql/src/test/results/clientpositive/udf9.q.out | 8 +- .../test/results/clientpositive/udf_10_trims.q.out | 18 +- .../test/results/clientpositive/udf_between.q.out | 28 +- .../clientpositive/udf_case_column_pruning.q.out | 28 +- .../results/clientpositive/udf_case_thrift.q.out | 4 +- .../clientpositive/udf_character_length.q.out | 24 +- .../results/clientpositive/udf_concat_ws.q.out | 4 +- ql/src/test/results/clientpositive/udf_count.q.out | 30 +- .../results/clientpositive/udf_find_in_set.q.out | 4 +- .../clientpositive/udf_folder_constants.q.out | 22 +- .../clientpositive/udf_get_json_object.q.out | 4 +- ql/src/test/results/clientpositive/udf_hour.q.out | 6 +- .../test/results/clientpositive/udf_in_file.q.out | 8 +- .../clientpositive/udf_isnull_isnotnull.q.out | 8 +- .../test/results/clientpositive/udf_length.q.out | 20 +- ql/src/test/results/clientpositive/udf_like.q.out | 6 +- ql/src/test/results/clientpositive/udf_lower.q.out | 8 +- .../test/results/clientpositive/udf_minute.q.out | 8 +- .../test/results/clientpositive/udf_notequal.q.out | 12 +- .../results/clientpositive/udf_octet_length.q.out | 20 +- .../results/clientpositive/udf_parse_url.q.out | 8 +- .../test/results/clientpositive/udf_reflect.q.out | 4 +- .../test/results/clientpositive/udf_reflect2.q.out | 6 +- .../test/results/clientpositive/udf_reverse.q.out | 16 +- .../test/results/clientpositive/udf_second.q.out | 6 +- ql/src/test/results/clientpositive/udf_size.q.out | 8 +- .../clientpositive/udf_to_unix_timestamp.q.out | 12 +- .../results/clientpositive/udf_trunc_number.q.out | 20 +- ql/src/test/results/clientpositive/udf_union.q.out | 4 +- .../results/clientpositive/udtf_json_tuple.q.out | 102 +- .../clientpositive/udtf_parse_url_tuple.q.out | 98 +- ql/src/test/results/clientpositive/union.q.out | 20 +- ql/src/test/results/clientpositive/union11.q.out | 58 +- ql/src/test/results/clientpositive/union13.q.out | 16 +- ql/src/test/results/clientpositive/union14.q.out | 32 +- ql/src/test/results/clientpositive/union15.q.out | 42 +- ql/src/test/results/clientpositive/union17.q.out | 54 +- ql/src/test/results/clientpositive/union18.q.out | 50 +- ql/src/test/results/clientpositive/union19.q.out | 54 +- ql/src/test/results/clientpositive/union20.q.out | 32 +- ql/src/test/results/clientpositive/union21.q.out | 50 +- ql/src/test/results/clientpositive/union22.q.out | 68 +- ql/src/test/results/clientpositive/union23.q.out | 22 +- ql/src/test/results/clientpositive/union24.q.out | 136 +- ql/src/test/results/clientpositive/union25.q.out | 46 +- ql/src/test/results/clientpositive/union26.q.out | 56 +- ql/src/test/results/clientpositive/union27.q.out | 34 +- ql/src/test/results/clientpositive/union28.q.out | 64 +- ql/src/test/results/clientpositive/union29.q.out | 52 +- ql/src/test/results/clientpositive/union30.q.out | 80 +- ql/src/test/results/clientpositive/union31.q.out | 190 +-- ql/src/test/results/clientpositive/union32.q.out | 144 +- ql/src/test/results/clientpositive/union33.q.out | 92 +- ql/src/test/results/clientpositive/union34.q.out | 72 +- ql/src/test/results/clientpositive/union37.q.out | 76 +- ql/src/test/results/clientpositive/union5.q.out | 40 +- ql/src/test/results/clientpositive/union6.q.out | 28 +- ql/src/test/results/clientpositive/union7.q.out | 32 +- ql/src/test/results/clientpositive/union8.q.out | 24 +- .../results/clientpositive/union_lateralview.q.out | 72 +- .../test/results/clientpositive/union_offcbo.q.out | 304 ++-- .../test/results/clientpositive/union_paren.q.out | 16 +- .../results/clientpositive/union_pos_alias.q.out | 88 +- ql/src/test/results/clientpositive/union_ppr.q.out | 28 +- .../results/clientpositive/union_remove_1.q.out | 24 +- .../results/clientpositive/union_remove_10.q.out | 24 +- .../results/clientpositive/union_remove_11.q.out | 30 +- .../results/clientpositive/union_remove_12.q.out | 24 +- .../results/clientpositive/union_remove_13.q.out | 30 +- .../results/clientpositive/union_remove_14.q.out | 24 +- .../results/clientpositive/union_remove_15.q.out | 28 +- .../results/clientpositive/union_remove_16.q.out | 28 +- .../results/clientpositive/union_remove_17.q.out | 20 +- .../results/clientpositive/union_remove_18.q.out | 28 +- .../results/clientpositive/union_remove_19.q.out | 76 +- .../results/clientpositive/union_remove_2.q.out | 24 +- .../results/clientpositive/union_remove_20.q.out | 28 +- .../results/clientpositive/union_remove_21.q.out | 24 +- .../results/clientpositive/union_remove_22.q.out | 56 +- .../results/clientpositive/union_remove_23.q.out | 38 +- .../results/clientpositive/union_remove_24.q.out | 28 +- .../results/clientpositive/union_remove_25.q.out | 88 +- .../results/clientpositive/union_remove_3.q.out | 30 +- .../results/clientpositive/union_remove_4.q.out | 24 +- .../results/clientpositive/union_remove_5.q.out | 24 +- .../results/clientpositive/union_remove_6.q.out | 32 +- .../clientpositive/union_remove_6_subq.q.out | 74 +- .../results/clientpositive/union_remove_7.q.out | 24 +- .../results/clientpositive/union_remove_8.q.out | 24 +- .../results/clientpositive/union_remove_9.q.out | 32 +- .../test/results/clientpositive/union_view.q.out | 380 ++--- .../clientpositive/unionall_unbalancedppd.q.out | 32 +- .../results/clientpositive/updateBasicStats.q.out | 48 +- .../clientpositive/vector_aggregate_9.q.out | 42 +- .../vector_aggregate_without_gby.q.out | 14 +- .../clientpositive/vector_between_columns.q.out | 30 +- .../vector_binary_join_groupby.q.out | 64 +- .../results/clientpositive/vector_bround.q.out | 6 +- .../clientpositive/vector_case_when_1.q.out | 18 +- .../clientpositive/vector_case_when_2.q.out | 30 +- .../clientpositive/vector_cast_constant.q.out | 20 +- .../results/clientpositive/vector_char_2.q.out | 36 +- .../results/clientpositive/vector_char_4.q.out | 6 +- .../clientpositive/vector_char_mapjoin1.q.out | 6 +- .../results/clientpositive/vector_coalesce_2.q.out | 40 +- .../results/clientpositive/vector_coalesce_3.q.out | 14 +- .../results/clientpositive/vector_coalesce_4.q.out | 10 +- .../test/results/clientpositive/vector_count.q.out | 48 +- .../vector_custom_udf_configure.q.out | 6 +- .../results/clientpositive/vector_data_types.q.out | 36 +- .../results/clientpositive/vector_date_1.q.out | 68 +- .../results/clientpositive/vector_decimal_1.q.out | 90 +- .../clientpositive/vector_decimal_10_0.q.out | 20 +- .../results/clientpositive/vector_decimal_5.q.out | 6 +- .../results/clientpositive/vector_decimal_6.q.out | 50 +- .../clientpositive/vector_decimal_aggregate.q.out | 64 +- .../clientpositive/vector_decimal_cast.q.out | 20 +- .../vector_decimal_expressions.q.out | 28 +- .../clientpositive/vector_decimal_mapjoin.q.out | 96 +- .../clientpositive/vector_decimal_math_funcs.q.out | 16 +- .../clientpositive/vector_decimal_precision.q.out | 28 +- .../clientpositive/vector_decimal_round.q.out | 60 +- .../clientpositive/vector_decimal_round_2.q.out | 40 +- .../clientpositive/vector_decimal_trailing.q.out | 10 +- .../clientpositive/vector_decimal_udf2.q.out | 32 +- .../results/clientpositive/vector_distinct_2.q.out | 14 +- .../test/results/clientpositive/vector_elt.q.out | 10 +- .../clientpositive/vector_empty_where.q.out | 78 +- .../clientpositive/vector_gather_stats.q.out | 2 +- .../results/clientpositive/vector_groupby4.q.out | 26 +- .../results/clientpositive/vector_groupby6.q.out | 26 +- .../results/clientpositive/vector_groupby_3.q.out | 14 +- .../clientpositive/vector_groupby_mapjoin.q.out | 50 +- .../clientpositive/vector_groupby_reduce.q.out | 84 +- .../clientpositive/vector_grouping_sets.q.out | 40 +- .../results/clientpositive/vector_if_expr.q.out | 12 +- .../clientpositive/vector_include_no_sel.q.out | 10 +- .../results/clientpositive/vector_interval_1.q.out | 80 +- .../vector_interval_arithmetic.q.out | 60 +- .../clientpositive/vector_interval_mapjoin.q.out | 18 +- .../clientpositive/vector_join_part_col_char.q.out | 16 +- .../clientpositive/vector_left_outer_join.q.out | 24 +- .../clientpositive/vector_left_outer_join2.q.out | 84 +- .../results/clientpositive/vector_map_order.q.out | 6 +- .../vector_mr_diff_schema_alias.q.out | 44 +- .../clientpositive/vector_multi_insert.q.out | 6 +- .../vector_non_constant_in_expr.q.out | 8 +- .../vector_non_string_partition.q.out | 28 +- .../test/results/clientpositive/vector_nvl.q.out | 18 +- .../results/clientpositive/vector_orderby_5.q.out | 16 +- .../clientpositive/vector_outer_join0.q.out | 24 +- .../clientpositive/vector_outer_join1.q.out | 48 +- .../clientpositive/vector_outer_join2.q.out | 24 +- .../clientpositive/vector_outer_join3.q.out | 6 +- .../clientpositive/vector_outer_join4.q.out | 6 +- .../clientpositive/vector_outer_join6.q.out | 4 +- .../results/clientpositive/vector_reduce1.q.out | 10 +- .../results/clientpositive/vector_reduce2.q.out | 10 +- .../results/clientpositive/vector_reduce3.q.out | 10 +- .../vector_reduce_groupby_decimal.q.out | 18 +- .../vector_reduce_groupby_duplicate_cols.q.out | 16 +- .../clientpositive/vector_string_concat.q.out | 26 +- .../results/clientpositive/vector_struct_in.q.out | 56 +- .../test/results/clientpositive/vector_udf3.q.out | 6 +- .../vector_udf_character_length.q.out | 18 +- .../clientpositive/vector_udf_octet_length.q.out | 12 +- .../results/clientpositive/vector_varchar_4.q.out | 6 +- .../clientpositive/vector_varchar_mapjoin1.q.out | 60 +- .../clientpositive/vector_varchar_simple.q.out | 40 +- .../clientpositive/vector_when_case_null.q.out | 12 +- .../results/clientpositive/vectorization_1.q.out | 16 +- .../results/clientpositive/vectorization_10.q.out | 8 +- .../results/clientpositive/vectorization_11.q.out | 8 +- .../results/clientpositive/vectorization_12.q.out | 20 +- .../results/clientpositive/vectorization_13.q.out | 44 +- .../results/clientpositive/vectorization_14.q.out | 20 +- .../results/clientpositive/vectorization_15.q.out | 20 +- .../results/clientpositive/vectorization_16.q.out | 16 +- .../results/clientpositive/vectorization_17.q.out | 12 +- .../results/clientpositive/vectorization_2.q.out | 16 +- .../results/clientpositive/vectorization_3.q.out | 16 +- .../results/clientpositive/vectorization_4.q.out | 16 +- .../results/clientpositive/vectorization_5.q.out | 16 +- .../results/clientpositive/vectorization_6.q.out | 8 +- .../results/clientpositive/vectorization_7.q.out | 28 +- .../results/clientpositive/vectorization_8.q.out | 28 +- .../results/clientpositive/vectorization_9.q.out | 16 +- .../vectorization_decimal_date.q.out | 10 +- .../clientpositive/vectorization_limit.q.out | 98 +- .../clientpositive/vectorization_nested_udf.q.out | 12 +- .../vectorization_numeric_overflows.q.out | 120 +- .../vectorization_offset_limit.q.out | 24 +- .../vectorization_parquet_projection.q.out | 56 +- .../vectorization_part_project.q.out | 12 +- .../clientpositive/vectorization_pushdown.q.out | 16 +- .../clientpositive/vectorized_bucketmapjoin1.q.out | 12 +- .../results/clientpositive/vectorized_case.q.out | 76 +- .../results/clientpositive/vectorized_casts.q.out | 8 +- .../clientpositive/vectorized_context.q.out | 28 +- .../clientpositive/vectorized_date_funcs.q.out | 42 +- .../clientpositive/vectorized_distinct_gby.q.out | 26 +- .../clientpositive/vectorized_mapjoin.q.out | 26 +- .../clientpositive/vectorized_mapjoin3.q.out | 54 +- .../clientpositive/vectorized_math_funcs.q.out | 8 +- .../clientpositive/vectorized_parquet_types.q.out | 54 +- .../clientpositive/vectorized_shufflejoin.q.out | 34 +- .../clientpositive/vectorized_string_funcs.q.out | 8 +- .../clientpositive/vectorized_timestamp.q.out | 56 +- .../vectorized_timestamp_funcs.q.out | 80 +- .../vectorized_timestamp_ints_casts.q.out | 16 +- ql/src/test/results/clientpositive/view_cbo.q.out | 68 +- .../results/clientpositive/windowing_gby2.q.out | 114 +- .../results/clientpositive/windowing_navfn.q.out | 12 +- .../clientpositive/windowing_streaming.q.out | 40 +- 1235 files changed, 51831 insertions(+), 52542 deletions(-) diff --git a/accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out b/accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out index 0389362b1b..9316f6542f 100644 --- a/accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out +++ b/accumulo-handler/src/test/results/positive/accumulo_predicate_pushdown.q.out @@ -39,11 +39,11 @@ STAGE PLANS: TableScan alias: accumulo_pushdown filterExpr: (key > '90') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select * from accumulo_pushdown where key>'90' @@ -178,11 +178,11 @@ STAGE PLANS: TableScan alias: accumulo_pushdown filterExpr: (key >= '90') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select * from accumulo_pushdown where key>=cast(40 + 50 as string) @@ -214,17 +214,17 @@ STAGE PLANS: TableScan alias: accumulo_pushdown filterExpr: (key > '90') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value like '%9%') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -267,17 +267,17 @@ STAGE PLANS: TableScan alias: accumulo_pushdown filterExpr: (key >= '90') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) = UDFToDouble(UDFToInteger(value))) and (value like '%9%')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -316,17 +316,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: accumulo_pushdown - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -363,11 +363,11 @@ STAGE PLANS: Processor Tree: TableScan alias: accumulo_pushdown - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: explain select * from accumulo_pushdown @@ -387,17 +387,17 @@ STAGE PLANS: TableScan alias: accumulo_pushdown filterExpr: (not NVL((key < '90'),false)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not NVL((key < '90'),false)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -427,17 +427,17 @@ STAGE PLANS: TableScan alias: accumulo_pushdown filterExpr: ((key <= '80') or (value like '%90%')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key <= '80') or (value like '%90%')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -467,11 +467,11 @@ STAGE PLANS: TableScan alias: accumulo_pushdown filterExpr: ((key > '281') and (key < '287')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select * from accumulo_pushdown where key > '281' @@ -503,17 +503,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: accumulo_pushdown - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key <= '90') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/accumulo-handler/src/test/results/positive/accumulo_queries.q.out b/accumulo-handler/src/test/results/positive/accumulo_queries.q.out index d0fdae42d8..eac42c9d1d 100644 --- a/accumulo-handler/src/test/results/positive/accumulo_queries.q.out +++ b/accumulo-handler/src/test/results/positive/accumulo_queries.q.out @@ -63,17 +63,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) % 2.0D) = 0.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.accumulo.mr.HiveAccumuloTableInputFormat output format: org.apache.hadoop.hive.accumulo.mr.HiveAccumuloTableOutputFormat @@ -136,34 +136,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: accumulo_table_1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -173,11 +173,11 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -192,20 +192,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -288,34 +288,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: accumulo_table_1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < 120) and (key > 100)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: accumulo_table_2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key < 120) and (key > 100)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -325,11 +325,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -344,16 +344,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -529,21 +529,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -552,7 +552,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -565,26 +565,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: accumulo_table_1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -594,14 +594,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 26125 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 26125 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 26125 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.accumulo.mr.HiveAccumuloTableInputFormat output format: org.apache.hadoop.hive.accumulo.mr.HiveAccumuloTableOutputFormat diff --git a/accumulo-handler/src/test/results/positive/accumulo_single_sourced_multi_insert.q.out b/accumulo-handler/src/test/results/positive/accumulo_single_sourced_multi_insert.q.out index 7e36206b9e..a066f408b6 100644 --- a/accumulo-handler/src/test/results/positive/accumulo_single_sourced_multi_insert.q.out +++ b/accumulo-handler/src/test/results/positive/accumulo_single_sourced_multi_insert.q.out @@ -72,17 +72,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 50) and (key > 0)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), '' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9405 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -91,26 +91,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), '' (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9405 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 100) and (key > 50)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), '' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9625 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9625 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.accumulo.mr.HiveAccumuloTableInputFormat output format: org.apache.hadoop.hive.accumulo.mr.HiveAccumuloTableOutputFormat @@ -121,10 +121,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 402d66d9bf..e7145ebe00 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -2368,7 +2368,7 @@ private static void populateLlapDaemonVarsSet(Set llapDaemonVarsSetLocal "entries/values can be specified using this config."), // statistics annotation fetches column statistics for all required columns which can // be very expensive sometimes - HIVE_STATS_FETCH_COLUMN_STATS("hive.stats.fetch.column.stats", false, + HIVE_STATS_FETCH_COLUMN_STATS("hive.stats.fetch.column.stats", true, "Annotation of operator tree with statistics information requires column statistics.\n" + "Column statistics are fetched from metastore. Fetching column statistics for each needed column\n" + "can be expensive when the number of columns is high. This flag can be used to disable fetching\n" + diff --git a/contrib/src/test/results/clientpositive/serde_typedbytes.q.out b/contrib/src/test/results/clientpositive/serde_typedbytes.q.out index c9d0fb6b63..a0f7de79b9 100644 --- a/contrib/src/test/results/clientpositive/serde_typedbytes.q.out +++ b/contrib/src/test/results/clientpositive/serde_typedbytes.q.out @@ -48,25 +48,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -75,25 +75,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/serde_typedbytes2.q.out b/contrib/src/test/results/clientpositive/serde_typedbytes2.q.out index 715dc95f8b..c2461c51c8 100644 --- a/contrib/src/test/results/clientpositive/serde_typedbytes2.q.out +++ b/contrib/src/test/results/clientpositive/serde_typedbytes2.q.out @@ -48,21 +48,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToShort(key) (type: smallint), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -71,25 +71,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: smallint), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/serde_typedbytes3.q.out b/contrib/src/test/results/clientpositive/serde_typedbytes3.q.out index b66d5043b9..145c9b4402 100644 --- a/contrib/src/test/results/clientpositive/serde_typedbytes3.q.out +++ b/contrib/src/test/results/clientpositive/serde_typedbytes3.q.out @@ -48,21 +48,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToShort(key) (type: smallint), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -71,25 +71,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/serde_typedbytes4.q.out b/contrib/src/test/results/clientpositive/serde_typedbytes4.q.out index 38e80c63a2..c802f8db48 100644 --- a/contrib/src/test/results/clientpositive/serde_typedbytes4.q.out +++ b/contrib/src/test/results/clientpositive/serde_typedbytes4.q.out @@ -46,33 +46,33 @@ STAGE PLANS: TableScan alias: src filterExpr: (key < 100) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToByte(key) (type: tinyint), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -81,19 +81,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out b/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out index 4beb35a243..885a636464 100644 --- a/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out +++ b/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out @@ -48,25 +48,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: python ../../data/scripts/cat.py output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -75,25 +75,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udaf_example_avg.q.out b/contrib/src/test/results/clientpositive/udaf_example_avg.q.out index 7fbf22910d..5d64d39916 100644 --- a/contrib/src/test/results/clientpositive/udaf_example_avg.q.out +++ b/contrib/src/test/results/clientpositive/udaf_example_avg.q.out @@ -24,29 +24,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) > 250.0D), null, substr(value, 5)) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: example_avg(_col0), example_avg(_col1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: example_avg(VALUE._col0), example_avg(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out b/contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out index c261eb2cc1..db8730b89f 100644 --- a/contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out +++ b/contrib/src/test/results/clientpositive/udaf_example_group_concat.q.out @@ -24,22 +24,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5, 1) (type: string), key (type: string), value (type: string) outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: example_group_concat('(', _col2, ':', _col4, ')') keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 526000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 526000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: array) Reduce Operator Tree: Group By Operator @@ -47,10 +47,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udaf_example_max.q.out b/contrib/src/test/results/clientpositive/udaf_example_max.q.out index e11ad8ec17..a0125d26f8 100644 --- a/contrib/src/test/results/clientpositive/udaf_example_max.q.out +++ b/contrib/src/test/results/clientpositive/udaf_example_max.q.out @@ -31,29 +31,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) > 250.0D), null, substr(value, 5)) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: example_max(_col0), example_max(_col1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: example_max(VALUE._col0), example_max(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udaf_example_max_n.q.out b/contrib/src/test/results/clientpositive/udaf_example_max_n.q.out index f17eef8ed0..90b8fe5018 100644 --- a/contrib/src/test/results/clientpositive/udaf_example_max_n.q.out +++ b/contrib/src/test/results/clientpositive/udaf_example_max_n.q.out @@ -24,29 +24,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) > 250.0D), null, substr(value, 5)) (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: example_max_n(_col0, 10), example_max_n(_col2, 10) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct,n:int>), _col1 (type: struct,n:int>) Reduce Operator Tree: Group By Operator aggregations: example_max_n(VALUE._col0), example_max_n(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udaf_example_min.q.out b/contrib/src/test/results/clientpositive/udaf_example_min.q.out index 75f33eb7af..98296254f2 100644 --- a/contrib/src/test/results/clientpositive/udaf_example_min.q.out +++ b/contrib/src/test/results/clientpositive/udaf_example_min.q.out @@ -31,29 +31,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) > 250.0D), null, substr(value, 5)) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: example_min(_col0), example_min(_col1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Group By Operator aggregations: example_min(VALUE._col0), example_min(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udaf_example_min_n.q.out b/contrib/src/test/results/clientpositive/udaf_example_min_n.q.out index ae770c0749..6fa4b07946 100644 --- a/contrib/src/test/results/clientpositive/udaf_example_min_n.q.out +++ b/contrib/src/test/results/clientpositive/udaf_example_min_n.q.out @@ -24,29 +24,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), if((UDFToDouble(substr(value, 5)) < 250.0D), null, substr(value, 5)) (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: example_min_n(_col0, 10), example_min_n(_col2, 10) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct,n:int>), _col1 (type: struct,n:int>) Reduce Operator Tree: Group By Operator aggregations: example_min_n(VALUE._col0), example_min_n(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udf_example_arraymapstruct.q.out b/contrib/src/test/results/clientpositive/udf_example_arraymapstruct.q.out index 32a12cfab7..6f95d9e1eb 100644 --- a/contrib/src/test/results/clientpositive/udf_example_arraymapstruct.q.out +++ b/contrib/src/test/results/clientpositive/udf_example_arraymapstruct.q.out @@ -34,14 +34,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: example_arraysum(lint) (type: double), example_mapconcat(mstringstring) (type: string), example_structprint(lintstring[0]) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/udf_row_sequence.q.out b/contrib/src/test/results/clientpositive/udf_row_sequence.q.out index c619cdcf03..1aef4c7be1 100644 --- a/contrib/src/test/results/clientpositive/udf_row_sequence.q.out +++ b/contrib/src/test/results/clientpositive/udf_row_sequence.q.out @@ -37,25 +37,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), row_sequence() (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/contrib/src/test/results/clientpositive/vector_udf_example_arraymapstruct.q.out b/contrib/src/test/results/clientpositive/vector_udf_example_arraymapstruct.q.out index 75bbdffc7d..db2405acae 100644 --- a/contrib/src/test/results/clientpositive/vector_udf_example_arraymapstruct.q.out +++ b/contrib/src/test/results/clientpositive/vector_udf_example_arraymapstruct.q.out @@ -34,14 +34,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: example_arraysum(lint) (type: double), example_mapconcat(mstringstring) (type: string), example_structprint(lintstring[0]) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/acid_mapjoin.q.out b/ql/src/test/results/clientpositive/acid_mapjoin.q.out index 40ea74bb39..99ec570f60 100644 --- a/ql/src/test/results/clientpositive/acid_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/acid_mapjoin.q.out @@ -81,14 +81,14 @@ STAGE PLANS: TableScan alias: acid2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 210 Data size: 804 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 765 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 210 Data size: 840 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 765 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -100,21 +100,21 @@ STAGE PLANS: TableScan alias: acid1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 316 Data size: 1265 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 1208 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 316 Data size: 1265 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301 Data size: 1150 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 316 Data size: 1265 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301 Data size: 1150 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 347 Data size: 1391 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 331 Data size: 1265 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/acid_nullscan.q.out b/ql/src/test/results/clientpositive/acid_nullscan.q.out index ceb102917e..8f57ff28a5 100644 --- a/ql/src/test/results/clientpositive/acid_nullscan.q.out +++ b/ql/src/test/results/clientpositive/acid_nullscan.q.out @@ -45,21 +45,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_vectorized_n1 - Statistics: Num rows: 11 Data size: 25960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(a) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -128,13 +128,13 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/acid_table_stats.q.out b/ql/src/test/results/clientpositive/acid_table_stats.q.out index 32badd0fc7..e27a2c5363 100644 --- a/ql/src/test/results/clientpositive/acid_table_stats.q.out +++ b/ql/src/test/results/clientpositive/acid_table_stats.q.out @@ -437,19 +437,19 @@ STAGE PLANS: TableScan alias: acid filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 2000 Data size: 81260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 2000 Data size: 81260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -457,10 +457,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/alias_casted_column.q.out b/ql/src/test/results/clientpositive/alias_casted_column.q.out index c06173d097..9185b7e0bc 100644 --- a/ql/src/test/results/clientpositive/alias_casted_column.q.out +++ b/ql/src/test/results/clientpositive/alias_casted_column.q.out @@ -12,14 +12,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -46,14 +46,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/allcolref_in_udf.q.out b/ql/src/test/results/clientpositive/allcolref_in_udf.q.out index dbd17157e8..e34c29ad20 100644 --- a/ql/src/test/results/clientpositive/allcolref_in_udf.q.out +++ b/ql/src/test/results/clientpositive/allcolref_in_udf.q.out @@ -15,20 +15,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: concat(key, value) (type: string), array(key,value) (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 349264 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -80,36 +80,36 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (UDFToDouble(_col0) + 1.0D) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(_col0) + 1.0D) (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -119,24 +119,24 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + 1.0D) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 2 (type: int), concat(_col0, _col1, _col5, _col6) (type: string), concat(_col0, _col1) (type: string), concat(_col5, _col6) (type: string), concat(_col0, _col1, _col5) (type: string), concat(_col0, _col5, _col6) (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 242088 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 242088 Basic stats: COMPLETE Column stats: COMPLETE function name: stack Select Operator expressions: col0 (type: string), col1 (type: string), col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -195,24 +195,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: allcolref - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 913920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _c0 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 913920 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 913920 Basic stats: COMPLETE Column stats: NONE function name: explode Select Operator expressions: col (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 913920 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18270 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18270 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/alterColumnStatsPart.q.out b/ql/src/test/results/clientpositive/alterColumnStatsPart.q.out index b474019b21..6756527b8f 100644 --- a/ql/src/test/results/clientpositive/alterColumnStatsPart.q.out +++ b/ql/src/test/results/clientpositive/alterColumnStatsPart.q.out @@ -120,19 +120,19 @@ STAGE PLANS: TableScan alias: p filterExpr: (c = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: a - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(a) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -140,10 +140,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -255,19 +255,19 @@ STAGE PLANS: TableScan alias: p filterExpr: (c = 4) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: a - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(a) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -275,10 +275,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -349,19 +349,19 @@ STAGE PLANS: TableScan alias: p filterExpr: (c = 100) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: a - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: max(a) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -369,10 +369,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -413,19 +413,19 @@ STAGE PLANS: TableScan alias: p filterExpr: (c = 100) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: a - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: max(a) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -433,10 +433,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/alter_partition_coltype.q.out b/ql/src/test/results/clientpositive/alter_partition_coltype.q.out index 5727f0a65c..e8b9724c66 100644 --- a/ql/src/test/results/clientpositive/alter_partition_coltype.q.out +++ b/ql/src/test/results/clientpositive/alter_partition_coltype.q.out @@ -334,12 +334,12 @@ STAGE PLANS: TableScan alias: alter_coltype filterExpr: dt is not null (type: boolean) - Statistics: Num rows: 50 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 18350 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), dt (type: string), ts (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 50 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 18350 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select count(*) from alter_coltype where ts = 3.0 @@ -527,12 +527,12 @@ STAGE PLANS: TableScan alias: alterdynamic_part_table filterExpr: ((partcol1 = 1) and (partcol2 = '1')) (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: intcol (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select intcol from pt.alterdynamic_part_table where (partcol1='2' and partcol2='1')or (partcol1='1' and partcol2='__HIVE_DEFAULT_PARTITION__') @@ -598,12 +598,12 @@ STAGE PLANS: TableScan alias: alterdynamic_part_table filterExpr: (struct(partcol1,partcol2)) IN (const struct(2,'1'), const struct(1,'__HIVE_DEFAULT_PARTITION__')) (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: intcol (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select intcol from pt.alterdynamic_part_table where (partcol1='2' and partcol2='1')or (partcol1='1' and partcol2='__HIVE_DEFAULT_PARTITION__') diff --git a/ql/src/test/results/clientpositive/ambiguous_col.q.out b/ql/src/test/results/clientpositive/ambiguous_col.q.out index 49a8e9f2de..3de6b1bb8d 100644 --- a/ql/src/test/results/clientpositive/ambiguous_col.q.out +++ b/ql/src/test/results/clientpositive/ambiguous_col.q.out @@ -13,36 +13,36 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -51,14 +51,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -132,35 +132,35 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -169,14 +169,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -250,35 +250,35 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -287,14 +287,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out b/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out index 353813ee2d..924c609324 100644 --- a/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out +++ b/ql/src/test/results/clientpositive/analyze_table_null_partition.q.out @@ -284,12 +284,12 @@ STAGE PLANS: Processor Tree: TableScan alias: test2_n6 - Statistics: Num rows: 5 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 460 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: name (type: string), age (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 460 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: DROP TABLE test1_n9 diff --git a/ql/src/test/results/clientpositive/analyze_tbl_date.q.out b/ql/src/test/results/clientpositive/analyze_tbl_date.q.out index e9400b2231..f8257d45da 100644 --- a/ql/src/test/results/clientpositive/analyze_tbl_date.q.out +++ b/ql/src/test/results/clientpositive/analyze_tbl_date.q.out @@ -74,17 +74,17 @@ STAGE PLANS: TableScan alias: test_table_n7 filterExpr: d is not null (type: boolean) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: d is not null (type: boolean) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d (type: date) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out b/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out index 8aaa2532ec..3d0211f1b0 100644 --- a/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/ansi_sql_arithmetic.q.out @@ -12,17 +12,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (CAST( UDFToInteger(key) AS decimal(10,0)) / CAST( UDFToInteger(key) AS decimal(10,0))) (type: decimal(21,11)) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 56000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -58,17 +58,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(UDFToInteger(key)) / UDFToDouble(UDFToInteger(key))) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out b/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out index 7442c058fd..59b212e230 100644 --- a/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out +++ b/ql/src/test/results/clientpositive/array_map_access_nonconstant.q.out @@ -32,11 +32,11 @@ STAGE PLANS: Processor Tree: TableScan alias: array_table - Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 7696 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: index (type: int), array[index] (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 7696 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select index, `array`[index] from array_table @@ -85,11 +85,11 @@ STAGE PLANS: Processor Tree: TableScan alias: map_table - Statistics: Num rows: 4 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 3696 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), data[key] (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 3696 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select key, data[key] from map_table diff --git a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out index 190686547c..521519b308 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out @@ -61,28 +61,28 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 899146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 671202 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), CAST( cstring1 AS varchar(128)) (type: varchar(128)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 1479384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 1479384 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: varchar(128)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(128)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 1479384 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,17 +97,17 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: varchar(128)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: varchar(128)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -117,12 +117,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: varchar(128)) outputColumnNames: a, b - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -155,7 +155,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -163,10 +163,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/autoColumnStats_6.q.out b/ql/src/test/results/clientpositive/autoColumnStats_6.q.out index 98b5bc0d1e..6bf5e0794c 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_6.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_6.q.out @@ -40,14 +40,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 10) (type: int), (hash(value) pmod 10) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -56,18 +56,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string), CAST( _col3 AS STRING) (type: string) outputColumnNames: key, value, one, two, three - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 274000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: one (type: string), two (type: string), three (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 329250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 329250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: struct), _col4 (type: struct), _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/autoColumnStats_7.q.out b/ql/src/test/results/clientpositive/autoColumnStats_7.q.out index 8c07d61390..46881773e2 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_7.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_7.q.out @@ -36,16 +36,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_temp - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -53,7 +53,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -69,7 +69,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -78,14 +78,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -94,7 +94,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) outputColumnNames: key, c1, c2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -127,7 +127,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string), c1 (type: int), c2 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -135,7 +135,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -149,7 +149,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -157,10 +157,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/autoColumnStats_8.q.out b/ql/src/test/results/clientpositive/autoColumnStats_8.q.out index 8bdba66805..920c41aee8 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_8.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_8.q.out @@ -57,22 +57,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -99,37 +99,37 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false Filter Operator isSamplingPred: false predicate: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-12-31/ - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -156,13 +156,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: '2008-12-31' (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -392,17 +392,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -501,7 +501,7 @@ STAGE PLANS: null sort order: aa sort order: ++ Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -540,17 +540,17 @@ STAGE PLANS: keys: '2008-12-31' (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), '2008-12-31' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out index 1c3db7c03e..4e87953ddd 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out @@ -30,35 +30,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -69,14 +69,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,12 +85,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -129,10 +129,10 @@ STAGE PLANS: Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -141,12 +141,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -180,7 +180,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -188,10 +188,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join0.q.out b/ql/src/test/results/clientpositive/auto_join0.q.out index 5f7a6cc6ba..2b9ed3fac9 100644 --- a/ql/src/test/results/clientpositive/auto_join0.q.out +++ b/ql/src/test/results/clientpositive/auto_join0.q.out @@ -42,24 +42,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -95,12 +95,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -117,7 +117,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -125,10 +125,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -159,12 +159,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -181,12 +181,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -196,12 +196,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -215,24 +215,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/auto_join1.q.out b/ql/src/test/results/clientpositive/auto_join1.q.out index 6bda885aae..174bc7033f 100644 --- a/ql/src/test/results/clientpositive/auto_join1.q.out +++ b/ql/src/test/results/clientpositive/auto_join1.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,14 +67,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -83,12 +83,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -122,7 +122,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -130,10 +130,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join10.q.out b/ql/src/test/results/clientpositive/auto_join10.q.out index 7c7f4c826c..0a8fada624 100644 --- a/ql/src/test/results/clientpositive/auto_join10.q.out +++ b/ql/src/test/results/clientpositive/auto_join10.q.out @@ -31,14 +31,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -50,14 +50,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -65,19 +65,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col1,_col2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -87,10 +87,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join11.q.out b/ql/src/test/results/clientpositive/auto_join11.q.out index 4a0a2ea1b4..17ea27377c 100644 --- a/ql/src/test/results/clientpositive/auto_join11.q.out +++ b/ql/src/test/results/clientpositive/auto_join11.q.out @@ -31,14 +31,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -50,14 +50,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -65,19 +65,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col2) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -87,10 +87,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join12.q.out b/ql/src/test/results/clientpositive/auto_join12.q.out index 7b384b6065..edca4af2c7 100644 --- a/ql/src/test/results/clientpositive/auto_join12.q.out +++ b/ql/src/test/results/clientpositive/auto_join12.q.out @@ -40,14 +40,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -57,14 +57,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -77,14 +77,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -94,19 +94,19 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -116,10 +116,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join13.q.out b/ql/src/test/results/clientpositive/auto_join13.q.out index 15558a2188..9a411fcb7c 100644 --- a/ql/src/test/results/clientpositive/auto_join13.q.out +++ b/ql/src/test/results/clientpositive/auto_join13.q.out @@ -40,14 +40,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) @@ -56,14 +56,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -75,14 +75,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -90,7 +90,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -98,19 +98,19 @@ STAGE PLANS: 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col1, _col2 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2,_col1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -120,10 +120,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join14.q.out b/ql/src/test/results/clientpositive/auto_join14.q.out index 6317590265..3e3c97fff4 100644 --- a/ql/src/test/results/clientpositive/auto_join14.q.out +++ b/ql/src/test/results/clientpositive/auto_join14.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (UDFToDouble(key) > 100.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 90576 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,14 +67,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 30972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -83,12 +83,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: c1, c2 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -122,7 +122,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -130,10 +130,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join15.q.out b/ql/src/test/results/clientpositive/auto_join15.q.out index 960940e775..3ee0232423 100644 --- a/ql/src/test/results/clientpositive/auto_join15.q.out +++ b/ql/src/test/results/clientpositive/auto_join15.q.out @@ -31,10 +31,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -46,10 +46,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -57,19 +57,19 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -79,10 +79,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join16.q.out b/ql/src/test/results/clientpositive/auto_join16.q.out index 2782376853..c5f49acd45 100644 --- a/ql/src/test/results/clientpositive/auto_join16.q.out +++ b/ql/src/test/results/clientpositive/auto_join16.q.out @@ -31,14 +31,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string), _col1 (type: string) @@ -50,14 +50,14 @@ STAGE PLANS: TableScan alias: tab filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -65,19 +65,19 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -87,10 +87,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join17.q.out b/ql/src/test/results/clientpositive/auto_join17.q.out index 300cbb6159..63327ca4a2 100644 --- a/ql/src/test/results/clientpositive/auto_join17.q.out +++ b/ql/src/test/results/clientpositive/auto_join17.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,14 +67,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -83,12 +83,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: key1, value1, key2, value2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(value1, 'hll'), compute_stats(key2, 'hll'), compute_stats(value2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -122,7 +122,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -130,10 +130,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join18.q.out b/ql/src/test/results/clientpositive/auto_join18.q.out index 7e8de946c2..8164f6bf98 100644 --- a/ql/src/test/results/clientpositive/auto_join18.q.out +++ b/ql/src/test/results/clientpositive/auto_join18.q.out @@ -37,22 +37,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -61,7 +61,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -77,14 +77,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -94,16 +94,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2457 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col1,_col2,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2457 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -117,7 +117,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -125,10 +125,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -139,29 +139,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2196 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2196 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out index 9c0bffda30..dd11740557 100644 --- a/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/auto_join18_multi_distinct.q.out @@ -39,22 +39,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -63,7 +63,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -79,14 +79,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -96,16 +96,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2561 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col1,_col2,_col3,_col4) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2561 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -119,7 +119,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -127,10 +127,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -141,29 +141,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value), count(DISTINCT key) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2292 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2292 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/auto_join19.q.out b/ql/src/test/results/clientpositive/auto_join19.q.out index e04c3bfe6f..920c7adeda 100644 --- a/ql/src/test/results/clientpositive/auto_join19.q.out +++ b/ql/src/test/results/clientpositive/auto_join19.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((ds) IN ('2008-04-08', '2008-04-09') and (hr) IN ('12', '11') and key is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,14 +69,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col4 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 300580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 300580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,12 +85,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 300580 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -124,7 +124,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -132,10 +132,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join19_inclause.q.out b/ql/src/test/results/clientpositive/auto_join19_inclause.q.out index 7e0ab61e7c..c34026caff 100644 --- a/ql/src/test/results/clientpositive/auto_join19_inclause.q.out +++ b/ql/src/test/results/clientpositive/auto_join19_inclause.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((ds) IN ('2008-04-08', '2008-04-09') and (hr) IN ('12', '11') and key is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,14 +69,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col4 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 300580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 300580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,12 +85,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 300580 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -124,7 +124,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -132,10 +132,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join2.q.out b/ql/src/test/results/clientpositive/auto_join2.q.out index 8e51fa67f1..8ee6b98200 100644 --- a/ql/src/test/results/clientpositive/auto_join2.q.out +++ b/ql/src/test/results/clientpositive/auto_join2.q.out @@ -36,14 +36,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -71,14 +71,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -86,7 +86,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -94,14 +94,14 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col3 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -110,12 +110,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -149,7 +149,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -157,10 +157,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join20.q.out b/ql/src/test/results/clientpositive/auto_join20.q.out index 8f015b3917..a638bd8672 100644 --- a/ql/src/test/results/clientpositive/auto_join20.q.out +++ b/ql/src/test/results/clientpositive/auto_join20.q.out @@ -34,10 +34,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -51,10 +51,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -70,7 +70,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -84,19 +84,19 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3,_col4,_col5)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -106,10 +106,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -176,10 +176,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key < 15) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -193,10 +193,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -212,7 +212,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -226,19 +226,19 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0,_col1,_col2,_col3,_col4,_col5)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -248,10 +248,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join21.q.out b/ql/src/test/results/clientpositive/auto_join21.q.out index 0dccbcbe84..c982a8bbcb 100644 --- a/ql/src/test/results/clientpositive/auto_join21.q.out +++ b/ql/src/test/results/clientpositive/auto_join21.q.out @@ -23,7 +23,7 @@ STAGE PLANS: src1 TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -37,10 +37,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -56,7 +56,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -70,15 +70,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -86,10 +86,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join22.q.out b/ql/src/test/results/clientpositive/auto_join22.q.out index 81e5fb8e12..130c25de98 100644 --- a/ql/src/test/results/clientpositive/auto_join22.q.out +++ b/ql/src/test/results/clientpositive/auto_join22.q.out @@ -24,14 +24,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -40,14 +40,14 @@ STAGE PLANS: TableScan alias: src4 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -59,14 +59,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -74,7 +74,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -82,19 +82,19 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 113841 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 113841 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -104,10 +104,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join23.q.out b/ql/src/test/results/clientpositive/auto_join23.q.out index e31941db2d..cbd4f36dee 100644 --- a/ql/src/test/results/clientpositive/auto_join23.q.out +++ b/ql/src/test/results/clientpositive/auto_join23.q.out @@ -22,10 +22,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -37,10 +37,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -48,15 +48,15 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -64,10 +64,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join24.q.out b/ql/src/test/results/clientpositive/auto_join24.q.out index 7322a78835..f0302cdc0b 100644 --- a/ql/src/test/results/clientpositive/auto_join24.q.out +++ b/ql/src/test/results/clientpositive/auto_join24.q.out @@ -41,14 +41,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28119 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28119 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), cnt (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 28119 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -75,15 +75,15 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 339 Data size: 1630 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -93,10 +93,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join26.q.out b/ql/src/test/results/clientpositive/auto_join26.q.out index 8d3e0162e1..7349221d2c 100644 --- a/ql/src/test/results/clientpositive/auto_join26.q.out +++ b/ql/src/test/results/clientpositive/auto_join26.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,18 +67,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Local Work: @@ -89,14 +89,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -105,12 +105,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -142,7 +142,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -150,10 +150,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join27.q.out b/ql/src/test/results/clientpositive/auto_join27.q.out index 292d6d2b6d..6f7d361e0c 100644 --- a/ql/src/test/results/clientpositive/auto_join27.q.out +++ b/ql/src/test/results/clientpositive/auto_join27.q.out @@ -36,31 +36,31 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -79,14 +79,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -98,28 +98,28 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 249 Data size: 2644 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 249 Data size: 21663 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 249 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -128,19 +128,19 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan Union - Statistics: Num rows: 249 Data size: 2644 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 249 Data size: 21663 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 249 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -156,7 +156,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -164,10 +164,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join28.q.out b/ql/src/test/results/clientpositive/auto_join28.q.out index c6233e7631..b7c3a22f39 100644 --- a/ql/src/test/results/clientpositive/auto_join28.q.out +++ b/ql/src/test/results/clientpositive/auto_join28.q.out @@ -23,7 +23,7 @@ STAGE PLANS: src1 TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -37,10 +37,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -56,7 +56,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -70,15 +70,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -86,10 +86,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,10 +127,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -144,10 +144,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -163,7 +163,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -177,15 +177,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -193,10 +193,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -234,10 +234,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -251,10 +251,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -270,7 +270,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -284,15 +284,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -300,10 +300,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -341,10 +341,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -357,7 +357,7 @@ STAGE PLANS: src2 TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -373,7 +373,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -387,15 +387,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -403,10 +403,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join29.q.out b/ql/src/test/results/clientpositive/auto_join29.q.out index ab1047ec14..93ce713ee9 100644 --- a/ql/src/test/results/clientpositive/auto_join29.q.out +++ b/ql/src/test/results/clientpositive/auto_join29.q.out @@ -23,7 +23,7 @@ STAGE PLANS: src1 TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -37,10 +37,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -56,7 +56,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -70,15 +70,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -86,10 +86,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -635,10 +635,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -652,10 +652,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -671,7 +671,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -685,15 +685,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -701,10 +701,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1250,10 +1250,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -1267,10 +1267,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -1286,7 +1286,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1300,15 +1300,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -1316,10 +1316,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1877,10 +1877,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -1893,7 +1893,7 @@ STAGE PLANS: src2 TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -1909,7 +1909,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1923,15 +1923,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -1939,10 +1939,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2500,10 +2500,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -2513,10 +2513,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -2529,10 +2529,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2542,15 +2542,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -2558,10 +2558,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2607,10 +2607,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -2624,10 +2624,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -2643,7 +2643,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2657,15 +2657,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -2673,10 +2673,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3222,10 +3222,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -3239,10 +3239,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(key < 10)} @@ -3258,7 +3258,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -3272,15 +3272,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -3288,10 +3288,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3337,10 +3337,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -3354,10 +3354,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -3374,10 +3374,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -3391,15 +3391,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -3407,10 +3407,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3478,10 +3478,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -3491,10 +3491,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -3507,10 +3507,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: ((key > 10) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3520,15 +3520,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -3536,10 +3536,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join3.q.out b/ql/src/test/results/clientpositive/auto_join3.q.out index 2bffe6e4f9..1561b8c1a3 100644 --- a/ql/src/test/results/clientpositive/auto_join3.q.out +++ b/ql/src/test/results/clientpositive/auto_join3.q.out @@ -36,14 +36,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -53,14 +53,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -73,14 +73,14 @@ STAGE PLANS: TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -90,14 +90,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 118845 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 118845 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -106,12 +106,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 118845 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -145,7 +145,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -153,10 +153,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join31.q.out b/ql/src/test/results/clientpositive/auto_join31.q.out index ffee3debd3..b10ba7d8f7 100644 --- a/ql/src/test/results/clientpositive/auto_join31.q.out +++ b/ql/src/test/results/clientpositive/auto_join31.q.out @@ -39,11 +39,11 @@ STAGE PLANS: x:src TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,11 +52,11 @@ STAGE PLANS: y:src TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -68,11 +68,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -82,15 +82,15 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -100,10 +100,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join32.q.out b/ql/src/test/results/clientpositive/auto_join32.q.out index 09fcd7d12a..a5d9bbdc42 100644 --- a/ql/src/test/results/clientpositive/auto_join32.q.out +++ b/ql/src/test/results/clientpositive/auto_join32.q.out @@ -41,14 +41,14 @@ STAGE PLANS: TableScan alias: s filterExpr: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: v filterExpr: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: name (type: string), registration (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -75,18 +75,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT _col2) keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -95,10 +95,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -163,14 +163,14 @@ STAGE PLANS: TableScan alias: s filterExpr: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -275,14 +275,14 @@ STAGE PLANS: TableScan alias: s filterExpr: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -409,14 +409,14 @@ STAGE PLANS: TableScan alias: s filterExpr: ((p = 'bar') and name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((p = 'bar') and name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 271 Basic stats: COMPLETE Column stats: PARTIAL Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/auto_join33.q.out b/ql/src/test/results/clientpositive/auto_join33.q.out index 9c9c8987c5..1c0a865239 100644 --- a/ql/src/test/results/clientpositive/auto_join33.q.out +++ b/ql/src/test/results/clientpositive/auto_join33.q.out @@ -29,14 +29,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToDouble(key) + 1.0D) < 10.0D) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(key) + 1.0D) < 10.0D) and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + 1.0D) (type: double) @@ -48,14 +48,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToDouble(key) + 2.0D) < 10.0D) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(key) + 2.0D) < 10.0D) and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -63,10 +63,10 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + 1.0D) (type: double) 1 (UDFToDouble(_col0) + 2.0D) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join4.q.out b/ql/src/test/results/clientpositive/auto_join4.q.out index 0d926569b8..6c2d20c6ca 100644 --- a/ql/src/test/results/clientpositive/auto_join4.q.out +++ b/ql/src/test/results/clientpositive/auto_join4.q.out @@ -55,14 +55,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -74,14 +74,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -89,14 +89,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -105,12 +105,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -144,7 +144,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -152,10 +152,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join5.q.out b/ql/src/test/results/clientpositive/auto_join5.q.out index b3c1c256cd..0bf7f2996e 100644 --- a/ql/src/test/results/clientpositive/auto_join5.q.out +++ b/ql/src/test/results/clientpositive/auto_join5.q.out @@ -55,14 +55,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -74,14 +74,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -89,14 +89,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -105,12 +105,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -144,7 +144,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -152,10 +152,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join6.q.out b/ql/src/test/results/clientpositive/auto_join6.q.out index a3e829fdda..8e008f03bc 100644 --- a/ql/src/test/results/clientpositive/auto_join6.q.out +++ b/ql/src/test/results/clientpositive/auto_join6.q.out @@ -49,36 +49,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -88,14 +88,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 19936 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 11072 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 11072 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,12 +104,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 11072 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -141,7 +141,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -149,10 +149,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join7.q.out b/ql/src/test/results/clientpositive/auto_join7.q.out index 1f2616eddf..d674bedbfd 100644 --- a/ql/src/test/results/clientpositive/auto_join7.q.out +++ b/ql/src/test/results/clientpositive/auto_join7.q.out @@ -59,53 +59,53 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src3 filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -117,14 +117,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 29370 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string), UDFToInteger(_col4) (type: int), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 15675 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 15675 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -133,12 +133,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: int), _col5 (type: string) outputColumnNames: c1, c2, c3, c4, c5, c6 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 15675 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -170,7 +170,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -178,10 +178,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join8.q.out b/ql/src/test/results/clientpositive/auto_join8.q.out index e55081031a..8676d7b73c 100644 --- a/ql/src/test/results/clientpositive/auto_join8.q.out +++ b/ql/src/test/results/clientpositive/auto_join8.q.out @@ -55,14 +55,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -74,14 +74,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -89,17 +89,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is null (type: boolean) - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -108,12 +108,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -147,7 +147,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -155,10 +155,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join9.q.out b/ql/src/test/results/clientpositive/auto_join9.q.out index fb09841b6f..b0de3993af 100644 --- a/ql/src/test/results/clientpositive/auto_join9.q.out +++ b/ql/src/test/results/clientpositive/auto_join9.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((ds = '2008-04-08') and (hr = '12') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 133500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,14 +67,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -83,12 +83,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -122,7 +122,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -130,10 +130,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out b/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out index eb608d4321..8e73f6c47a 100644 --- a/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out +++ b/ql/src/test/results/clientpositive/auto_join_reordering_values.q.out @@ -111,44 +111,44 @@ STAGE PLANS: TableScan alias: orderpayment filterExpr: (date is not null and dealid is not null and cityid is not null and userid is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (cityid is not null and date is not null and dealid is not null and userid is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: dealid (type: int), date (type: string), cityid (type: int), userid (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int) auto parallelism: false TableScan alias: dim_pay_date filterExpr: date is not null (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: date is not null (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: date (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 auto parallelism: false Path -> Alias: @@ -213,7 +213,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -243,29 +243,29 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: string) auto parallelism: false TableScan alias: deal filterExpr: dealid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: dealid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: dealid (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 auto parallelism: false Path -> Alias: @@ -353,7 +353,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -383,29 +383,29 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col3 (type: int), _col4 (type: string), _col5 (type: int) auto parallelism: false TableScan alias: order_city filterExpr: cityid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: cityid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cityid (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 auto parallelism: false Path -> Alias: @@ -493,7 +493,7 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -523,29 +523,29 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 1 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col4 (type: string), _col5 (type: int) auto parallelism: false TableScan alias: user filterExpr: userid is not null (type: boolean) - Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: userid is not null (type: boolean) - Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: userid (type: int) outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 auto parallelism: false Path -> Alias: @@ -633,20 +633,20 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col4, _col5 - Statistics: Num rows: 110 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 5 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/auto_join_stats.q.out b/ql/src/test/results/clientpositive/auto_join_stats.q.out index 346c9c21cb..8ec59fdaad 100644 --- a/ql/src/test/results/clientpositive/auto_join_stats.q.out +++ b/ql/src/test/results/clientpositive/auto_join_stats.q.out @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -71,14 +71,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -86,7 +86,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -108,14 +108,14 @@ STAGE PLANS: TableScan alias: smalltable_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -132,10 +132,10 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 870 Data size: 151397 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 870 Data size: 151397 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -155,14 +155,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -174,14 +174,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -189,7 +189,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -206,35 +206,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -243,7 +243,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -323,14 +323,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -342,14 +342,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -357,7 +357,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -382,14 +382,14 @@ STAGE PLANS: TableScan alias: smalltable_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -399,14 +399,14 @@ STAGE PLANS: TableScan alias: smalltable2_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -426,14 +426,14 @@ STAGE PLANS: 1 UDFToDouble(_col0) (type: double) 2 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1740 Data size: 302794 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1740 Data size: 302794 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1740 Data size: 302794 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -453,14 +453,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -472,14 +472,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -487,7 +487,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -504,35 +504,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -541,7 +541,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/auto_join_stats2.q.out b/ql/src/test/results/clientpositive/auto_join_stats2.q.out index 6eab581009..bc0350d472 100644 --- a/ql/src/test/results/clientpositive/auto_join_stats2.q.out +++ b/ql/src/test/results/clientpositive/auto_join_stats2.q.out @@ -39,14 +39,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -55,14 +55,14 @@ STAGE PLANS: TableScan alias: smalltable filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -74,14 +74,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -89,7 +89,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 155812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 136000 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -97,17 +97,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 171393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 149600 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(_col2) + UDFToDouble(_col0)) = UDFToDouble(_col1)) (type: boolean) - Statistics: Num rows: 275 Data size: 85696 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 74800 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 85696 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 74800 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 85696 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 74800 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -186,14 +186,14 @@ STAGE PLANS: TableScan alias: smalltable filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -203,14 +203,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -219,14 +219,14 @@ STAGE PLANS: TableScan alias: smalltable2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -239,14 +239,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -254,7 +254,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -264,14 +264,14 @@ STAGE PLANS: 1 UDFToDouble(_col0) (type: double) 2 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1740 Data size: 302794 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1740 Data size: 302794 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1740 Data size: 302794 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out index 2f32cf2d4d..bc8ba217c1 100644 --- a/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out +++ b/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out @@ -29,14 +29,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -48,14 +48,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -63,7 +63,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -80,19 +80,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -109,14 +109,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -128,14 +128,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -143,7 +143,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -159,36 +159,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -197,7 +197,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -299,14 +299,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -318,14 +318,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -333,7 +333,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -357,14 +357,14 @@ STAGE PLANS: TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -381,7 +381,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 229264 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -398,19 +398,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 229264 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 229264 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -422,14 +422,14 @@ STAGE PLANS: TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -437,7 +437,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 229264 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -462,24 +462,24 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -488,7 +488,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 229264 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -507,14 +507,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -526,14 +526,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -541,7 +541,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -557,36 +557,36 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -595,7 +595,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -700,14 +700,14 @@ STAGE PLANS: TableScan alias: b filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -719,14 +719,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) > 100.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) > 100.0D) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -734,7 +734,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -758,14 +758,14 @@ STAGE PLANS: TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -782,7 +782,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -799,19 +799,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -823,14 +823,14 @@ STAGE PLANS: TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -838,7 +838,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -863,24 +863,24 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -889,7 +889,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -908,14 +908,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) > 100.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) > 100.0D) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -927,14 +927,14 @@ STAGE PLANS: TableScan alias: b filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -942,7 +942,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -958,36 +958,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) > 100.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) > 100.0D) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -996,7 +996,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out b/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out index 6b3920c92a..8a33779f94 100644 --- a/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out +++ b/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out @@ -251,11 +251,11 @@ STAGE PLANS: TableScan alias: episodes_partitioned_n0 filterExpr: (doctor_pt > 6) (type: boolean) - Statistics: Num rows: 3 Data size: 8950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: title (type: string), air_date (type: string), doctor (type: int), value (type: int), doctor_pt (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 8950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: SELECT * FROM episodes_partitioned_n0 WHERE doctor_pt > 6 @@ -341,14 +341,14 @@ STAGE PLANS: TableScan alias: episodes_partitioned_n0 filterExpr: (doctor_pt > 6) (type: boolean) - Statistics: Num rows: 3 Data size: 8950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: title (type: string), air_date (type: string), doctor (type: int), value (type: int), doctor_pt (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 8950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 8950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/beeline/explain_outputs.q.out b/ql/src/test/results/clientpositive/beeline/explain_outputs.q.out index 1d4c7ada92..9a0857f547 100644 --- a/ql/src/test/results/clientpositive/beeline/explain_outputs.q.out +++ b/ql/src/test/results/clientpositive/beeline/explain_outputs.q.out @@ -50,35 +50,35 @@ STAGE PLANS: TableScan alias: t1_n22 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2_n14 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -87,12 +87,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -106,7 +106,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -114,10 +114,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -151,35 +151,35 @@ STAGE PLANS: TableScan alias: t1_n22 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2_n14 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -188,12 +188,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5/1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -207,7 +207,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -215,10 +215,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -260,35 +260,35 @@ STAGE PLANS: TableScan alias: t1_n22 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2_n14 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -297,12 +297,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -316,7 +316,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -324,10 +324,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out b/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out index 7813aac294..edfb03fb10 100644 --- a/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out +++ b/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out @@ -122,11 +122,11 @@ STAGE PLANS: Processor Tree: TableScan alias: default.cmv_mat_view2_n4 - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 3 (type: int), c (type: decimal(10,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select a, c from cmv_basetable_n10 where a = 3 @@ -175,32 +175,32 @@ STAGE PLANS: TableScan alias: cmv_basetable_n10 filterExpr: (a = 3) (type: boolean) - Statistics: Num rows: 5 Data size: 9740 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (a = 3) (type: boolean) - Statistics: Num rows: 2 Data size: 3896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: decimal(10,2)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 3896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 2 Data size: 3896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(10,2)) TableScan alias: cmv_basetable_n10 filterExpr: ((d = 3) and (a = 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 9740 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((a = 3) and (d = 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: decimal(10,2)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(10,2)) Reduce Operator Tree: Join Operator @@ -210,14 +210,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 7794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 3 (type: int), _col0 (type: decimal(10,2)), 3 (type: int), _col1 (type: decimal(10,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 7794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 7794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -298,17 +298,17 @@ STAGE PLANS: TableScan alias: cmv_basetable_n10 filterExpr: ((a = 3) and (d = 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 9740 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((a = 3) and (d = 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: decimal(10,2)) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(10,2)) TableScan alias: default.cmv_mat_view2_n4 @@ -325,14 +325,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col6 - Statistics: Num rows: 2 Data size: 4130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 474 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col0 (type: int), _col6 (type: decimal(10,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 4130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 474 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 4130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 474 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -399,32 +399,32 @@ STAGE PLANS: TableScan alias: cmv_basetable_n10 filterExpr: (a = 3) (type: boolean) - Statistics: Num rows: 5 Data size: 9740 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (a = 3) (type: boolean) - Statistics: Num rows: 2 Data size: 3896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: decimal(10,2)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 3896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 2 Data size: 3896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(10,2)) TableScan alias: cmv_basetable_n10 filterExpr: ((d = 3) and (a = 3)) (type: boolean) - Statistics: Num rows: 5 Data size: 9740 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((a = 3) and (d = 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: decimal(10,2)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1948 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(10,2)) Reduce Operator Tree: Join Operator @@ -434,14 +434,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 7794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 3 (type: int), _col0 (type: decimal(10,2)), 3 (type: int), _col1 (type: decimal(10,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 7794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 7794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_1.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_1.q.out index 733a3f5c18..39c635c97d 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_1.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_1.q.out @@ -109,10 +109,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -162,7 +162,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -217,7 +217,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -271,7 +271,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 @@ -331,10 +331,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -384,7 +384,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -439,7 +439,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -493,7 +493,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out index 8b48c7f12c..8dd02b317a 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out @@ -79,10 +79,10 @@ STAGE PLANS: TableScan alias: b filterExpr: (userid is not null and pageid is not null and postid is not null and type is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 4140 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 6688 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (pageid is not null and postid is not null and type is not null and userid is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 4140 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 6688 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_11.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_11.q.out index de02982c6e..b7cc459e9e 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_11.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_11.q.out @@ -59,12 +59,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1893,23 +1893,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1_n1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 16) = 1) (type: boolean) sampleDesc: BUCKET 2 OUT OF 16 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2004,23 +2004,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table3_n1 - Statistics: Num rows: 1028 Data size: 10968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 286812 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 16) = 1) (type: boolean) sampleDesc: BUCKET 2 OUT OF 16 - Statistics: Num rows: 514 Data size: 5484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514 Data size: 143406 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 514 Data size: 5484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514 Data size: 143406 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 514 Data size: 5484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514 Data size: 143406 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_12.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_12.q.out index c626c7e18b..a9f6cbf545 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_12.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_12.q.out @@ -70,12 +70,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -273,12 +273,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 3084 Data size: 32904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3084 Data size: 583932 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 3084 Data size: 32904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2930 Data size: 554773 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_13.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_13.q.out index 123e84457a..a5e8a7f504 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_13.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_13.q.out @@ -77,12 +77,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -239,12 +239,12 @@ STAGE PLANS: TableScan alias: b filterExpr: UDFToDouble(value) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(value) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 UDFToDouble(key) (type: double) @@ -257,12 +257,12 @@ STAGE PLANS: TableScan alias: a filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -271,16 +271,16 @@ STAGE PLANS: 1 UDFToDouble(value) (type: double) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE tag: -1 TopN: 10 TopN Hash Memory Usage: 0.1 @@ -351,16 +351,16 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_16.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_16.q.out index 3fb1769a05..e111326a80 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_16.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_16.q.out @@ -49,10 +49,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_2.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_2.q.out index e39edcc2fd..5e565016bf 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_2.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_2.q.out @@ -63,10 +63,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -118,7 +118,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -173,7 +173,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -229,7 +229,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 @@ -289,10 +289,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -344,7 +344,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -399,7 +399,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -455,7 +455,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_3.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_3.q.out index fa7968da80..d10568ba2b 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_3.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_3.q.out @@ -63,10 +63,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -118,7 +118,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -172,7 +172,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -228,7 +228,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 @@ -287,10 +287,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -342,7 +342,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -396,7 +396,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -452,7 +452,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_7.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_7.q.out index 4b1313dc93..cda0976e59 100644 --- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_7.q.out +++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_7.q.out @@ -630,7 +630,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/binary_output_format.q.out b/ql/src/test/results/clientpositive/binary_output_format.q.out index 9b0ee6b125..040ce6ca3c 100644 --- a/ql/src/test/results/clientpositive/binary_output_format.q.out +++ b/ql/src/test/results/clientpositive/binary_output_format.q.out @@ -64,12 +64,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: @@ -83,13 +83,13 @@ STAGE PLANS: serialization.last.column.takes.rest true serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -121,16 +121,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: mydata - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(mydata, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct) auto parallelism: false @@ -193,13 +193,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/binarysortable_1.q.out b/ql/src/test/results/clientpositive/binarysortable_1.q.out index f073949021..6f0707f112 100644 --- a/ql/src/test/results/clientpositive/binarysortable_1.q.out +++ b/ql/src/test/results/clientpositive/binarysortable_1.q.out @@ -46,22 +46,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: mytable_n0 - Statistics: Num rows: 1 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double) Reduce Operator Tree: Group By Operator @@ -69,14 +69,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: regexp_replace(regexp_replace(regexp_replace(_col0, '', '^A'), '', '^@'), '', '^B') (type: string), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/bucket1.q.out b/ql/src/test/results/clientpositive/bucket1.q.out index f39af86ff0..49fbe2f974 100644 --- a/ql/src/test/results/clientpositive/bucket1.q.out +++ b/ql/src/test/results/clientpositive/bucket1.q.out @@ -28,17 +28,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -101,13 +101,13 @@ STAGE PLANS: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -139,12 +139,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -212,7 +212,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -250,13 +250,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/bucket2.q.out b/ql/src/test/results/clientpositive/bucket2.q.out index 8d1d066370..385e532560 100644 --- a/ql/src/test/results/clientpositive/bucket2.q.out +++ b/ql/src/test/results/clientpositive/bucket2.q.out @@ -27,17 +27,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -100,13 +100,13 @@ STAGE PLANS: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -138,22 +138,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -239,17 +239,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/bucket3.q.out b/ql/src/test/results/clientpositive/bucket3.q.out index ed7da20a46..163019415a 100644 --- a/ql/src/test/results/clientpositive/bucket3.q.out +++ b/ql/src/test/results/clientpositive/bucket3.q.out @@ -28,17 +28,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -101,14 +101,14 @@ STAGE PLANS: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 2 Static Partition Specification: ds=1/ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -137,13 +137,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -212,7 +212,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -251,17 +251,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -320,17 +320,17 @@ STAGE PLANS: TableScan alias: s filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/bucket_map_join_1.q.out b/ql/src/test/results/clientpositive/bucket_map_join_1.q.out index fb99ead317..944e1bea7a 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_1.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_1.q.out @@ -65,12 +65,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -83,12 +83,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -96,7 +96,7 @@ STAGE PLANS: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/bucket_map_join_2.q.out b/ql/src/test/results/clientpositive/bucket_map_join_2.q.out index 3377621f38..29dc53a18f 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_2.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_2.q.out @@ -65,12 +65,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -83,12 +83,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -96,7 +96,7 @@ STAGE PLANS: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out b/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out index 6da9934fe4..9cae2b26cd 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out @@ -191,16 +191,16 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -213,16 +213,16 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -231,17 +231,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -272,7 +272,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash @@ -642,16 +642,16 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -664,16 +664,16 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -682,17 +682,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -723,7 +723,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/bucket_map_join_spark2.q.out b/ql/src/test/results/clientpositive/bucket_map_join_spark2.q.out index b086c0eb2f..65a4a0b289 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_spark2.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_spark2.q.out @@ -175,16 +175,16 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 78 Data size: 44908 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -197,16 +197,16 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -215,17 +215,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 0 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -256,7 +256,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash @@ -626,16 +626,16 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 78 Data size: 44908 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -648,16 +648,16 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -666,17 +666,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 0 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -707,7 +707,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/bucket_map_join_spark3.q.out b/ql/src/test/results/clientpositive/bucket_map_join_spark3.q.out index bd91b447e4..1db2ab84f5 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_spark3.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_spark3.q.out @@ -175,16 +175,16 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 78 Data size: 44908 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -197,16 +197,16 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -215,17 +215,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -256,7 +256,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash @@ -626,16 +626,16 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 78 Data size: 44908 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 78 Data size: 30620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 75 Data size: 43180 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -648,16 +648,16 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85004 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 149 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 142 Data size: 81010 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -666,17 +666,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -707,7 +707,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 163 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89111 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/bucket_map_join_spark4.q.out b/ql/src/test/results/clientpositive/bucket_map_join_spark4.q.out index 5f0cea5cb0..f09a3e2553 100644 --- a/ql/src/test/results/clientpositive/bucket_map_join_spark4.q.out +++ b/ql/src/test/results/clientpositive/bucket_map_join_spark4.q.out @@ -96,16 +96,16 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -115,16 +115,16 @@ STAGE PLANS: TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: value is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -137,16 +137,16 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -155,7 +155,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -164,17 +164,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 Position of Big Table: 0 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 7046 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 7046 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 7046 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -471,16 +471,16 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -490,16 +490,16 @@ STAGE PLANS: TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: value is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -512,16 +512,16 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -530,7 +530,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2912 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -539,17 +539,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 Position of Big Table: 0 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 7046 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 7046 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 7046 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/bucketcontext_1.q.out b/ql/src/test/results/clientpositive/bucketcontext_1.q.out index 9bb73e6eb8..2fcbec4a8b 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_1.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_1.q.out @@ -167,12 +167,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 56 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 56 Data size: 37620 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 56 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 54 Data size: 36276 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -192,12 +192,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 240 Data size: 158376 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 228 Data size: 150457 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -205,7 +205,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 264 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 250 Data size: 165502 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -396,12 +396,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 240 Data size: 158376 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 228 Data size: 150457 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketcontext_2.q.out b/ql/src/test/results/clientpositive/bucketcontext_2.q.out index 00164dd671..31a0a68eee 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_2.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_2.q.out @@ -151,12 +151,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 79280 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 114 Data size: 75316 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -176,12 +176,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -189,7 +189,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 132 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 125 Data size: 82847 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -380,12 +380,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketcontext_3.q.out b/ql/src/test/results/clientpositive/bucketcontext_3.q.out index 71d4b4de11..0054c95a7e 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_3.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_3.q.out @@ -199,12 +199,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -224,12 +224,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 79280 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 114 Data size: 75316 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -237,7 +237,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 132 Data size: 63932 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 125 Data size: 82847 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -377,12 +377,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 79280 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 114 Data size: 75316 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketcontext_4.q.out b/ql/src/test/results/clientpositive/bucketcontext_4.q.out index fab45580c4..47b6123eb3 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_4.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_4.q.out @@ -215,12 +215,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 240 Data size: 158376 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 228 Data size: 150457 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -240,12 +240,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 56 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 56 Data size: 37620 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 56 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 54 Data size: 36276 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -253,7 +253,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 264 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 250 Data size: 165502 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -393,12 +393,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 56 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 56 Data size: 37620 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 56 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 54 Data size: 36276 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketcontext_5.q.out b/ql/src/test/results/clientpositive/bucketcontext_5.q.out index e14c61b995..d151696a21 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_5.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_5.q.out @@ -83,12 +83,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -108,12 +108,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -121,7 +121,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 1 Data size: 63932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -255,12 +255,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketcontext_6.q.out b/ql/src/test/results/clientpositive/bucketcontext_6.q.out index d68438e16d..20e1aeeb0c 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_6.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_6.q.out @@ -101,12 +101,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -126,12 +126,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -139,7 +139,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 123 Data size: 60500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 117 Data size: 78681 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -328,12 +328,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketcontext_7.q.out b/ql/src/test/results/clientpositive/bucketcontext_7.q.out index e9e22bbf3d..846d4f457d 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_7.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_7.q.out @@ -232,12 +232,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 240 Data size: 158376 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 228 Data size: 150457 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -257,12 +257,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -270,7 +270,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 264 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 250 Data size: 165502 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -463,12 +463,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketcontext_8.q.out b/ql/src/test/results/clientpositive/bucketcontext_8.q.out index f5a84e63d7..08f98cc395 100644 --- a/ql/src/test/results/clientpositive/bucketcontext_8.q.out +++ b/ql/src/test/results/clientpositive/bucketcontext_8.q.out @@ -232,12 +232,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 112 Data size: 74872 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 107 Data size: 71529 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -257,12 +257,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 240 Data size: 158376 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 228 Data size: 150457 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -270,7 +270,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 - Statistics: Num rows: 264 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 250 Data size: 165502 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -463,12 +463,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 240 Data size: 158376 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 228 Data size: 150457 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketmapjoin10.q.out b/ql/src/test/results/clientpositive/bucketmapjoin10.q.out index 4cdd563466..458fbff189 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin10.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin10.q.out @@ -248,12 +248,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 178 Data size: 69500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 178 Data size: 70184 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 178 Data size: 69500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 170 Data size: 67029 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -266,12 +266,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 178 Data size: 69500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 178 Data size: 70184 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 178 Data size: 69500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 170 Data size: 67029 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -279,7 +279,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 195 Data size: 76450 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 187 Data size: 73731 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/bucketmapjoin11.q.out b/ql/src/test/results/clientpositive/bucketmapjoin11.q.out index 9013cc1914..1b174f5703 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin11.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin11.q.out @@ -256,12 +256,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 219 Data size: 86460 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 209 Data size: 82512 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -281,12 +281,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 219 Data size: 86460 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 209 Data size: 82512 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -294,7 +294,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 240 Data size: 94182 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 229 Data size: 90763 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -595,12 +595,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 219 Data size: 126756 Basic stats: PARTIAL Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 209 Data size: 120968 Basic stats: PARTIAL Column stats: PARTIAL HashTable Sink Operator keys: 0 key (type: int), part (type: string) @@ -620,12 +620,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 219 Data size: 126756 Basic stats: PARTIAL Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 219 Data size: 85620 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 209 Data size: 120968 Basic stats: PARTIAL Column stats: PARTIAL Map Join Operator condition map: Inner Join 0 to 1 @@ -633,7 +633,7 @@ STAGE PLANS: 0 key (type: int), part (type: string) 1 key (type: int), part (type: string) Position of Big Table: 0 - Statistics: Num rows: 240 Data size: 94182 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 229 Data size: 133064 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/bucketmapjoin12.q.out b/ql/src/test/results/clientpositive/bucketmapjoin12.q.out index 591a667419..1fd36e2dd8 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin12.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin12.q.out @@ -169,12 +169,12 @@ STAGE PLANS: TableScan alias: b filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -194,12 +194,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -207,7 +207,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 104 Data size: 30250 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 29363 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -406,12 +406,12 @@ STAGE PLANS: TableScan alias: b filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -424,12 +424,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -437,7 +437,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 104 Data size: 30250 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 29363 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/bucketmapjoin13.q.out b/ql/src/test/results/clientpositive/bucketmapjoin13.q.out index 8aa75e71cb..683692e777 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin13.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin13.q.out @@ -138,12 +138,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: int) @@ -156,12 +156,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -169,7 +169,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -423,12 +423,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: int) @@ -448,12 +448,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '2') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -461,7 +461,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 2200 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -671,12 +671,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: int) @@ -696,12 +696,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -709,7 +709,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 2200 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -919,12 +919,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: int) @@ -944,12 +944,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -957,7 +957,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 2200 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/bucketmapjoin5.q.out b/ql/src/test/results/clientpositive/bucketmapjoin5.q.out index a4d5e4e463..4edf1810d6 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin5.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin5.q.out @@ -197,12 +197,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -222,12 +222,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 298 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 298 Data size: 169820 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 298 Data size: 116240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 284 Data size: 161841 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -236,18 +236,18 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0, _col1, _col6 Position of Big Table: 1 - Statistics: Num rows: 327 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 312 Data size: 178025 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 327 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 312 Data size: 178025 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 327 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 312 Data size: 178025 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -278,7 +278,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 327 Data size: 127864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 312 Data size: 178025 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash @@ -801,12 +801,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -826,12 +826,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 156 Data size: 61240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89440 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 156 Data size: 61240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85426 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -840,18 +840,18 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0, _col1, _col6 Position of Big Table: 1 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -882,7 +882,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/bucketmapjoin8.q.out b/ql/src/test/results/clientpositive/bucketmapjoin8.q.out index 9fa225c270..944e5282b3 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin8.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin8.q.out @@ -135,12 +135,12 @@ STAGE PLANS: TableScan alias: b filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -160,12 +160,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -173,7 +173,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 104 Data size: 30250 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 29363 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -381,12 +381,12 @@ STAGE PLANS: TableScan alias: b filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -406,12 +406,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -419,7 +419,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 104 Data size: 30250 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 29363 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/bucketmapjoin9.q.out b/ql/src/test/results/clientpositive/bucketmapjoin9.q.out index 90bd8f9c1d..01b4f947d6 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin9.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin9.q.out @@ -143,12 +143,12 @@ STAGE PLANS: TableScan alias: b filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 145 Data size: 42000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 145 Data size: 42556 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 145 Data size: 42000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 138 Data size: 40501 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -161,12 +161,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -174,7 +174,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 159 Data size: 46200 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 151 Data size: 44551 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -414,12 +414,12 @@ STAGE PLANS: TableScan alias: b filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -432,12 +432,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 95 Data size: 27868 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 95 Data size: 27500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 26694 Basic stats: PARTIAL Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -445,7 +445,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 104 Data size: 30250 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 29363 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/bucketmapjoin_negative.q.out b/ql/src/test/results/clientpositive/bucketmapjoin_negative.q.out index 10c91cd1a4..7ebd765bb4 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin_negative.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin_negative.q.out @@ -146,12 +146,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (key is not null and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 140 Data size: 42000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 140 Data size: 67192 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 140 Data size: 42000 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 133 Data size: 63832 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -164,12 +164,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -178,17 +178,17 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0, _col1, _col6 Position of Big Table: 0 - Statistics: Num rows: 154 Data size: 46200 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 146 Data size: 70215 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 154 Data size: 46200 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 146 Data size: 70215 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 154 Data size: 46200 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 146 Data size: 70215 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -219,7 +219,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 154 Data size: 46200 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 146 Data size: 70215 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/bucketmapjoin_negative2.q.out b/ql/src/test/results/clientpositive/bucketmapjoin_negative2.q.out index 3009c4762f..7d2f26ced1 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin_negative2.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin_negative2.q.out @@ -202,12 +202,12 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 156 Data size: 61240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 156 Data size: 89440 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 156 Data size: 61240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 149 Data size: 85426 Basic stats: PARTIAL Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) @@ -227,12 +227,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -241,18 +241,18 @@ STAGE PLANS: 1 key (type: int) outputColumnNames: _col0, _col1, _col6 Position of Big Table: 0 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE BucketMapJoin: true Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -283,7 +283,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value1, value2 - Statistics: Num rows: 171 Data size: 67364 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 163 Data size: 93968 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/bucketmapjoin_negative3.q.out b/ql/src/test/results/clientpositive/bucketmapjoin_negative3.q.out index 500a516a89..2d9cd882ee 100644 --- a/ql/src/test/results/clientpositive/bucketmapjoin_negative3.q.out +++ b/ql/src/test/results/clientpositive/bucketmapjoin_negative3.q.out @@ -163,12 +163,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -188,12 +188,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -202,18 +202,18 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -316,12 +316,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -341,12 +341,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -355,18 +355,18 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -469,12 +469,12 @@ STAGE PLANS: TableScan alias: r filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 (key + key) (type: double) @@ -487,12 +487,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key + key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key + key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -501,17 +501,17 @@ STAGE PLANS: 1 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -614,12 +614,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -632,12 +632,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -646,17 +646,17 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -759,12 +759,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -777,12 +777,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -791,17 +791,17 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -904,12 +904,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -922,12 +922,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -936,17 +936,17 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1049,12 +1049,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -1067,12 +1067,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -1081,17 +1081,17 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1194,12 +1194,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -1212,12 +1212,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -1226,17 +1226,17 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1339,12 +1339,12 @@ STAGE PLANS: TableScan alias: r filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -1357,12 +1357,12 @@ STAGE PLANS: TableScan alias: l filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 42000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -1371,17 +1371,17 @@ STAGE PLANS: 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 46200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out index 910ba1f8f4..15c28bf4c1 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_1.q.out @@ -56,14 +56,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -167,14 +167,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -278,14 +278,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), concat(value, value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -339,25 +339,25 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -366,13 +366,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -408,7 +408,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -416,14 +416,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -455,14 +455,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), concat(value, value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out index 6db8bfb1dd..0ac2abb8d8 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_3.q.out @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -166,25 +166,25 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToInteger(_col1) (type: int) sort order: + Map-reduce partition columns: UDFToInteger(_col1) (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: CAST( VALUE._col0 AS STRING) (type: string), UDFToInteger(VALUE._col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -193,13 +193,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), '1' (type: string) outputColumnNames: value, key, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 136500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(value, 'hll'), compute_stats(key, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -235,7 +235,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -243,14 +243,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out index 638eaf6c0b..a461b455fd 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_4.q.out @@ -77,14 +77,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -279,14 +279,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_5.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_5.q.out index aa3d451743..3b0a0bd5cd 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_5.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_5.q.out @@ -77,14 +77,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -266,14 +266,14 @@ STAGE PLANS: TableScan alias: test_table1_n8 filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out index 1d3a8ad616..69db0b814a 100644 --- a/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out +++ b/ql/src/test/results/clientpositive/bucketsortoptimize_insert_8.q.out @@ -77,14 +77,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -261,14 +261,14 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/case_sensitivity.q.out b/ql/src/test/results/clientpositive/case_sensitivity.q.out index 6382115da4..99e4ad5add 100644 --- a/ql/src/test/results/clientpositive/case_sensitivity.q.out +++ b/ql/src/test/results/clientpositive/case_sensitivity.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: src_thrift filterExpr: (lint[0] > 0) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (lint[0] > 0) (type: boolean) - Statistics: Num rows: 3 Data size: 8372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 8039 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint[1] (type: int), lintstring[0].mystring (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 8372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 8039 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 8372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 8039 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -50,25 +50,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 3 Data size: 8372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 8039 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3544 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3544 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cast1.q.out b/ql/src/test/results/clientpositive/cast1.q.out index d3491325b3..17c1155f25 100644 --- a/ql/src/test/results/clientpositive/cast1.q.out +++ b/ql/src/test/results/clientpositive/cast1.q.out @@ -29,17 +29,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 5 (type: int), 5.0D (type: double), 5.0D (type: double), 5.0D (type: double), 5 (type: int), 'TRUE' (type: string), 1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 31000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 31000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -48,25 +48,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: int), _col5 (type: string), _col6 (type: int) outputColumnNames: c1, c2, c3, c4, c5, c6, c7 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 31000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 2984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2984 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2984 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cast_on_constant.q.out b/ql/src/test/results/clientpositive/cast_on_constant.q.out index bdb03f72e4..bce07b65da 100644 --- a/ql/src/test/results/clientpositive/cast_on_constant.q.out +++ b/ql/src/test/results/clientpositive/cast_on_constant.q.out @@ -21,17 +21,17 @@ STAGE PLANS: TableScan alias: t1_n138 filterExpr: (ts_field = TIMESTAMP'2016-01-23 00:00:00') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts_field = TIMESTAMP'2016-01-23 00:00:00') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: TIMESTAMP'2016-01-23 00:00:00' (type: timestamp), date_field (type: date) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -59,17 +59,17 @@ STAGE PLANS: TableScan alias: t1_n138 filterExpr: (date_field = DATE'2016-01-23') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (date_field = DATE'2016-01-23') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts_field (type: timestamp), DATE'2016-01-23' (type: date) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -97,17 +97,17 @@ STAGE PLANS: TableScan alias: t1_n138 filterExpr: (ts_field = TIMESTAMP'2016-01-23 00:00:00') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts_field = TIMESTAMP'2016-01-23 00:00:00') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: TIMESTAMP'2016-01-23 00:00:00' (type: timestamp), date_field (type: date) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -135,17 +135,17 @@ STAGE PLANS: TableScan alias: t1_n138 filterExpr: (date_field = DATE'2016-01-23') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (date_field = DATE'2016-01-23') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts_field (type: timestamp), DATE'2016-01-23' (type: date) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -173,17 +173,17 @@ STAGE PLANS: TableScan alias: t1_n138 filterExpr: (CAST( date_field AS TIMESTAMP) = ts_field) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (CAST( date_field AS TIMESTAMP) = ts_field) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts_field (type: timestamp), date_field (type: date) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_SortUnionTransposeRule.q.out b/ql/src/test/results/clientpositive/cbo_SortUnionTransposeRule.q.out index 6900f62326..bfad440cc9 100644 --- a/ql/src/test/results/clientpositive/cbo_SortUnionTransposeRule.q.out +++ b/ql/src/test/results/clientpositive/cbo_SortUnionTransposeRule.q.out @@ -32,38 +32,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -119,38 +119,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -186,43 +186,43 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -276,29 +276,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -307,14 +307,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -328,7 +328,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -336,10 +336,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -352,26 +352,26 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -382,29 +382,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -413,14 +413,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -434,7 +434,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -442,10 +442,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -481,38 +481,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -570,17 +570,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) Execution mode: vectorized @@ -588,10 +588,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -604,26 +604,26 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -634,17 +634,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) Execution mode: vectorized @@ -652,10 +652,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -695,25 +695,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -726,31 +726,31 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 TableScan Union - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -761,25 +761,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -837,17 +837,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) Execution mode: vectorized @@ -855,10 +855,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -871,23 +871,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -896,14 +896,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -917,7 +917,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -925,10 +925,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -941,26 +941,26 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -971,17 +971,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) Execution mode: vectorized @@ -989,10 +989,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1005,23 +1005,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1030,14 +1030,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1051,7 +1051,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -1059,10 +1059,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1098,38 +1098,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1163,38 +1163,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_const.q.out b/ql/src/test/results/clientpositive/cbo_const.q.out index 302c60d1df..cacd3b62a6 100644 --- a/ql/src/test/results/clientpositive/cbo_const.q.out +++ b/ql/src/test/results/clientpositive/cbo_const.q.out @@ -158,17 +158,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 4.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 4.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -237,36 +237,36 @@ STAGE PLANS: TableScan alias: y filterExpr: (UDFToDouble(key) = 3.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 3.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: x filterExpr: ((UDFToDouble(key) = 3.0D) and value is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) = 3.0D) and value is not null) (type: boolean) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -276,7 +276,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -292,24 +292,24 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: z filterExpr: ((ds = '2008-04-08') and (UDFToDouble(hr) = 14.0D) and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 452 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(hr) = 14.0D) and (ds = '2008-04-08') and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 452 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -318,14 +318,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 302 Data size: 3213 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col4 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 302 Data size: 3213 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 302 Data size: 3213 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_input26.q.out b/ql/src/test/results/clientpositive/cbo_input26.q.out index 9431cd8c39..6bcccdd566 100644 --- a/ql/src/test/results/clientpositive/cbo_input26.q.out +++ b/ql/src/test/results/clientpositive/cbo_input26.q.out @@ -25,15 +25,15 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -41,14 +41,14 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -61,28 +61,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -94,20 +94,20 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -115,14 +115,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '14' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 454 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -186,29 +186,29 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), '11' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 865 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -221,28 +221,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1135 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: '2008-04-08' (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1135 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: '2008-04-08' (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -254,20 +254,20 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) Execution mode: vectorized @@ -275,14 +275,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), '14' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 270 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -346,29 +346,29 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), '11' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 865 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -381,28 +381,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1135 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: '2008-04-08' (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1135 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: '2008-04-08' (type: string), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2184 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -414,20 +414,20 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) Execution mode: vectorized @@ -435,14 +435,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), '14' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 270 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -506,17 +506,17 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -524,10 +524,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -540,28 +540,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1258 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), '2008-04-08' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1258 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), '2008-04-08' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -573,20 +573,20 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -594,10 +594,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/cbo_ppd_non_deterministic.q.out b/ql/src/test/results/clientpositive/cbo_ppd_non_deterministic.q.out index bdcd208c99..7ce18879c6 100644 --- a/ql/src/test/results/clientpositive/cbo_ppd_non_deterministic.q.out +++ b/ql/src/test/results/clientpositive/cbo_ppd_non_deterministic.q.out @@ -115,24 +115,24 @@ STAGE PLANS: TableScan alias: testa filterExpr: ((part1 = 'CA') and (part2 = 'ABC')) (type: boolean) - Statistics: Num rows: 2 Data size: 4580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 4596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rand() (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <= 0.5D) and (_col0 > 0.25D)) (type: boolean) - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'CA' (type: string), _col0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -165,24 +165,24 @@ STAGE PLANS: TableScan alias: testa filterExpr: ((part1 = 'CA') and (part2 = 'ABC')) (type: boolean) - Statistics: Num rows: 2 Data size: 4580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 4596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rand() (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4580 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <= 0.5D) and (_col0 > 0.25D)) (type: boolean) - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'CA' (type: string), _col0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out b/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out index 74022ae43a..02b8dbbc1c 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_auto_join17.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,14 +67,14 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), UDFToInteger(key0) (type: int), value0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -83,12 +83,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: key1, value1, key2, value2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(value1, 'hll'), compute_stats(key2, 'hll'), compute_stats(value2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -122,7 +122,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -130,14 +130,14 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out b/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out index cbb1d05523..e26fcef541 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out @@ -49,11 +49,11 @@ STAGE PLANS: b_n14 TableScan alias: b_n14 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -64,11 +64,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n18 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -76,10 +76,10 @@ STAGE PLANS: 0 1 outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 5000 Data size: 106120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5000 Data size: 106120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -118,11 +118,11 @@ STAGE PLANS: a_n18 TableScan alias: a_n18 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -131,14 +131,14 @@ STAGE PLANS: TableScan alias: d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -150,14 +150,14 @@ STAGE PLANS: TableScan alias: d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -165,7 +165,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -173,10 +173,10 @@ STAGE PLANS: 0 1 outputColumnNames: key, value, key0, value0, key1, value1 - Statistics: Num rows: 5500 Data size: 116432 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5500 Data size: 116432 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -221,14 +221,14 @@ STAGE PLANS: TableScan alias: od1:d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -240,14 +240,14 @@ STAGE PLANS: TableScan alias: od1:d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -255,21 +255,21 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: key - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -278,7 +278,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: key - Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -296,11 +296,11 @@ STAGE PLANS: a_n18 TableScan alias: a_n18 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -317,10 +317,10 @@ STAGE PLANS: 0 1 outputColumnNames: key, value, key0 - Statistics: Num rows: 2500 Data size: 52560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2500 Data size: 52560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -359,11 +359,11 @@ STAGE PLANS: od1:d1 TableScan alias: od1:d1 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -384,21 +384,21 @@ STAGE PLANS: 0 1 outputColumnNames: key - Statistics: Num rows: 100 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 100 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -407,7 +407,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: key - Statistics: Num rows: 50 Data size: 730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -425,11 +425,11 @@ STAGE PLANS: a_n18 TableScan alias: a_n18 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -446,10 +446,10 @@ STAGE PLANS: 0 1 outputColumnNames: key, value, key0 - Statistics: Num rows: 25000 Data size: 655600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25000 Data size: 655600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -493,28 +493,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ss:a_n18 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: key - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -550,10 +550,10 @@ STAGE PLANS: 0 1 outputColumnNames: key, key0 - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -587,10 +587,10 @@ STAGE PLANS: 0 1 outputColumnNames: key, key0 - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -605,12 +605,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -620,10 +620,10 @@ STAGE PLANS: 0 1 outputColumnNames: key, key0 - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -640,14 +640,14 @@ STAGE PLANS: TableScan alias: od1:d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -659,14 +659,14 @@ STAGE PLANS: TableScan alias: od1:d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -674,21 +674,21 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: key - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -697,7 +697,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: key - Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out index 3fb7f4a22d..e59b01f8d2 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_gby2_map_multi_distinct.q.out @@ -30,22 +30,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: $f0, $f1, $f2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 229500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT $f1), sum($f1), sum(DISTINCT $f1), count($f2) keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -53,14 +53,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: $f0, $f1, $f2, $f3, $f4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 54000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string), UDFToInteger($f3) (type: int), UDFToInteger($f4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -69,12 +69,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -106,7 +106,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -114,14 +114,14 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -188,22 +188,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: $f0, $f1, $f2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 229500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT $f0), sum($f1), sum(DISTINCT $f1), count($f2) keys: $f0 (type: string), $f1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -211,14 +211,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: $f0, $f1, $f2, $f3, $f4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 54000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string), UDFToInteger($f3) (type: int), UDFToInteger($f4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -227,12 +227,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -264,7 +264,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -272,14 +272,14 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out index 34cf06e19b..18923e32bc 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_groupby3_noskew_multi_distinct.q.out @@ -47,15 +47,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double) outputColumnNames: $f0, $f00, $f2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: $f0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: $f2 (type: double), $f00 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -63,14 +63,14 @@ STAGE PLANS: aggregations: sum(KEY._col0:0._col0), count(KEY._col0:0._col0), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), sum(VALUE._col0), sum(VALUE._col1) mode: complete outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: $f0 (type: double), ($f0 / $f1) (type: double), ($f2 / $f3) (type: double), UDFToDouble($f4) (type: double), UDFToDouble($f5) (type: double), power((($f6 - (($f7 * $f7) / $f1)) / $f1), 0.5) (type: double), power((($f6 - (($f7 * $f7) / $f1)) / CASE WHEN (($f1 = 1)) THEN (null) ELSE (($f1 - 1)) END), 0.5) (type: double), (($f6 - (($f7 * $f7) / $f1)) / $f1) (type: double), (($f6 - (($f7 * $f7) / $f1)) / CASE WHEN (($f1 = 1)) THEN (null) ELSE (($f1 - 1)) END) (type: double), $f2 (type: double), UDFToDouble($f3) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -79,19 +79,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll'), compute_stats(c10, 'hll'), compute_stats(c11, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 5256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 5256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4840 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4840 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_rp_join1.q.out b/ql/src/test/results/clientpositive/cbo_rp_join1.q.out index c5ec00dcc9..dd8b0a07f1 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_join1.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_join1.q.out @@ -30,25 +30,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) TableScan alias: b - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Join Operator @@ -61,11 +61,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(_col0,_col1,_col2,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -133,25 +133,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) TableScan alias: b - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Join Operator @@ -164,11 +164,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(_col0,_col1,_col2,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -236,25 +236,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) TableScan alias: b - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Join Operator @@ -267,11 +267,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(_col0,_col1,_col2,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash @@ -339,25 +339,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) TableScan alias: b - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Join Operator @@ -370,11 +370,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hash(_col0,_col1,_col2,_col3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) mode: hash diff --git a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out index cfc2dfcb5f..167d33a40f 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out @@ -27,44 +27,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) null sort order: a sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: value (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: key (type: string) null sort order: a sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: value (type: string) auto parallelism: false @@ -230,17 +230,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) outputColumnNames: key, value, key1, value1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -331,44 +331,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) null sort order: a sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: value (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: key (type: string) null sort order: a sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: value (type: string) auto parallelism: false @@ -534,17 +534,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: key, value, key0, value0 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) outputColumnNames: key, value, key1, value1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/cbo_rp_udaf_percentile_approx_23.q.out b/ql/src/test/results/clientpositive/cbo_rp_udaf_percentile_approx_23.q.out index 69785e1751..8a020debcb 100644 --- a/ql/src/test/results/clientpositive/cbo_rp_udaf_percentile_approx_23.q.out +++ b/ql/src/test/results/clientpositive/cbo_rp_udaf_percentile_approx_23.q.out @@ -510,29 +510,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: bucket_n1 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CASE WHEN ((key < 100.0D)) THEN (NaND) ELSE (key) END (type: double) outputColumnNames: $f0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: percentile_approx($f0, 0.5) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array) Reduce Operator Tree: Group By Operator aggregations: percentile_approx(VALUE._col0) mode: mergepartial outputColumnNames: $f0 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -569,29 +569,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: bucket_n1 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: double) outputColumnNames: $f0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: percentile_approx($f0, 0.5) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array) Reduce Operator Tree: Group By Operator aggregations: percentile_approx(VALUE._col0) mode: mergepartial outputColumnNames: $f0 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cbo_union_view.q.out b/ql/src/test/results/clientpositive/cbo_union_view.q.out index ecd4ec7547..085b94252f 100644 --- a/ql/src/test/results/clientpositive/cbo_union_view.q.out +++ b/ql/src/test/results/clientpositive/cbo_union_view.q.out @@ -69,23 +69,23 @@ STAGE PLANS: filterExpr: (key = 86) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -95,23 +95,23 @@ STAGE PLANS: filterExpr: (key = 86) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -121,23 +121,23 @@ STAGE PLANS: filterExpr: (key = 86) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -166,23 +166,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '1')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '1') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -192,23 +192,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '1')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '1') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -218,23 +218,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '1')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '1') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/column_pruner_multiple_children.q.out b/ql/src/test/results/clientpositive/column_pruner_multiple_children.q.out index cd0c969c48..3532bc4a09 100644 --- a/ql/src/test/results/clientpositive/column_pruner_multiple_children.q.out +++ b/ql/src/test/results/clientpositive/column_pruner_multiple_children.q.out @@ -36,16 +36,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s_n129 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -54,14 +54,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -70,7 +70,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -102,7 +102,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -110,10 +110,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/column_pruning_partitioned_view.q.out b/ql/src/test/results/clientpositive/column_pruning_partitioned_view.q.out index 3b9fe540a6..f498b032b2 100644 --- a/ql/src/test/results/clientpositive/column_pruning_partitioned_view.q.out +++ b/ql/src/test/results/clientpositive/column_pruning_partitioned_view.q.out @@ -33,10 +33,10 @@ STAGE PLANS: alias: lv_table properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: c1 (type: string), c2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL ListSink diff --git a/ql/src/test/results/clientpositive/columnarserde_create_shortcut.q.out b/ql/src/test/results/clientpositive/columnarserde_create_shortcut.q.out index 69488108d9..1f88f2106b 100644 --- a/ql/src/test/results/clientpositive/columnarserde_create_shortcut.q.out +++ b/ql/src/test/results/clientpositive/columnarserde_create_shortcut.q.out @@ -25,25 +25,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint (type: array), lstring (type: array), mstringstring (type: map), aint (type: int), astring (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array), _col1 (type: array), _col2 (type: map), _col3 (type: int), _col4 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: array), VALUE._col1 (type: array), VALUE._col2 (type: map), VALUE._col3 (type: int), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/columnstats_partlvl.q.out b/ql/src/test/results/clientpositive/columnstats_partlvl.q.out index 9792ef1af8..9a34679499 100644 --- a/ql/src/test/results/clientpositive/columnstats_partlvl.q.out +++ b/ql/src/test/results/clientpositive/columnstats_partlvl.q.out @@ -47,22 +47,22 @@ STAGE PLANS: TableScan alias: employee_part filterExpr: (employeesalary = 2000.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: employeeid (type: int) outputColumnNames: employeeid - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(employeeid, 'hll') keys: 2000.0D (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: 2000.0D (type: double) sort order: + Map-reduce partition columns: 2000.0D (type: double) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator @@ -70,14 +70,14 @@ STAGE PLANS: keys: 2000.0D (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col1 (type: struct), 2000.0D (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -108,25 +108,25 @@ STAGE PLANS: TableScan alias: employee_part filterExpr: (employeesalary = 2000.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Statistics Aggregation Key Prefix: default.employee_part/ GatherStats: true Select Operator expressions: employeeid (type: int) outputColumnNames: employeeid - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(employeeid, 'hll') keys: 2000.0D (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: 2000.0D (type: double) null sort order: a sort order: + Map-reduce partition columns: 2000.0D (type: double) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE tag: -1 value expressions: _col1 (type: struct) auto parallelism: false @@ -191,17 +191,17 @@ STAGE PLANS: keys: 2000.0D (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col1 (type: struct), 2000.0D (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -298,22 +298,22 @@ STAGE PLANS: TableScan alias: employee_part filterExpr: (employeesalary = 4000.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: employeeid (type: int) outputColumnNames: employeeid - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(employeeid, 'hll') keys: 4000.0D (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: 4000.0D (type: double) sort order: + Map-reduce partition columns: 4000.0D (type: double) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator @@ -321,14 +321,14 @@ STAGE PLANS: keys: 4000.0D (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col1 (type: struct), 4000.0D (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -359,25 +359,25 @@ STAGE PLANS: TableScan alias: employee_part filterExpr: (employeesalary = 4000.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Statistics Aggregation Key Prefix: default.employee_part/ GatherStats: true Select Operator expressions: employeeid (type: int) outputColumnNames: employeeid - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(employeeid, 'hll') keys: 4000.0D (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: 4000.0D (type: double) null sort order: a sort order: + Map-reduce partition columns: 4000.0D (type: double) - Statistics: Num rows: 3 Data size: 1050 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1062 Basic stats: PARTIAL Column stats: NONE tag: -1 value expressions: _col1 (type: struct) auto parallelism: false @@ -442,17 +442,17 @@ STAGE PLANS: keys: 4000.0D (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col1 (type: struct), 4000.0D (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 350 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 354 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -511,22 +511,22 @@ STAGE PLANS: TableScan alias: employee_part filterExpr: (employeesalary = 2000.0D) (type: boolean) - Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: employeeid (type: int), employeename (type: string) outputColumnNames: employeeid, employeename - Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(employeeid, 'hll'), compute_stats(employeename, 'hll') keys: 2000.0D (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: 2000.0D (type: double) sort order: + Map-reduce partition columns: 2000.0D (type: double) - Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -534,14 +534,14 @@ STAGE PLANS: keys: 2000.0D (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col1 (type: struct), _col2 (type: struct), 2000.0D (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -621,22 +621,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: employee_part - Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2596 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: employeeid (type: int), employeename (type: string), employeesalary (type: double) outputColumnNames: employeeid, employeename, employeesalary - Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2596 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(employeeid, 'hll'), compute_stats(employeename, 'hll') keys: employeesalary (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1744 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1744 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -644,14 +644,14 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1776 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1776 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1776 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -735,29 +735,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: employee_part - Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2388 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: employeeid (type: int), employeename (type: string) outputColumnNames: employeeid, employeename - Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2388 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(employeeid, 'hll'), compute_stats(employeename, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -807,7 +807,7 @@ num_trues num_falses bitVector HL comment from deserializer -COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"employeeid\":\"true\",\"employeename\":\"true\"}} +COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"employeename\":\"true\"}} PREHOOK: query: create database if not exists dummydb PREHOOK: type: CREATEDATABASE PREHOOK: Output: database:dummydb diff --git a/ql/src/test/results/clientpositive/columnstats_partlvl_dp.q.out b/ql/src/test/results/clientpositive/columnstats_partlvl_dp.q.out index 2fed6fdfe0..b03b4c8c1d 100644 --- a/ql/src/test/results/clientpositive/columnstats_partlvl_dp.q.out +++ b/ql/src/test/results/clientpositive/columnstats_partlvl_dp.q.out @@ -83,22 +83,22 @@ STAGE PLANS: TableScan alias: employee_part_n0 filterExpr: (employeesalary = 4000.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 640 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1012 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: employeeid (type: int), employeename (type: string), country (type: string) outputColumnNames: employeeid, employeename, country - Statistics: Num rows: 1 Data size: 640 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1012 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator aggregations: compute_stats(employeename, 'hll'), compute_stats(employeeid, 'hll') keys: 4000.0D (type: double), country (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 640 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1236 Basic stats: PARTIAL Column stats: PARTIAL Reduce Output Operator key expressions: 4000.0D (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: 4000.0D (type: double), _col1 (type: string) - Statistics: Num rows: 1 Data size: 640 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1236 Basic stats: PARTIAL Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -106,14 +106,14 @@ STAGE PLANS: keys: 4000.0D (type: double), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 640 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1252 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), 4000.0D (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 640 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1252 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 640 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1252 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -215,22 +215,22 @@ STAGE PLANS: TableScan alias: employee_part_n0 filterExpr: (employeesalary = 2000.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 1690 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 2254 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: employeeid (type: int), country (type: string) outputColumnNames: employeeid, country - Statistics: Num rows: 3 Data size: 1690 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 2254 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator aggregations: compute_stats(employeeid, 'hll') keys: 2000.0D (type: double), country (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 1690 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1836 Basic stats: PARTIAL Column stats: PARTIAL Reduce Output Operator key expressions: 2000.0D (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: 2000.0D (type: double), _col1 (type: string) - Statistics: Num rows: 3 Data size: 1690 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1836 Basic stats: PARTIAL Column stats: PARTIAL value expressions: _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -238,14 +238,14 @@ STAGE PLANS: keys: 2000.0D (type: double), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 563 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 628 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), 2000.0D (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 563 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 628 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 563 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 628 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -329,22 +329,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: employee_part_n0 - Statistics: Num rows: 31 Data size: 2536 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 31 Data size: 6072 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: employeeid (type: int), employeesalary (type: double), country (type: string) outputColumnNames: employeeid, employeesalary, country - Statistics: Num rows: 31 Data size: 2536 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 31 Data size: 6072 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator aggregations: compute_stats(employeeid, 'hll') keys: employeesalary (type: double), country (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 31 Data size: 2536 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 31 Data size: 19216 Basic stats: PARTIAL Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double), _col1 (type: string) - Statistics: Num rows: 31 Data size: 2536 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 31 Data size: 19216 Basic stats: PARTIAL Column stats: PARTIAL value expressions: _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -352,14 +352,14 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 1227 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 15 Data size: 9536 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col0 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 1227 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 15 Data size: 9536 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 1227 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 15 Data size: 9536 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,22 +441,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: employee_part_n0 - Statistics: Num rows: 54 Data size: 412 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 15386 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: employeeid (type: int), employeename (type: string), employeesalary (type: double), country (type: string) outputColumnNames: employeeid, employeename, employeesalary, country - Statistics: Num rows: 54 Data size: 412 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 15386 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(employeeid, 'hll'), compute_stats(employeename, 'hll') keys: employeesalary (type: double), country (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 54 Data size: 412 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 8448 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double), _col1 (type: string) - Statistics: Num rows: 54 Data size: 412 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 8448 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -464,14 +464,14 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 8576 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 8576 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 8576 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/columnstats_quoting.q.out b/ql/src/test/results/clientpositive/columnstats_quoting.q.out index 8ed8239711..822dbdb219 100644 --- a/ql/src/test/results/clientpositive/columnstats_quoting.q.out +++ b/ql/src/test/results/clientpositive/columnstats_quoting.q.out @@ -24,29 +24,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: user_web_events - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: user id (type: bigint), user name (type: string) outputColumnNames: user id, user name - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(user id, 'hll'), compute_stats(user name, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1072 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1072 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -84,29 +84,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: user_web_events - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: user id (type: bigint) outputColumnNames: user id - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(user id, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out index 0b4bb47988..4e68a986f5 100644 --- a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out +++ b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out @@ -54,29 +54,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_web_text_none - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -106,22 +106,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_web_text_none - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Statistics Aggregation Key Prefix: default.uservisits_web_text_none/ GatherStats: true Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -184,13 +184,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -244,29 +244,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_web_text_none - Statistics: Num rows: 55 Data size: 7005 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 65391 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: sourceip (type: string), desturl (type: string), visitdate (type: string), adrevenue (type: float), useragent (type: string), ccode (type: string), lcode (type: string), skeyword (type: string), avgtimeonsite (type: int) outputColumnNames: sourceip, desturl, visitdate, adrevenue, useragent, ccode, lcode, skeyword, avgtimeonsite - Statistics: Num rows: 55 Data size: 7005 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 65391 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(desturl, 'hll'), compute_stats(visitdate, 'hll'), compute_stats(adrevenue, 'hll'), compute_stats(useragent, 'hll'), compute_stats(ccode, 'hll'), compute_stats(lcode, 'hll'), compute_stats(skeyword, 'hll'), compute_stats(avgtimeonsite, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -383,29 +383,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: empty_tab - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary) outputColumnNames: a, b, c, d, e - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll'), compute_stats(e, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 1848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 1880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -528,29 +528,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_in_dummy_db - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -580,22 +580,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_in_dummy_db - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Statistics Aggregation Key Prefix: dummydb.uservisits_in_dummy_db/ GatherStats: true Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -658,13 +658,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -718,29 +718,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_in_dummy_db - Statistics: Num rows: 55 Data size: 7005 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 65391 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: sourceip (type: string), desturl (type: string), visitdate (type: string), adrevenue (type: float), useragent (type: string), ccode (type: string), lcode (type: string), skeyword (type: string), avgtimeonsite (type: int) outputColumnNames: sourceip, desturl, visitdate, adrevenue, useragent, ccode, lcode, skeyword, avgtimeonsite - Statistics: Num rows: 55 Data size: 7005 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 65391 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(desturl, 'hll'), compute_stats(visitdate, 'hll'), compute_stats(adrevenue, 'hll'), compute_stats(useragent, 'hll'), compute_stats(ccode, 'hll'), compute_stats(lcode, 'hll'), compute_stats(skeyword, 'hll'), compute_stats(avgtimeonsite, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3928 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/combine2.q.out b/ql/src/test/results/clientpositive/combine2.q.out index 7c39a6864d..43b6f1c45b 100644 --- a/ql/src/test/results/clientpositive/combine2.q.out +++ b/ql/src/test/results/clientpositive/combine2.q.out @@ -78,11 +78,11 @@ STAGE PLANS: TableScan alias: combine2_n0 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 12 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 3240 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key, value from combine2_n0 where value is not null @@ -166,22 +166,22 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: ds - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 192000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 192000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -190,10 +190,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/comments.q.out b/ql/src/test/results/clientpositive/comments.q.out index 314707d4d1..f32acb8e71 100644 --- a/ql/src/test/results/clientpositive/comments.q.out +++ b/ql/src/test/results/clientpositive/comments.q.out @@ -99,16 +99,16 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(key) > 0.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) > 0.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -121,16 +121,16 @@ STAGE PLANS: TableScan alias: b filterExpr: (UDFToDouble(key) > 0.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) > 0.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -138,16 +138,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -213,13 +213,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/complex_alias.q.out b/ql/src/test/results/clientpositive/complex_alias.q.out index e81b3b577d..3ad37daf74 100644 --- a/ql/src/test/results/clientpositive/complex_alias.q.out +++ b/ql/src/test/results/clientpositive/complex_alias.q.out @@ -74,30 +74,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: agg1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col0 (type: int) outputColumnNames: col0 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -111,11 +111,11 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -125,14 +125,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -144,59 +144,59 @@ STAGE PLANS: TableScan alias: agg1 filterExpr: (col0 = col0) (type: boolean) - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (col0 = col0) (type: boolean) - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '42' (type: string), col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 34 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 34 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 2 Data size: 34 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: agg1 filterExpr: (col0 = col0) (type: boolean) - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (col0 = col0) (type: boolean) - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '41' (type: string), col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 34 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 34 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 2 Data size: 34 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/compute_stats_date.q.out b/ql/src/test/results/clientpositive/compute_stats_date.q.out index 6715e05bf0..c2fbb4b0a1 100644 --- a/ql/src/test/results/clientpositive/compute_stats_date.q.out +++ b/ql/src/test/results/clientpositive/compute_stats_date.q.out @@ -60,29 +60,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tab_date - Statistics: Num rows: 1 Data size: 7780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) outputColumnNames: fl_date - Statistics: Num rows: 1 Data size: 7780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(fl_date, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 536 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 536 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/concat_op.q.out b/ql/src/test/results/clientpositive/concat_op.q.out index 0ad2d6f8c0..60e12660b7 100644 --- a/ql/src/test/results/clientpositive/concat_op.q.out +++ b/ql/src/test/results/clientpositive/concat_op.q.out @@ -12,14 +12,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: concat(key, value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constantPropWhen.q.out b/ql/src/test/results/clientpositive/constantPropWhen.q.out index 82fd74f854..f0bb2da78e 100644 --- a/ql/src/test/results/clientpositive/constantPropWhen.q.out +++ b/ql/src/test/results/clientpositive/constantPropWhen.q.out @@ -34,14 +34,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (not NVL((id = id2),false)) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -80,14 +80,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (not NVL((id = id2),false)) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -126,14 +126,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: NVL((id = id2),false) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -172,14 +172,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: NVL((id = id2),false) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -218,14 +218,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (not NVL((id = id2),false)) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -264,14 +264,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (not NVL((id = id2),false)) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -310,14 +310,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: NVL((id = id2),false) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -356,14 +356,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n4 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: NVL((id = id2),false) (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out b/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out index 532e977932..fe6032ecce 100644 --- a/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out +++ b/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out @@ -22,35 +22,35 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = '429') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '429') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -165,17 +165,17 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 6250 Data size: 120400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 13300 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '429' (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6250 Data size: 120400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 17650 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6250 Data size: 120400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 17650 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/constant_prop_1.q.out b/ql/src/test/results/clientpositive/constant_prop_1.q.out index e1e7cf5e03..1733ffdf2d 100644 --- a/ql/src/test/results/clientpositive/constant_prop_1.q.out +++ b/ql/src/test/results/clientpositive/constant_prop_1.q.out @@ -144,13 +144,13 @@ STAGE PLANS: TableScan alias: b filterExpr: (value = '12345') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value = '12345') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -160,14 +160,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col1 - Statistics: Num rows: 250 Data size: 4906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), _col1 (type: string), '12345' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 4906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 4906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -328,13 +328,13 @@ STAGE PLANS: TableScan alias: b filterExpr: (value = '12345') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value = '12345') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -344,14 +344,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 3906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), '12345' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 3906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 3906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -381,23 +381,23 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: (value = '234') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value = '234') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -405,14 +405,14 @@ STAGE PLANS: keys: 0 1 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '238' (type: string), '234' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,27 +441,27 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: (key is not null and (value = '234')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value = '234') and key is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -470,14 +470,14 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), '234' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -530,17 +530,17 @@ STAGE PLANS: TableScan alias: t_n26 filterExpr: ((a = 1) and (b = 2) and (c = 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((a = 1) and (b = 2) and (c = 3)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constant_prop_2.q.out b/ql/src/test/results/clientpositive/constant_prop_2.q.out index 6fef7f996f..a896d4e18b 100644 --- a/ql/src/test/results/clientpositive/constant_prop_2.q.out +++ b/ql/src/test/results/clientpositive/constant_prop_2.q.out @@ -38,22 +38,22 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: '2008-04-08' (type: string), '11' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: '2008-04-08' (type: string), '11' (type: string) sort order: ++ Map-reduce partition columns: '2008-04-08' (type: string), '11' (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -61,14 +61,14 @@ STAGE PLANS: keys: '2008-04-08' (type: string), '11' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constant_prop_3.q.out b/ql/src/test/results/clientpositive/constant_prop_3.q.out index 2fbd2d4401..52b4f3b7e0 100644 --- a/ql/src/test/results/clientpositive/constant_prop_3.q.out +++ b/ql/src/test/results/clientpositive/constant_prop_3.q.out @@ -174,36 +174,36 @@ STAGE PLANS: TableScan alias: partsupp_hive filterExpr: ps_partkey is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ps_partkey is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ps_partkey (type: int), ps_suppkey (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: part_hive filterExpr: ((p_size) IN (22, 14, 27, 49, 21, 33, 35, 28) and (p_brand <> 'Brand#34') and p_partkey is not null and (not (p_type like 'ECONOMY BRUSHED%'))) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((not (p_type like 'ECONOMY BRUSHED%')) and (p_brand <> 'Brand#34') and (p_size) IN (22, 14, 27, 49, 21, 33, 35, 28) and p_partkey is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int) Reduce Operator Tree: Join Operator @@ -213,7 +213,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -227,12 +227,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -242,7 +242,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 17 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -258,14 +258,14 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 17 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: bigint), _col7 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -275,20 +275,20 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col9 - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col6 = 0L) or (_col9 is null and _col1 is not null and (_col7 >= _col6))) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int) outputColumnNames: _col1, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col1) keys: _col3 (type: string), _col4 (type: string), _col5 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -304,7 +304,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -312,7 +312,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -327,16 +327,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col3 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: -+++ - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 18 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -348,22 +348,22 @@ STAGE PLANS: TableScan alias: supplier_hive filterExpr: (s_comment like '%Customer%Complaints%') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_comment like '%Customer%Complaints%') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_suppkey (type: int) outputColumnNames: s_suppkey - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(s_suppkey) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -371,7 +371,7 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -385,35 +385,35 @@ STAGE PLANS: TableScan alias: supplier_hive filterExpr: (s_comment like '%Customer%Complaints%') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_comment like '%Customer%Complaints%') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_suppkey (type: int) outputColumnNames: s_suppkey - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: s_suppkey (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/constprog2.q.out b/ql/src/test/results/clientpositive/constprog2.q.out index d5615d6228..2204f39b86 100644 --- a/ql/src/test/results/clientpositive/constprog2.q.out +++ b/ql/src/test/results/clientpositive/constprog2.q.out @@ -18,29 +18,29 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key = 86) (type: boolean) - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: (key = 86) (type: boolean) - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -50,14 +50,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col2 - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), 87 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -89,29 +89,29 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: (key = 86) (type: boolean) - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -121,14 +121,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col2 - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 91000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), 87 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constprog3.q.out b/ql/src/test/results/clientpositive/constprog3.q.out index 9fc06d6a26..efbe007e62 100644 --- a/ql/src/test/results/clientpositive/constprog3.q.out +++ b/ql/src/test/results/clientpositive/constprog3.q.out @@ -35,17 +35,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: table1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int), val (type: int), val1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) TableScan alias: table3 @@ -66,10 +66,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constprog_dp.q.out b/ql/src/test/results/clientpositive/constprog_dp.q.out index 67a9206555..faa1fb1a53 100644 --- a/ql/src/test/results/clientpositive/constprog_dp.q.out +++ b/ql/src/test/results/clientpositive/constprog_dp.q.out @@ -31,14 +31,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -47,18 +47,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -66,14 +66,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constprog_partitioner.q.out b/ql/src/test/results/clientpositive/constprog_partitioner.q.out index 917382e129..8d910a6a62 100644 --- a/ql/src/test/results/clientpositive/constprog_partitioner.q.out +++ b/ql/src/test/results/clientpositive/constprog_partitioner.q.out @@ -18,29 +18,29 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -50,14 +50,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col2 - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 100 (type: int), 101 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 5551000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -92,41 +92,41 @@ STAGE PLANS: TableScan alias: li filterExpr: ((l_linenumber = 1) and l_orderkey is not null) (type: boolean) - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((l_linenumber = 1) and l_orderkey is not null) (type: boolean) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), 1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), 1 (type: int) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: int) TableScan alias: lineitem filterExpr: ((l_shipmode = 'AIR') and (l_linenumber = 1) and l_orderkey is not null) (type: boolean) - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((l_linenumber = 1) and (l_shipmode = 'AIR') and l_orderkey is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_orderkey (type: int), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -135,14 +135,14 @@ STAGE PLANS: 0 _col0 (type: int), 1 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/constprog_when_case.q.out b/ql/src/test/results/clientpositive/constprog_when_case.q.out index 4d2214aa55..c8c9ddf9c5 100644 --- a/ql/src/test/results/clientpositive/constprog_when_case.q.out +++ b/ql/src/test/results/clientpositive/constprog_when_case.q.out @@ -44,14 +44,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_orc - Statistics: Num rows: 1000 Data size: 266000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 269000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: if(CASE WHEN (bool0) THEN (true) WHEN ((not bool0)) THEN (false) ELSE (null) END, key0, if(CASE WHEN (bool0) THEN (false) WHEN ((not bool0)) THEN (true) ELSE (null) END, key1, key2)) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 266000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 266000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer10.q.out b/ql/src/test/results/clientpositive/correlationoptimizer10.q.out index 440122056c..c5864f1df5 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer10.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer10.q.out @@ -25,35 +25,35 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -62,13 +62,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -84,7 +84,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -93,7 +93,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -109,29 +109,29 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -140,10 +140,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -214,59 +214,59 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 550 Data size: 5694 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 26050 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -274,17 +274,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 605 Data size: 6263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 330 Data size: 28655 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 605 Data size: 6263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 330 Data size: 28655 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3126 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 165 Data size: 14327 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 852 Data size: 8820 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 465 Data size: 40377 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Left Semi Join 0 to 1 @@ -292,16 +292,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 44414 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 44414 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 852 Data size: 8820 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 465 Data size: 40377 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Left Semi Join 0 to 1 @@ -309,10 +309,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 44414 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 44414 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -392,35 +392,35 @@ STAGE PLANS: TableScan alias: x filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(key) < 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -429,12 +429,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2349 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -448,26 +448,26 @@ STAGE PLANS: TableScan alias: xx filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2349 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -476,10 +476,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -556,57 +556,57 @@ STAGE PLANS: TableScan alias: xx filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: x filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(key) < 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 112 Data size: 1183 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 9920 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 235 Data size: 2484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 235 Data size: 20832 Basic stats: COMPLETE Column stats: PARTIAL Join Operator condition map: Left Semi Join 0 to 1 @@ -614,10 +614,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 258 Data size: 2732 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 258 Data size: 22915 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 258 Data size: 2732 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 258 Data size: 22915 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -629,9 +629,9 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 123 Data size: 1301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 10912 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 235 Data size: 2484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 235 Data size: 20832 Basic stats: COMPLETE Column stats: PARTIAL Join Operator condition map: Left Semi Join 0 to 1 @@ -639,10 +639,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 258 Data size: 2732 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 258 Data size: 22915 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 258 Data size: 2732 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 258 Data size: 22915 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -718,35 +718,35 @@ STAGE PLANS: TableScan alias: x filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -755,12 +755,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2349 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -774,26 +774,26 @@ STAGE PLANS: TableScan alias: xx filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2349 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -802,10 +802,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 66 Data size: 706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -894,57 +894,57 @@ STAGE PLANS: TableScan alias: xx filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: x filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 200.0D) and (UDFToDouble(key) > 180.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 165 Data size: 1752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 165 Data size: 19360 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 346 Data size: 3679 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 346 Data size: 40656 Basic stats: COMPLETE Column stats: PARTIAL Join Operator condition map: Left Semi Join 0 to 1 @@ -952,10 +952,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 380 Data size: 4046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 380 Data size: 44721 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 380 Data size: 4046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 380 Data size: 44721 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -967,9 +967,9 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 181 Data size: 1927 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 181 Data size: 21296 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 346 Data size: 3679 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 346 Data size: 40656 Basic stats: COMPLETE Column stats: PARTIAL Join Operator condition map: Left Semi Join 0 to 1 @@ -977,10 +977,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 380 Data size: 4046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 380 Data size: 44721 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 380 Data size: 4046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 380 Data size: 44721 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer11.q.out b/ql/src/test/results/clientpositive/correlationoptimizer11.q.out index f0ce4112f7..6efb29149d 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer11.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer11.q.out @@ -56,35 +56,35 @@ STAGE PLANS: TableScan alias: x filterExpr: ((partitionid = 1) and key is not null) (type: boolean) - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8700 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8700 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((partitionid = 2) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -93,13 +93,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 110 Data size: 1177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 665 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -115,7 +115,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 110 Data size: 1177 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 665 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -124,10 +124,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 588 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 665 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 588 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 665 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -187,38 +187,38 @@ STAGE PLANS: TableScan alias: x filterExpr: ((partitionid = 1) and key is not null) (type: boolean) - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8700 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8700 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1070 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9100 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((partitionid = 2) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 125 Data size: 1261 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 11350 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -226,18 +226,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 137 Data size: 1387 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 12485 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 137 Data size: 1387 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 12485 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 68 Data size: 688 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 68 Data size: 6196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 68 Data size: 688 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 68 Data size: 6196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -298,35 +298,35 @@ STAGE PLANS: TableScan alias: x filterExpr: ((partitionid = 2) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((partitionid = 2) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -335,13 +335,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -357,7 +357,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -366,10 +366,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -440,38 +440,38 @@ STAGE PLANS: TableScan alias: x filterExpr: ((partitionid = 2) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: ((partitionid = 2) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 50 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4500 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -479,18 +479,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4950 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4950 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2430 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2430 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer12.q.out b/ql/src/test/results/clientpositive/correlationoptimizer12.q.out index e63595d244..e4bbf8875d 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer12.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer12.q.out @@ -25,22 +25,22 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -60,11 +60,11 @@ STAGE PLANS: name: count window function: GenericUDAFCountEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), count_window_0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -80,14 +80,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2350 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -97,10 +97,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7371 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7371 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -112,22 +112,22 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 11075 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -147,11 +147,11 @@ STAGE PLANS: name: count window function: GenericUDAFCountEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 11075 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), count_window_0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2350 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out index ada79213f6..6f65741262 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer13.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer13.q.out @@ -48,56 +48,56 @@ STAGE PLANS: TableScan alias: x filterExpr: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 97660 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 342 Data size: 32490 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan alias: x1 filterExpr: ((c2 > 100) and (c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 101772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and (c2 > 100) and c3 is not null) (type: boolean) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c3 (type: string) outputColumnNames: c1, c3 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 456 Data size: 10185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 456 Data size: 10184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 456 Data size: 46968 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -105,11 +105,11 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -121,9 +121,9 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 456 Data size: 10184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 456 Data size: 46968 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -131,11 +131,11 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -150,16 +150,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: bigint), _col5 (type: bigint) sort order: ++++++ - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: bigint), KEY.reducesinkkey5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer14.q.out b/ql/src/test/results/clientpositive/correlationoptimizer14.q.out index cca6892662..1c7330b5d6 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer14.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer14.q.out @@ -27,25 +27,25 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -61,14 +61,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -78,10 +78,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -93,25 +93,25 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -154,25 +154,25 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -188,14 +188,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -205,10 +205,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -220,25 +220,25 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -281,26 +281,26 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -316,14 +316,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -333,10 +333,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -348,26 +348,26 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -465,46 +465,46 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 93375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 93450 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 1050 Data size: 11006 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 186900 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -512,10 +512,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -523,9 +523,9 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 93450 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 1050 Data size: 11006 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 186900 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -533,10 +533,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -634,26 +634,26 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -669,14 +669,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -686,10 +686,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -701,26 +701,26 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -763,25 +763,25 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -797,14 +797,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -814,10 +814,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -829,25 +829,25 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -890,26 +890,26 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -925,14 +925,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -942,10 +942,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -957,26 +957,26 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1074,46 +1074,46 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 93375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 93450 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 1050 Data size: 11006 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 186900 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -1121,10 +1121,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1132,9 +1132,9 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 93450 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 1050 Data size: 11006 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 186900 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -1142,10 +1142,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1155 Data size: 12106 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1155 Data size: 205590 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1243,26 +1243,26 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1278,14 +1278,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -1295,10 +1295,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 4896 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 4896 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1310,21 +1310,21 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1333,7 +1333,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1431,48 +1431,48 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 512 Data size: 90128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 512 Data size: 91648 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 787 Data size: 8249 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 524 Data size: 92776 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -1480,10 +1480,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 865 Data size: 9073 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 576 Data size: 102053 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 865 Data size: 9073 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 576 Data size: 102053 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1493,9 +1493,9 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 787 Data size: 8249 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 524 Data size: 92776 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -1503,10 +1503,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 865 Data size: 9073 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 576 Data size: 102053 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 865 Data size: 9073 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 576 Data size: 102053 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer15.q.out b/ql/src/test/results/clientpositive/correlationoptimizer15.q.out index 6e3ea641f9..a4838ea88a 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer15.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer15.q.out @@ -26,35 +26,35 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -63,13 +63,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -85,7 +85,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -94,7 +94,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -110,24 +110,24 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -136,7 +136,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -151,16 +151,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) sort order: +++ - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -252,54 +252,54 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 550 Data size: 5694 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47800 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -307,17 +307,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 605 Data size: 6263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52580 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 605 Data size: 6263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52580 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3126 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 302 Data size: 26246 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 852 Data size: 8820 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 74046 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -325,16 +325,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 937 Data size: 81450 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 937 Data size: 81450 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 852 Data size: 8820 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 74046 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -342,10 +342,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 937 Data size: 81450 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 937 Data size: 9702 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 937 Data size: 81450 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer5.q.out b/ql/src/test/results/clientpositive/correlationoptimizer5.q.out index 483139c51c..6bffdf615a 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer5.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer5.q.out @@ -117,36 +117,36 @@ STAGE PLANS: TableScan alias: n filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: m filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -155,11 +155,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -173,41 +173,41 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -219,14 +219,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col3 - Statistics: Num rows: 2 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -305,73 +305,73 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: n filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: m filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 4 Data size: 120990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 200 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 12 Data size: 375069 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 620 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 @@ -381,14 +381,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col3 - Statistics: Num rows: 13 Data size: 412575 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 682 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 412575 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 682 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 412575 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 682 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -401,13 +401,13 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 4 Data size: 133089 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 133089 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 220 Basic stats: COMPLETE Column stats: NONE Mux Operator - Statistics: Num rows: 12 Data size: 375069 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 620 Basic stats: COMPLETE Column stats: NONE Join Operator condition map: Inner Join 0 to 1 @@ -417,14 +417,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col3 - Statistics: Num rows: 13 Data size: 412575 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 682 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 412575 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 682 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 412575 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 682 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -515,14 +515,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -532,14 +532,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 57910 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -549,14 +549,14 @@ STAGE PLANS: TableScan alias: m filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -568,14 +568,14 @@ STAGE PLANS: TableScan alias: n filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -583,11 +583,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -597,14 +597,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col3 - Statistics: Num rows: 2 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer7.q.out b/ql/src/test/results/clientpositive/correlationoptimizer7.q.out index e03e6695ac..837939aa8b 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer7.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer7.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,18 +67,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Local Work: @@ -89,7 +89,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -108,14 +108,14 @@ STAGE PLANS: TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -132,10 +132,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 810 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 810 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -218,14 +218,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -237,31 +237,31 @@ STAGE PLANS: TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -269,32 +269,32 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Demux Operator - Statistics: Num rows: 575 Data size: 6034 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4565 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 287 Data size: 3011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 862 Data size: 9045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 4755 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -302,16 +302,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 862 Data size: 9045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 4755 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -319,10 +319,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -404,14 +404,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -423,14 +423,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -438,18 +438,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Local Work: @@ -460,7 +460,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -479,14 +479,14 @@ STAGE PLANS: TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -503,10 +503,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 810 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 810 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -589,14 +589,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -608,31 +608,31 @@ STAGE PLANS: TableScan alias: yy filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -640,32 +640,32 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: Demux Operator - Statistics: Num rows: 575 Data size: 6034 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4565 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 287 Data size: 3011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 862 Data size: 9045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 4755 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -673,16 +673,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 862 Data size: 9045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 4755 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -690,10 +690,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 948 Data size: 9949 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31 Data size: 5230 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/correlationoptimizer8.q.out b/ql/src/test/results/clientpositive/correlationoptimizer8.q.out index 102cc01ad3..ba3b35e063 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer8.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer8.q.out @@ -29,21 +29,21 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -52,7 +52,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -65,38 +65,38 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x filterExpr: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -106,14 +106,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,21 +125,21 @@ STAGE PLANS: TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -148,7 +148,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -226,71 +226,71 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x filterExpr: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 348 Data size: 3648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 18570 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 174 Data size: 1824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 348 Data size: 3648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 696 Data size: 7296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348 Data size: 34340 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -298,14 +298,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -315,11 +315,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 174 Data size: 1824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 348 Data size: 3648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 696 Data size: 7296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348 Data size: 34340 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -327,20 +327,20 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 696 Data size: 7296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348 Data size: 34340 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -348,14 +348,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 765 Data size: 8025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 37774 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -433,21 +433,21 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -456,7 +456,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -469,34 +469,34 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8273 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8273 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8273 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87 Data size: 911 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8273 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -506,10 +506,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 95 Data size: 1002 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 13164 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 95 Data size: 1002 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 13164 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -521,25 +521,25 @@ STAGE PLANS: TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -548,7 +548,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -646,71 +646,71 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 199 Data size: 2015 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 12648 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 1002 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8051 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 198 Data size: 2004 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 16102 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 397 Data size: 4019 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 278 Data size: 28750 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Left Outer Join 0 to 1 @@ -718,10 +718,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 436 Data size: 4420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 305 Data size: 31625 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 436 Data size: 4420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 305 Data size: 31625 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -731,11 +731,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 1002 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8051 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 198 Data size: 2004 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 16102 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 397 Data size: 4019 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 278 Data size: 28750 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Left Outer Join 0 to 1 @@ -743,16 +743,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 436 Data size: 4420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 305 Data size: 31625 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 436 Data size: 4420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 305 Data size: 31625 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 397 Data size: 4019 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 278 Data size: 28750 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Left Outer Join 0 to 1 @@ -760,10 +760,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 436 Data size: 4420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 305 Data size: 31625 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 436 Data size: 4420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 305 Data size: 31625 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -861,21 +861,21 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -884,7 +884,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -897,38 +897,38 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x filterExpr: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -938,14 +938,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -957,21 +957,21 @@ STAGE PLANS: TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -980,11 +980,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1030,21 +1030,21 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1053,11 +1053,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToLong(UDFToInteger(_col0)) (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1070,34 +1070,34 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 2656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 2656 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) TableScan Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 2656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 2656 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) TableScan alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1107,10 +1107,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191 Data size: 9741 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191 Data size: 9741 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1122,21 +1122,21 @@ STAGE PLANS: TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1145,11 +1145,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), UDFToLong(UDFToInteger(_col0)) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out index f8e75c2671..abadba4235 100644 --- a/ql/src/test/results/clientpositive/correlationoptimizer9.q.out +++ b/ql/src/test/results/clientpositive/correlationoptimizer9.q.out @@ -49,21 +49,21 @@ STAGE PLANS: TableScan alias: x filterExpr: ((c1 < 120) and (c1 > 100)) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and (c1 > 100)) (type: boolean) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -72,7 +72,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 57 Data size: 1273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -88,14 +88,14 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57 Data size: 1273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57 Data size: 1273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -105,14 +105,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 62 Data size: 1400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 62 Data size: 1400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 62 Data size: 1400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -124,21 +124,21 @@ STAGE PLANS: TableScan alias: x1 filterExpr: ((c2 > 100) and (c2 < 120)) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c2 < 120) and (c2 > 100)) (type: boolean) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c2 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -147,7 +147,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 57 Data size: 1273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -215,52 +215,52 @@ STAGE PLANS: TableScan alias: x filterExpr: ((c1 < 120) and (c1 > 100)) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and (c1 > 100)) (type: boolean) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: x1 filterExpr: ((c2 > 100) and (c2 < 120)) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 4112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c2 < 120) and (c2 > 100)) (type: boolean) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c2 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 68 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 68 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -268,14 +268,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 5601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 5601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 5601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -285,9 +285,9 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 34 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 68 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -295,14 +295,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 5601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 5601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 5601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74 Data size: 897 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -370,21 +370,21 @@ STAGE PLANS: TableScan alias: x filterExpr: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 97660 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 342 Data size: 32490 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -393,7 +393,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -409,14 +409,14 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 171 Data size: 3819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 57 Data size: 1273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -426,14 +426,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 188 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 11742 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 188 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 11742 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 188 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 11742 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -445,25 +445,25 @@ STAGE PLANS: TableScan alias: x1 filterExpr: ((c2 > 100) and (c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 101772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and (c2 > 100) and c3 is not null) (type: boolean) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c3 (type: string) outputColumnNames: c1, c3 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -472,7 +472,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57 Data size: 1273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -540,56 +540,56 @@ STAGE PLANS: TableScan alias: x filterExpr: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 97660 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 342 Data size: 32490 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 171 Data size: 17613 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan alias: x1 filterExpr: ((c2 > 100) and (c1 < 120) and c3 is not null) (type: boolean) - Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 101772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c1 < 120) and (c2 > 100) and c3 is not null) (type: boolean) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c3 (type: string) outputColumnNames: c1, c3 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114 Data size: 11286 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57 Data size: 5871 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Demux Operator - Statistics: Num rows: 456 Data size: 10185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 456 Data size: 10184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 456 Data size: 46968 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -597,14 +597,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -614,9 +614,9 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 228 Data size: 23484 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 456 Data size: 10184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 456 Data size: 46968 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Inner Join 0 to 1 @@ -624,14 +624,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col2 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 11202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 51664 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/count_dist_rewrite.q.out b/ql/src/test/results/clientpositive/count_dist_rewrite.q.out index 68f4c5df57..dfc2030ac5 100644 --- a/ql/src/test/results/clientpositive/count_dist_rewrite.q.out +++ b/ql/src/test/results/clientpositive/count_dist_rewrite.q.out @@ -13,33 +13,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -53,7 +53,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -61,10 +61,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -100,22 +100,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -124,12 +124,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), count(_col0) mode: partial2 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -143,7 +143,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -151,10 +151,10 @@ STAGE PLANS: aggregations: max(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -190,22 +190,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(key), min(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 113750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 113750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -214,12 +214,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 113750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), count(_col0), min(_col2) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -233,7 +233,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -241,10 +241,10 @@ STAGE PLANS: aggregations: max(VALUE._col0), count(VALUE._col1), min(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -280,22 +280,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(key), min(key), sum(key), count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 117750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 117750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: double), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -303,12 +303,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 117750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), count(_col0), min(_col2), sum(_col3), count(_col4) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -322,7 +322,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: double), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -330,14 +330,14 @@ STAGE PLANS: aggregations: max(VALUE._col0), count(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), (_col3 / _col4) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -373,22 +373,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -397,12 +397,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), count(_col0) mode: partial2 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -416,7 +416,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -424,10 +424,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -475,22 +475,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(key), max(value), max(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 117750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 117750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint), _col4 (type: string), _col5 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -499,12 +499,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 117750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), count(_col2), count(_col0), max(_col3), max(_col4) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -518,7 +518,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -526,10 +526,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), max(VALUE._col3), max(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -577,22 +577,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double), (UDFToDouble(key) * UDFToDouble(key)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col2), sum(_col1), count(_col0) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 29750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 29750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -601,12 +601,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 29750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), count(_col0), sum(_col2), sum(_col3), count(_col4) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -620,7 +620,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -628,14 +628,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), UDFToInteger(power(((_col2 - ((_col3 * _col3) / _col4)) / _col4), 0.5)) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -698,22 +698,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), max(_col0), min(_col0), sum(_col2), sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 146000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 146000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: bigint), _col4 (type: string), _col5 (type: string), _col6 (type: double), _col7 (type: double) Reduce Operator Tree: Group By Operator @@ -721,12 +721,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 146000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col2), count(_col0), max(_col3), min(_col4), sum(_col5), sum(_col6) mode: partial2 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -740,7 +740,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: string), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -748,14 +748,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2), max(VALUE._col3), min(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), (_col0 / _col1) (type: double), _col2 (type: bigint), _col3 (type: string), _col4 (type: string), UDFToInteger(power(((_col5 - ((_col6 * _col6) / _col1)) / _col1), 0.5)) (type: int), UDFToInteger(power(((_col5 - ((_col6 * _col6) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5)) (type: int), UDFToInteger(((_col5 - ((_col6 * _col6) / _col1)) / _col1)) (type: int), UDFToInteger(((_col5 - ((_col6 * _col6) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END)) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -808,22 +808,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(key), count(DISTINCT key), min(key), sum(key), count(key) keys: value (type: string), key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col4 (type: string), _col5 (type: double), _col6 (type: bigint) Reduce Operator Tree: Group By Operator @@ -831,14 +831,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 120750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: bigint), _col3 (type: string), (_col4 / _col5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cp_sel.q.out b/ql/src/test/results/clientpositive/cp_sel.q.out index 8222156705..752a2925d8 100644 --- a/ql/src/test/results/clientpositive/cp_sel.q.out +++ b/ql/src/test/results/clientpositive/cp_sel.q.out @@ -15,15 +15,15 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -31,17 +31,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), 'hello' (type: string), 'world' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -93,26 +93,26 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), 'hello' (type: string), 'world' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -121,13 +121,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1058 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -164,7 +164,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1058 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -173,14 +173,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1058 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1058 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1058 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/create_genericudaf.q.out b/ql/src/test/results/clientpositive/create_genericudaf.q.out index dd2ce7fbf3..50752fbaa0 100644 --- a/ql/src/test/results/clientpositive/create_genericudaf.q.out +++ b/ql/src/test/results/clientpositive/create_genericudaf.q.out @@ -38,29 +38,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string) outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: test_avg(1), test_avg(_col1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: test_avg(VALUE._col0), test_avg(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/create_view.q.out b/ql/src/test/results/clientpositive/create_view.q.out index d2c516fdfe..5c201003fb 100644 --- a/ql/src/test/results/clientpositive/create_view.q.out +++ b/ql/src/test/results/clientpositive/create_view.q.out @@ -192,17 +192,17 @@ STAGE PLANS: filterExpr: (UDFToDouble(key) = 18.0D) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 18.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cross_join.q.out b/ql/src/test/results/clientpositive/cross_join.q.out index b9daa35b42..775d245c0b 100644 --- a/ql/src/test/results/clientpositive/cross_join.q.out +++ b/ql/src/test/results/clientpositive/cross_join.q.out @@ -13,14 +13,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: src2 @@ -38,10 +38,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -68,14 +68,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: src2 @@ -93,10 +93,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -123,35 +123,35 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -160,10 +160,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -196,11 +196,11 @@ STAGE PLANS: $hdt$_0:src TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -221,10 +221,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -260,11 +260,11 @@ STAGE PLANS: $hdt$_0:src TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -285,10 +285,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -324,14 +324,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -343,14 +343,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -358,10 +358,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cross_join_merge.q.out b/ql/src/test/results/clientpositive/cross_join_merge.q.out index 016acc6c61..6ba4734986 100644 --- a/ql/src/test/results/clientpositive/cross_join_merge.q.out +++ b/ql/src/test/results/clientpositive/cross_join_merge.q.out @@ -15,14 +15,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: src3 @@ -50,10 +50,10 @@ STAGE PLANS: 1 2 outputColumnNames: _col0 - Statistics: Num rows: 125000000 Data size: 2453000000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125000000 Data size: 10875000000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125000000 Data size: 2453000000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125000000 Data size: 10875000000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -82,51 +82,51 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -137,10 +137,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 108837 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 108837 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -169,51 +169,51 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -224,10 +224,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 108837 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 108837 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -258,35 +258,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -295,7 +295,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -309,20 +309,20 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: src2 filterExpr: (UDFToDouble(key) = 5.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 5.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -331,10 +331,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 197750 Data size: 17204250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 197750 Data size: 17204250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -365,14 +365,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: src2 @@ -390,7 +390,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -404,7 +404,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250000 Data size: 3906000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: src3 @@ -422,10 +422,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 125000000 Data size: 2578000000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125000000 Data size: 10875000000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125000000 Data size: 2578000000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125000000 Data size: 10875000000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -454,51 +454,51 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -509,10 +509,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 108837 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 108837 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cross_product_check_1.q.out b/ql/src/test/results/clientpositive/cross_product_check_1.q.out index 2d1eb7e2c2..0bdfa8d3e0 100644 --- a/ql/src/test/results/clientpositive/cross_product_check_1.q.out +++ b/ql/src/test/results/clientpositive/cross_product_check_1.q.out @@ -43,25 +43,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n8 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: b_n6 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -71,10 +71,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5000 Data size: 110120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5000 Data size: 110120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -103,36 +103,36 @@ STAGE PLANS: TableScan alias: d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -142,7 +142,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -156,18 +156,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: a_n8 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -177,10 +177,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 5500 Data size: 120932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5500 Data size: 120932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -216,35 +216,35 @@ STAGE PLANS: TableScan alias: d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -253,12 +253,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -274,14 +274,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -294,19 +294,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n8 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -316,10 +316,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2500 Data size: 54560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2500 Data size: 54560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -349,14 +349,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: d1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan alias: d2 @@ -374,12 +374,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -395,14 +395,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 50 Data size: 770 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -415,19 +415,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n8 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 50 Data size: 770 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -437,10 +437,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25000 Data size: 675600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25000 Data size: 675600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -474,28 +474,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n8 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -509,12 +509,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -524,10 +524,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1250 Data size: 27280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 27280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -539,35 +539,35 @@ STAGE PLANS: TableScan alias: d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -576,12 +576,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -597,14 +597,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/cross_product_check_2.q.out b/ql/src/test/results/clientpositive/cross_product_check_2.q.out index 61c40741fe..193b7d9bf5 100644 --- a/ql/src/test/results/clientpositive/cross_product_check_2.q.out +++ b/ql/src/test/results/clientpositive/cross_product_check_2.q.out @@ -49,11 +49,11 @@ STAGE PLANS: $hdt$_1:b_n2 TableScan alias: b_n2 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -64,11 +64,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -76,10 +76,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5000 Data size: 106120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5000 Data size: 106120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -119,14 +119,14 @@ STAGE PLANS: TableScan alias: d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -134,11 +134,11 @@ STAGE PLANS: $hdt$_2:a_n2 TableScan alias: a_n2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -150,14 +150,14 @@ STAGE PLANS: TableScan alias: d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -165,7 +165,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -173,10 +173,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 5500 Data size: 116432 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5500 Data size: 116432 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -221,14 +221,14 @@ STAGE PLANS: TableScan alias: d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -240,14 +240,14 @@ STAGE PLANS: TableScan alias: d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -255,17 +255,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -274,7 +274,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -292,11 +292,11 @@ STAGE PLANS: $hdt$_0:a_n2 TableScan alias: a_n2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -313,10 +313,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2500 Data size: 52560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2500 Data size: 52560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -355,11 +355,11 @@ STAGE PLANS: $hdt$_1:$hdt$_1:d1 TableScan alias: d1 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -380,17 +380,17 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 100 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -399,7 +399,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 50 Data size: 730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -417,11 +417,11 @@ STAGE PLANS: $hdt$_0:a_n2 TableScan alias: a_n2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -438,10 +438,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25000 Data size: 655600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 25000 Data size: 655600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -485,28 +485,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -542,10 +542,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -579,10 +579,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -597,12 +597,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -612,10 +612,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 26280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -632,14 +632,14 @@ STAGE PLANS: TableScan alias: d1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -651,14 +651,14 @@ STAGE PLANS: TableScan alias: d2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -666,17 +666,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 105 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -685,7 +685,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/ctas.q.out b/ql/src/test/results/clientpositive/ctas.q.out index 5f1a379d21..c398f238f4 100644 --- a/ql/src/test/results/clientpositive/ctas.q.out +++ b/ql/src/test/results/clientpositive/ctas.q.out @@ -31,25 +31,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -64,20 +64,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -185,25 +185,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -218,20 +218,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -339,25 +339,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key / 2) (type: double), concat(value, '_con') (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -372,20 +372,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -557,25 +557,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -590,20 +590,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -713,25 +713,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -746,20 +746,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/ctas_colname.q.out b/ql/src/test/results/clientpositive/ctas_colname.q.out index ff1fd8d204..cbc2d91063 100644 --- a/ql/src/test/results/clientpositive/ctas_colname.q.out +++ b/ql/src/test/results/clientpositive/ctas_colname.q.out @@ -16,17 +16,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0D) (type: double), concat(value, value) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7400 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double), _col3 (type: string) Execution mode: vectorized @@ -34,13 +34,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: double), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7400 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -163,18 +163,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 11075 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -195,14 +195,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 11075 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4475 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4475 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -329,18 +329,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -361,14 +361,14 @@ STAGE PLANS: window function: GenericUDAFLeadEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), lead_window_0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -382,7 +382,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Execution mode: vectorized @@ -390,13 +390,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -522,14 +522,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -695,22 +695,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -719,10 +719,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1133,21 +1133,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 9.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 9.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1156,10 +1156,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1266,21 +1266,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 9.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 9.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -1289,17 +1289,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out b/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out index 68bc0153c6..adaccee2a2 100644 --- a/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out +++ b/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out @@ -35,14 +35,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_1.q.out b/ql/src/test/results/clientpositive/cte_1.q.out index 0edfeb7596..c002f960af 100644 --- a/ql/src/test/results/clientpositive/cte_1.q.out +++ b/ql/src/test/results/clientpositive/cte_1.q.out @@ -19,17 +19,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -76,17 +76,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -133,17 +133,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_3.q.out b/ql/src/test/results/clientpositive/cte_3.q.out index d3884f1278..40c3f08d52 100644 --- a/ql/src/test/results/clientpositive/cte_3.q.out +++ b/ql/src/test/results/clientpositive/cte_3.q.out @@ -25,17 +25,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -94,11 +94,11 @@ STAGE PLANS: Processor Tree: TableScan alias: q1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: with q1 as ( select key from src where key = '5') @@ -147,17 +147,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -216,11 +216,11 @@ STAGE PLANS: Processor Tree: TableScan alias: q1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: with q1 as ( select key from src where key = '5') @@ -276,17 +276,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -315,17 +315,17 @@ STAGE PLANS: TableScan alias: q2 filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -414,11 +414,11 @@ STAGE PLANS: Processor Tree: TableScan alias: q1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: with q1 as ( select key from q2 where key = '5'), diff --git a/ql/src/test/results/clientpositive/cte_5.q.out b/ql/src/test/results/clientpositive/cte_5.q.out index 6789cd38c9..912a024575 100644 --- a/ql/src/test/results/clientpositive/cte_5.q.out +++ b/ql/src/test/results/clientpositive/cte_5.q.out @@ -65,27 +65,27 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(colnum) = 5.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(colnum) = 5.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -93,14 +93,14 @@ STAGE PLANS: keys: 0 1 - Statistics: Num rows: 250 Data size: 3656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 5 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 3656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 3656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_6.q.out b/ql/src/test/results/clientpositive/cte_6.q.out index 2bf6589b1b..6837a33879 100644 --- a/ql/src/test/results/clientpositive/cte_6.q.out +++ b/ql/src/test/results/clientpositive/cte_6.q.out @@ -17,17 +17,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -61,17 +61,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_mat_1.q.out b/ql/src/test/results/clientpositive/cte_mat_1.q.out index 7e84cba8e5..a663e17969 100644 --- a/ql/src/test/results/clientpositive/cte_mat_1.q.out +++ b/ql/src/test/results/clientpositive/cte_mat_1.q.out @@ -22,27 +22,27 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -50,14 +50,14 @@ STAGE PLANS: keys: 0 1 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_mat_2.q.out b/ql/src/test/results/clientpositive/cte_mat_2.q.out index 7e84cba8e5..a663e17969 100644 --- a/ql/src/test/results/clientpositive/cte_mat_2.q.out +++ b/ql/src/test/results/clientpositive/cte_mat_2.q.out @@ -22,27 +22,27 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -50,14 +50,14 @@ STAGE PLANS: keys: 0 1 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_mat_3.q.out b/ql/src/test/results/clientpositive/cte_mat_3.q.out index 3d597c0397..cf999b43eb 100644 --- a/ql/src/test/results/clientpositive/cte_mat_3.q.out +++ b/ql/src/test/results/clientpositive/cte_mat_3.q.out @@ -28,17 +28,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -67,35 +67,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -104,10 +104,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_mat_4.q.out b/ql/src/test/results/clientpositive/cte_mat_4.q.out index 943ca59843..9f9e05ef33 100644 --- a/ql/src/test/results/clientpositive/cte_mat_4.q.out +++ b/ql/src/test/results/clientpositive/cte_mat_4.q.out @@ -53,17 +53,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -92,35 +92,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -129,10 +129,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -263,17 +263,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -302,35 +302,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -339,10 +339,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/cte_mat_5.q.out b/ql/src/test/results/clientpositive/cte_mat_5.q.out index 1a6f0863e1..fec027723e 100644 --- a/ql/src/test/results/clientpositive/cte_mat_5.q.out +++ b/ql/src/test/results/clientpositive/cte_mat_5.q.out @@ -71,17 +71,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -110,36 +110,36 @@ STAGE PLANS: TableScan alias: a filterExpr: colnum is not null (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: colnum is not null (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: colnum (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -148,10 +148,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/decimal_join2.q.out b/ql/src/test/results/clientpositive/decimal_join2.q.out index 43610eae5e..5824e831f4 100644 --- a/ql/src/test/results/clientpositive/decimal_join2.q.out +++ b/ql/src/test/results/clientpositive/decimal_join2.q.out @@ -58,36 +58,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(38,18)), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(38,18)) sort order: + Map-reduce partition columns: _col0 (type: decimal(38,18)) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(38,18)), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(38,18)) sort order: + Map-reduce partition columns: _col0 (type: decimal(38,18)) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -97,7 +97,7 @@ STAGE PLANS: 0 _col0 (type: decimal(38,18)) 1 _col0 (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -112,16 +112,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: decimal(38,18)), _col1 (type: int), _col2 (type: decimal(38,18)), _col3 (type: int) sort order: ++++ - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(38,18)), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: decimal(38,18)), KEY.reducesinkkey3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -229,14 +229,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(38,18)), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: decimal(38,18)) @@ -248,14 +248,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38 Data size: 4408 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(38,18)), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37 Data size: 4292 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -263,11 +263,11 @@ STAGE PLANS: 0 _col0 (type: decimal(38,18)) 1 _col0 (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(38,18)), _col1 (type: int), _col2 (type: decimal(38,18)), _col3 (type: int) sort order: ++++ - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -275,10 +275,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(38,18)), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: decimal(38,18)), KEY.reducesinkkey3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 4725 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 4721 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/decimal_precision.q.out b/ql/src/test/results/clientpositive/decimal_precision.q.out index 921d86bff9..ce3b2cebfe 100644 --- a/ql/src/test/results/clientpositive/decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/decimal_precision.q.out @@ -536,19 +536,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_precision_n0 - Statistics: Num rows: 1 Data size: 26610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(20,10)) outputColumnNames: dec - Statistics: Num rows: 1 Data size: 26610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(dec), count(dec) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(30,10)), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -556,14 +556,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (_col0 / _col1) (type: decimal(38,18)), CAST( _col0 AS decimal(30,10)) (type: decimal(30,10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/decimal_udf.q.out b/ql/src/test/results/clientpositive/decimal_udf.q.out index 78f4b7d384..b9e1cb78f0 100644 --- a/ql/src/test/results/clientpositive/decimal_udf.q.out +++ b/ql/src/test/results/clientpositive/decimal_udf.q.out @@ -38,11 +38,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key + key) (type: decimal(21,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key + key FROM DECIMAL_UDF @@ -105,11 +105,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key + CAST( value AS decimal(10,0))) (type: decimal(21,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key + value FROM DECIMAL_UDF @@ -172,11 +172,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + (UDFToDouble(value) / 2.0D)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key + (value/2) FROM DECIMAL_UDF @@ -239,11 +239,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key + '1.0' FROM DECIMAL_UDF @@ -306,11 +306,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key - key) (type: decimal(21,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key - key FROM DECIMAL_UDF @@ -373,11 +373,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key - CAST( value AS decimal(10,0))) (type: decimal(21,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key - value FROM DECIMAL_UDF @@ -440,11 +440,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) - (UDFToDouble(value) / 2.0D)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key - (value/2) FROM DECIMAL_UDF @@ -507,11 +507,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) - 1.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key - '1.0' FROM DECIMAL_UDF @@ -574,11 +574,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key * key) (type: decimal(38,17)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key * key FROM DECIMAL_UDF @@ -642,14 +642,14 @@ STAGE PLANS: TableScan alias: decimal_udf filterExpr: ((key * CAST( value AS decimal(10,0))) > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key * CAST( value AS decimal(10,0))) > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key, value FROM DECIMAL_UDF where key * value > 0 @@ -697,11 +697,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key * CAST( value AS decimal(10,0))) (type: decimal(31,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key * value FROM DECIMAL_UDF @@ -764,11 +764,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) * (UDFToDouble(value) / 2.0D)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key * (value/2) FROM DECIMAL_UDF @@ -831,11 +831,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) * 2.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key * '2.0' FROM DECIMAL_UDF @@ -898,14 +898,14 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / 0) (type: decimal(22,12)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key / 0 FROM DECIMAL_UDF limit 1 @@ -931,14 +931,14 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) / null) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key / NULL FROM DECIMAL_UDF limit 1 @@ -965,14 +965,14 @@ STAGE PLANS: TableScan alias: decimal_udf filterExpr: (key <> 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key <> 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / key) (type: decimal(38,18)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key / key FROM DECIMAL_UDF WHERE key is not null and key <> 0 @@ -1032,14 +1032,14 @@ STAGE PLANS: TableScan alias: decimal_udf filterExpr: (value <> 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value <> 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (key / CAST( value AS decimal(10,0))) (type: decimal(31,21)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key / value FROM DECIMAL_UDF WHERE value is not null and value <> 0 @@ -1089,14 +1089,14 @@ STAGE PLANS: TableScan alias: decimal_udf filterExpr: (value <> 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value <> 0) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(key) / (UDFToDouble(value) / 2.0D)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT key / (value/2) FROM DECIMAL_UDF WHERE value is not null and value <> 0 @@ -1145,11 +1145,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (1.0D + (UDFToDouble(key) / 2.0D)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT 1 + (key / '2.0') FROM DECIMAL_UDF @@ -1212,11 +1212,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: abs(key) (type: decimal(20,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT abs(key) FROM DECIMAL_UDF @@ -1280,22 +1280,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(key), count(key) keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(30,10)), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1304,11 +1304,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), (_col1 / CAST( _col2 AS decimal(19,0))) (type: decimal(38,18)), (CAST( _col1 AS decimal(24,14)) / _col2) (type: decimal(38,28)), _col1 (type: decimal(30,10)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1323,17 +1323,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(38,18)), _col2 (type: decimal(38,28)), _col3 (type: decimal(30,10)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: decimal(38,18)), VALUE._col1 (type: decimal(38,28)), VALUE._col2 (type: decimal(30,10)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1384,11 +1384,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (- key) (type: decimal(20,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT -key FROM DECIMAL_UDF @@ -1451,11 +1451,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT +key FROM DECIMAL_UDF @@ -1518,11 +1518,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ceil(key) (type: decimal(11,0)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT CEIL(key) FROM DECIMAL_UDF @@ -1585,11 +1585,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: floor(key) (type: decimal(11,0)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT FLOOR(key) FROM DECIMAL_UDF @@ -1652,11 +1652,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: round(key, 2) (type: decimal(13,2)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT ROUND(key, 2) FROM DECIMAL_UDF @@ -1719,11 +1719,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: power(key, 2) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT POWER(key, 2) FROM DECIMAL_UDF @@ -1786,11 +1786,11 @@ STAGE PLANS: Processor Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ((key + 1) % (key / 2)) (type: decimal(22,12)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT (key + 1) % (key / 2) FROM DECIMAL_UDF @@ -1853,22 +1853,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)), UDFToDouble(key) (type: double), (UDFToDouble(key) * UDFToDouble(key)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col3), sum(_col2), count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1877,14 +1877,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1935,22 +1935,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)), UDFToDouble(key) (type: double), (UDFToDouble(key) * UDFToDouble(key)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col3), sum(_col2), count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1959,14 +1959,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), power(((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2017,29 +2017,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: histogram_numeric(_col0, 3) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array) Reduce Operator Tree: Group By Operator aggregations: histogram_numeric(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 832 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 832 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2074,19 +2074,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) outputColumnNames: key - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(20,10)) Execution mode: vectorized Reduce Operator Tree: @@ -2094,10 +2094,10 @@ STAGE PLANS: aggregations: min(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2132,19 +2132,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) outputColumnNames: key - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(20,10)) Execution mode: vectorized Reduce Operator Tree: @@ -2152,10 +2152,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2190,19 +2190,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_udf - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) outputColumnNames: key - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -2210,10 +2210,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/decimal_udf2.q.out b/ql/src/test/results/clientpositive/decimal_udf2.q.out index b804530deb..49ea5a3784 100644 --- a/ql/src/test/results/clientpositive/decimal_udf2.q.out +++ b/ql/src/test/results/clientpositive/decimal_udf2.q.out @@ -43,17 +43,17 @@ STAGE PLANS: TableScan alias: decimal_udf2 filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: double), null (type: double), 1.4711276743037347D (type: double), -0.8390715290764524D (type: double), -0.5440211108893698D (type: double), 0.6483608274590866D (type: double), 0.17453292519943295D (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -102,17 +102,17 @@ STAGE PLANS: TableScan alias: decimal_udf2 filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 22026.465794806718D (type: double), 2.302585092994046D (type: double), 2.302585092994046D (type: double), 1.0D (type: double), log(10, value) (type: double), log(value, 10) (type: double), 1.0D (type: double), 3.1622776601683795D (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out index 4d5144c835..5152002e57 100644 --- a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out +++ b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out @@ -79,29 +79,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_web_text_none_n0 - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -131,22 +131,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_web_text_none_n0 - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Statistics Aggregation Key Prefix: default.uservisits_web_text_none_n0/ GatherStats: true Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -209,13 +209,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -365,29 +365,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: empty_tab_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary) outputColumnNames: a, b, c, d, e - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll'), compute_stats(e, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 1848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 1880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/distinct_stats.q.out b/ql/src/test/results/clientpositive/distinct_stats.q.out index aa89d10994..9d93042793 100644 --- a/ql/src/test/results/clientpositive/distinct_stats.q.out +++ b/ql/src/test/results/clientpositive/distinct_stats.q.out @@ -42,36 +42,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n11 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT b) keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -99,31 +99,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n11 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: b (type: string) outputColumnNames: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: b (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -151,22 +151,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n11 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: string) outputColumnNames: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: a (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -175,10 +175,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/distinct_windowing.q.out b/ql/src/test/results/clientpositive/distinct_windowing.q.out index 39b87e8b87..1bc69f41b4 100644 --- a/ql/src/test/results/clientpositive/distinct_windowing.q.out +++ b/ql/src/test/results/clientpositive/distinct_windowing.q.out @@ -61,19 +61,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n15 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: si (type: smallint), i (type: int) sort order: ++ Map-reduce partition columns: si (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: t (type: tinyint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -93,16 +93,16 @@ STAGE PLANS: name: first_value window function: GenericUDAFFirstValueEvaluator window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: first_value_window_0 (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -118,7 +118,7 @@ STAGE PLANS: key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -126,13 +126,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -181,18 +181,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n15 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: si (type: smallint), i (type: int) sort order: ++ Map-reduce partition columns: si (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -212,16 +212,16 @@ STAGE PLANS: name: last_value window function: GenericUDAFLastValueEvaluator window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: last_value_window_0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -237,7 +237,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -245,13 +245,13 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,19 +304,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n15 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: si (type: smallint), i (type: int) sort order: ++ Map-reduce partition columns: si (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: t (type: tinyint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -342,16 +342,16 @@ STAGE PLANS: name: first_value window function: GenericUDAFFirstValueEvaluator window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: last_value_window_0 (type: int), first_value_window_1 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -367,7 +367,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: tinyint) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: tinyint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -375,13 +375,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/distinct_windowing_no_cbo.q.out b/ql/src/test/results/clientpositive/distinct_windowing_no_cbo.q.out index c1fe3a2ece..895c92f43d 100644 --- a/ql/src/test/results/clientpositive/distinct_windowing_no_cbo.q.out +++ b/ql/src/test/results/clientpositive/distinct_windowing_no_cbo.q.out @@ -61,19 +61,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n14 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: si (type: smallint), i (type: int) sort order: ++ Map-reduce partition columns: si (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: t (type: tinyint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -93,16 +93,16 @@ STAGE PLANS: name: first_value window function: GenericUDAFFirstValueEvaluator window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: first_value_window_0 (type: tinyint) outputColumnNames: first_value_window_0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: first_value_window_0 (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -118,7 +118,7 @@ STAGE PLANS: key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -126,13 +126,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -181,18 +181,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n14 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: si (type: smallint), i (type: int) sort order: ++ Map-reduce partition columns: si (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -212,16 +212,16 @@ STAGE PLANS: name: last_value window function: GenericUDAFLastValueEvaluator window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: last_value_window_0 (type: int) outputColumnNames: last_value_window_0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: last_value_window_0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -237,7 +237,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -245,13 +245,13 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,19 +304,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n14 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: si (type: smallint), i (type: int) sort order: ++ Map-reduce partition columns: si (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: t (type: tinyint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -342,16 +342,16 @@ STAGE PLANS: name: first_value window function: GenericUDAFFirstValueEvaluator window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: last_value_window_0 (type: int), first_value_window_1 (type: tinyint) outputColumnNames: last_value_window_0, first_value_window_1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: last_value_window_0 (type: int), first_value_window_1 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -367,7 +367,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: tinyint) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: tinyint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -375,13 +375,13 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -480,22 +480,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n14 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: si (type: smallint), f (type: float) outputColumnNames: si, f - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(f) keys: si (type: smallint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: float) Execution mode: vectorized Reduce Operator Tree: @@ -504,10 +504,10 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col1 > 0.0) (type: boolean) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -523,13 +523,13 @@ STAGE PLANS: key expressions: _col0 (type: smallint), _col1 (type: float) sort order: ++ Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -550,17 +550,17 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: smallint), _col1 (type: float), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -659,18 +659,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over10k_n14 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: si (type: smallint), i (type: int) sort order: ++ Map-reduce partition columns: si (type: smallint) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey1 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -691,16 +691,16 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rank_window_0 (type: int), _col1 (type: smallint) outputColumnNames: rank_window_0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col1 (type: smallint), rank_window_0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -716,7 +716,7 @@ STAGE PLANS: key expressions: _col0 (type: smallint), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int) - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -724,13 +724,13 @@ STAGE PLANS: keys: KEY._col0 (type: smallint), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10175440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out b/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out index 88b24a7501..266cccabc3 100644 --- a/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out +++ b/ql/src/test/results/clientpositive/dynamic_partition_skip_default.q.out @@ -108,12 +108,12 @@ STAGE PLANS: TableScan alias: dynamic_part_table filterExpr: ((partcol1 = '1') and (partcol2 = '1')) (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: intcol (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select intcol from dynamic_part_table where partcol1='1' and partcol2='1' @@ -182,12 +182,12 @@ STAGE PLANS: TableScan alias: dynamic_part_table filterExpr: ((partcol1 = '1') and (partcol2 = '1')) (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: intcol (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select intcol from dynamic_part_table where (partcol1='1' and partcol2='1')or (partcol1='1' and partcol2='__HIVE_DEFAULT_PARTITION__') @@ -300,11 +300,11 @@ STAGE PLANS: TableScan alias: dynamic_part_table filterExpr: ((partcol2) IN ('1', '__HIVE_DEFAULT_PARTITION__') and (partcol1 = '1')) (type: boolean) - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: intcol (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: PARTIAL ListSink diff --git a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out index aea757205f..62ab211636 100644 --- a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out +++ b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid2.q.out @@ -29,27 +29,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col2 (type: string), _col3 (type: string), '_bucket_number' (type: string), _col1 (type: string) sort order: ++++ Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, '_bucket_number' - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1288000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1288000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/empty_join.q.out b/ql/src/test/results/clientpositive/empty_join.q.out index 2c0c7d5274..e8a0f1a19b 100644 --- a/ql/src/test/results/clientpositive/empty_join.q.out +++ b/ql/src/test/results/clientpositive/empty_join.q.out @@ -72,14 +72,14 @@ STAGE PLANS: TableScan alias: t2 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -89,14 +89,14 @@ STAGE PLANS: TableScan alias: t3 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -109,14 +109,14 @@ STAGE PLANS: TableScan alias: t1 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -126,10 +126,10 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out b/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out index f8f0a76709..07846f4a1d 100644 --- a/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out +++ b/ql/src/test/results/clientpositive/encrypted/encryption_join_unencrypted_tbl.q.out @@ -554,44 +554,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) null sort order: a sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) null sort order: a sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: int), _col1 (type: string) auto parallelism: false @@ -711,13 +711,13 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 215943 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 directory: hdfs://### HDFS PATH ### NumFilesPerFileSink: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 215943 Basic stats: COMPLETE Column stats: COMPLETE Stats Publishing Key Prefix: hdfs://### HDFS PATH ### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/escape_clusterby1.q.out b/ql/src/test/results/clientpositive/escape_clusterby1.q.out index da37ef5ec6..65468b3498 100644 --- a/ql/src/test/results/clientpositive/escape_clusterby1.q.out +++ b/ql/src/test/results/clientpositive/escape_clusterby1.q.out @@ -14,25 +14,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -60,25 +60,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/escape_distributeby1.q.out b/ql/src/test/results/clientpositive/escape_distributeby1.q.out index ed202012e0..2c84ade47d 100644 --- a/ql/src/test/results/clientpositive/escape_distributeby1.q.out +++ b/ql/src/test/results/clientpositive/escape_distributeby1.q.out @@ -14,25 +14,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -60,25 +60,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/escape_orderby1.q.out b/ql/src/test/results/clientpositive/escape_orderby1.q.out index 70ed8f4831..5895a6560f 100644 --- a/ql/src/test/results/clientpositive/escape_orderby1.q.out +++ b/ql/src/test/results/clientpositive/escape_orderby1.q.out @@ -14,24 +14,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -59,24 +59,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/escape_sortby1.q.out b/ql/src/test/results/clientpositive/escape_sortby1.q.out index 7d28cf2f2f..4375a898b6 100644 --- a/ql/src/test/results/clientpositive/escape_sortby1.q.out +++ b/ql/src/test/results/clientpositive/escape_sortby1.q.out @@ -14,24 +14,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -59,24 +59,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/except_all.q.out b/ql/src/test/results/clientpositive/except_all.q.out index 5263e3c716..c4cc74a908 100644 --- a/ql/src/test/results/clientpositive/except_all.q.out +++ b/ql/src/test/results/clientpositive/except_all.q.out @@ -226,22 +226,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -250,11 +250,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 2L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -267,41 +267,41 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -309,21 +309,21 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((2 * _col2) - (3 * _col3)) (type: bigint), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE function name: UDTFReplicateRows Select Operator expressions: col1 (type: string), col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -334,22 +334,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -358,11 +358,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 1L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -405,22 +405,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -429,11 +429,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 2L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -446,41 +446,41 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -488,24 +488,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((2 * _col2) - (3 * _col3)) (type: bigint), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE function name: UDTFReplicateRows Select Operator expressions: col1 (type: string), col2 (type: string) outputColumnNames: col1, col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: col1 (type: string), col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -521,7 +521,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -530,11 +530,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 2L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -547,41 +547,41 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 251 Data size: 48516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 251 Data size: 48516 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 24250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 24250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) TableScan Union - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 251 Data size: 48516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 251 Data size: 48516 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 24250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 24250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -589,24 +589,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 187 Data size: 1986 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 24250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col2 * 2) = _col3) and (_col2 > 0L)) (type: boolean) - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3880 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 2L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 15 Data size: 159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -619,41 +619,41 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 52380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 52380 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 26190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 26190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) TableScan Union - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 52380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 52380 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 26190 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 26190 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -661,17 +661,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 132 Data size: 1402 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 26190 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col2 * 2) = _col3) and (_col2 > 0L)) (type: boolean) - Statistics: Num rows: 22 Data size: 233 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4268 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 233 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 22 Data size: 233 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -682,22 +682,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -706,11 +706,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 1L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -723,22 +723,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -747,11 +747,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 1L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -764,22 +764,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -788,11 +788,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 1L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -830,38 +830,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n15 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: value - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: value (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), 2L (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -874,41 +874,41 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: bigint), (_col1 * _col2) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: bigint), (_col1 * _col2) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -916,17 +916,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col1 * 2) = _col2) and (_col1 > 0L)) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -937,38 +937,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b_n11 - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), 1L (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out index b178affef5..704cde31be 100644 --- a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out +++ b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out @@ -24,29 +24,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n25 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/explain_ddl.q.out b/ql/src/test/results/clientpositive/explain_ddl.q.out index df31faa865..586d8631ca 100644 --- a/ql/src/test/results/clientpositive/explain_ddl.q.out +++ b/ql/src/test/results/clientpositive/explain_ddl.q.out @@ -63,14 +63,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -157,14 +157,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: m1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -253,14 +253,14 @@ STAGE PLANS: alias: src properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -347,14 +347,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: m1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -512,14 +512,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: m1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -528,25 +528,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/explain_logical.q.out b/ql/src/test/results/clientpositive/explain_logical.q.out index c7eb6e90e0..4155cff21b 100644 --- a/ql/src/test/results/clientpositive/explain_logical.q.out +++ b/ql/src/test/results/clientpositive/explain_logical.q.out @@ -77,32 +77,32 @@ srcpart TableScan (TS_0) alias: srcpart filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_2) expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator (GBY_3) aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator (RS_4) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) Group By Operator (GBY_5) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator (FS_7) compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -118,32 +118,32 @@ LOGICAL PLAN: src TableScan (TS_0) alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_1) expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator (GBY_2) aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_3) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Group By Operator (GBY_4) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator (FS_6) compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -163,16 +163,16 @@ LOGICAL PLAN: $hdt$_0-subquery1:src TableScan (TS_0) alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_1) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union (UNION_5) - Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 445000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator (FS_7) compressed: false - Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 445000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -181,13 +181,13 @@ $hdt$_0-subquery2:srcpart TableScan (TS_2) alias: srcpart filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_4) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Union (UNION_5) - Statistics: Num rows: 2500 Data size: 26560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2500 Data size: 445000 Basic stats: COMPLETE Column stats: PARTIAL PREHOOK: query: EXPLAIN LOGICAL SELECT S1.key, S2.value FROM src S1 JOIN srcpart S2 ON S1.key = S2.key WHERE ds IS NOT NULL @@ -200,19 +200,19 @@ $hdt$_0:s1 TableScan (TS_0) alias: s1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator (FIL_11) predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_2) expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_6) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Join Operator (JOIN_8) condition map: Inner Join 0 to 1 @@ -220,14 +220,14 @@ $hdt$_0:s1 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_9) expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator (FS_10) compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -236,19 +236,19 @@ $hdt$_1:s2 TableScan (TS_3) alias: s2 filterExpr: (key is not null and ds is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator (FIL_12) predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_5) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator (RS_7) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) Join Operator (JOIN_8) condition map: @@ -257,7 +257,7 @@ $hdt$_1:s2 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V1_n8 PREHOOK: type: QUERY @@ -269,11 +269,11 @@ src alias: src properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_1) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink (LIST_SINK_3) PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V2_n3 @@ -287,11 +287,11 @@ srcpart filterExpr: ds is not null (type: boolean) properties: insideView TRUE - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_2) expressions: ds (type: string), key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL ListSink (LIST_SINK_5) PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V3_n1 @@ -305,19 +305,19 @@ $hdt$_0:srcpart filterExpr: (ds is not null and key is not null) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator (FIL_11) predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_2) expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator (RS_6) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Join Operator (JOIN_8) condition map: Inner Join 0 to 1 @@ -325,14 +325,14 @@ $hdt$_0:srcpart 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_9) expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator (FS_10) compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -343,19 +343,19 @@ $hdt$_1:src2 filterExpr: key is not null (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator (FIL_12) predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_5) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_7) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Join Operator (JOIN_8) condition map: @@ -364,7 +364,7 @@ $hdt$_1:src2 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL PREHOOK: query: EXPLAIN LOGICAL SELECT * FROM V4_n1 PREHOOK: type: QUERY @@ -377,19 +377,19 @@ $hdt$_0:srcpart filterExpr: (ds is not null and key is not null) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator (FIL_15) predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_2) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator (RS_9) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) Join Operator (JOIN_12) condition map: @@ -400,14 +400,14 @@ $hdt$_0:srcpart 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5007 Data size: 1346883 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_13) expressions: _col2 (type: string), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5007 Data size: 1346883 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator (FS_14) compressed: false - Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5007 Data size: 1346883 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -418,19 +418,19 @@ $hdt$_1:src filterExpr: key is not null (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator (FIL_16) predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_5) expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_10) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Join Operator (JOIN_12) condition map: Inner Join 0 to 1 @@ -440,26 +440,26 @@ $hdt$_1:src 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5007 Data size: 1346883 Basic stats: COMPLETE Column stats: PARTIAL $hdt$_2:src3 TableScan (TS_6) alias: src3 filterExpr: key is not null (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator (FIL_17) predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_8) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_11) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Join Operator (JOIN_12) condition map: @@ -470,7 +470,7 @@ $hdt$_2:src3 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5007 Data size: 1346883 Basic stats: COMPLETE Column stats: PARTIAL PREHOOK: query: CREATE VIEW V5_n0 as SELECT * FROM srcpart where ds = '10' PREHOOK: type: CREATEVIEW @@ -497,14 +497,14 @@ srcpart filterExpr: (ds = '10') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator (FIL_4) predicate: (ds = '10') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Select Operator (SEL_2) expressions: key (type: string), value (type: string), '10' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 638 Basic stats: COMPLETE Column stats: PARTIAL ListSink (LIST_SINK_5) PREHOOK: query: EXPLAIN LOGICAL SELECT s1.key, s1.cnt, s2.value FROM (SELECT key, count(value) as cnt FROM src GROUP BY key) s1 JOIN src s2 ON (s1.key = s2.key) ORDER BY s1.key @@ -516,33 +516,33 @@ $hdt$_0:src TableScan (TS_0) alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator (FIL_17) predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator (GBY_3) aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_4) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Group By Operator (GBY_5) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_10) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Join Operator (JOIN_12) condition map: @@ -551,23 +551,23 @@ $hdt$_0:src 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_13) expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_14) key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: string) Select Operator (SEL_15) expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator (FS_16) compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -576,19 +576,19 @@ $hdt$_1:s2 TableScan (TS_7) alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator (FIL_18) predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator (SEL_9) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator (RS_11) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Join Operator (JOIN_12) condition map: @@ -597,5 +597,5 @@ $hdt$_1:s2 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/explain_outputs.q.out b/ql/src/test/results/clientpositive/explain_outputs.q.out index d0fe893c75..adfd28d836 100644 --- a/ql/src/test/results/clientpositive/explain_outputs.q.out +++ b/ql/src/test/results/clientpositive/explain_outputs.q.out @@ -50,35 +50,35 @@ STAGE PLANS: TableScan alias: t1_n22 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2_n14 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -87,12 +87,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -106,7 +106,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -114,10 +114,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -157,35 +157,35 @@ STAGE PLANS: TableScan alias: t1_n22 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2/2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2_n14 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5/5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5/5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -194,12 +194,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5/1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -213,7 +213,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -221,10 +221,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -266,35 +266,35 @@ STAGE PLANS: TableScan alias: t1_n22 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2_n14 filterExpr: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -303,12 +303,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -322,7 +322,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -330,10 +330,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/explain_rearrange.q.out b/ql/src/test/results/clientpositive/explain_rearrange.q.out index 6ff089fe81..ec512451c4 100644 --- a/ql/src/test/results/clientpositive/explain_rearrange.q.out +++ b/ql/src/test/results/clientpositive/explain_rearrange.q.out @@ -69,14 +69,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -244,14 +244,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -343,14 +343,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -518,14 +518,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -617,14 +617,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -661,14 +661,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -891,14 +891,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -935,14 +935,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/extract.q.out b/ql/src/test/results/clientpositive/extract.q.out index 3386f66325..f85a9ce190 100644 --- a/ql/src/test/results/clientpositive/extract.q.out +++ b/ql/src/test/results/clientpositive/extract.q.out @@ -41,14 +41,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: extract_udf - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: day(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -90,14 +90,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: extract_udf - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: day(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/fetch_aggregation.q.out b/ql/src/test/results/clientpositive/fetch_aggregation.q.out index 801c6de35d..27b20b8e09 100644 --- a/ql/src/test/results/clientpositive/fetch_aggregation.q.out +++ b/ql/src/test/results/clientpositive/fetch_aggregation.q.out @@ -14,16 +14,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double), (UDFToDouble(key) * UDFToDouble(key)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), sum(_col0), min(_col0), max(_col0), sum(_col2), sum(_col1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -39,11 +39,11 @@ STAGE PLANS: aggregations: count(_col0), sum(_col1), min(_col2), max(_col3), sum(_col4), sum(_col5) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col1 (type: double), (_col1 / _col0) (type: double), _col2 (type: string), _col3 (type: string), power(((_col4 - ((_col5 * _col5) / _col0)) / _col0), 0.5) (type: double), ((_col4 - ((_col5 * _col5) / _col0)) / _col0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select count(key),sum(key),avg(key),min(key),max(key),std(key),variance(key) from src diff --git a/ql/src/test/results/clientpositive/filter_aggr.q.out b/ql/src/test/results/clientpositive/filter_aggr.q.out index 0b42dca52a..fbcc046bd9 100644 --- a/ql/src/test/results/clientpositive/filter_aggr.q.out +++ b/ql/src/test/results/clientpositive/filter_aggr.q.out @@ -29,24 +29,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -111,17 +111,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), 1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out index 19b506b30f..f1217d698d 100644 --- a/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out +++ b/ql/src/test/results/clientpositive/filter_cond_pushdown.q.out @@ -20,36 +20,36 @@ STAGE PLANS: TableScan alias: m filterExpr: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: f filterExpr: ((value) IN ('2008-04-08', '2008-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value) IN ('2008-04-08', '2008-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -59,10 +59,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 10491 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col3 = '2008-04-08') and (_col1 = '2008-04-08')) or (_col3 = '2008-04-09')) (type: boolean) - Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 807 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -78,24 +78,24 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 412 Data size: 4376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 807 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) TableScan alias: g filterExpr: (value <> '') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value <> '') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -104,14 +104,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col2, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -145,36 +145,36 @@ STAGE PLANS: TableScan alias: f filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: m filterExpr: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -184,10 +184,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 212779 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((_col1 = '2008-04-08') or (_col1 = '2008-04-10')) and (_col3 = '2008-04-08')) or (_col1 = '2008-04-09')) (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -203,24 +203,24 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: g filterExpr: (value <> '') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value <> '') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -229,14 +229,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col4 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -280,36 +280,36 @@ STAGE PLANS: TableScan alias: t2 filterExpr: (UDFToDouble(key) = 1.0D) (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1767 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 1.0D) (type: boolean) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), c_int (type: int), c_float (type: float) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: float) TableScan alias: t3 filterExpr: ((c_int = 1) and (UDFToDouble(key) = 1.0D)) (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1767 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) = 1.0D) and (c_int = 1)) (type: boolean) - Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), c_float (type: float) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 65 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float) Reduce Operator Tree: Join Operator @@ -319,14 +319,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col1 + 1) > 2) or ((_col2 + _col4) > 2)) (type: boolean) - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -340,25 +340,25 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (UDFToDouble(key) = 1.0D) (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1615 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 1.0D) (type: boolean) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5370 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5370 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -367,10 +367,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 144 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -403,36 +403,36 @@ STAGE PLANS: TableScan alias: f filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: m filterExpr: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -442,17 +442,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 212779 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((_col1 = '2008-04-08') or (_col1 = '2008-04-10')) and ((_col1 = '2008-04-08') or (_col1 = '2008-04-09')) and (_col3 = '2008-04-10')) or (_col3 = '2008-04-08')) (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1076 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/filter_cond_pushdown2.q.out b/ql/src/test/results/clientpositive/filter_cond_pushdown2.q.out index 39ddaac9ac..3aefd8b241 100644 --- a/ql/src/test/results/clientpositive/filter_cond_pushdown2.q.out +++ b/ql/src/test/results/clientpositive/filter_cond_pushdown2.q.out @@ -108,31 +108,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: users_table - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: field_3 (type: boolean) - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: field_1 (type: int), field_2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -148,13 +148,13 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -163,13 +163,13 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 1 Data size: 25080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(), sum(if(_col3 is not null, 1, 0)) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 25080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -185,7 +185,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 25080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -194,7 +194,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 25080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -209,17 +209,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 1 Data size: 25080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 25080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 25080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -230,31 +230,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: users_table - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: field_4 (type: boolean) - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: field_1 (type: int), field_2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 22800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/filter_cond_pushdown_HIVE_15647.q.out b/ql/src/test/results/clientpositive/filter_cond_pushdown_HIVE_15647.q.out index db4aee7a1f..2c88dc3763 100644 --- a/ql/src/test/results/clientpositive/filter_cond_pushdown_HIVE_15647.q.out +++ b/ql/src/test/results/clientpositive/filter_cond_pushdown_HIVE_15647.q.out @@ -36,27 +36,27 @@ STAGE PLANS: TableScan alias: sales filterExpr: ((store_number = customer_id) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((store_number = customer_id) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TableScan alias: store filterExpr: (store_id is not null and salad_bar) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (salad_bar and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -64,12 +64,12 @@ STAGE PLANS: keys: 0 store_id (type: int) 1 store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -83,7 +83,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -91,10 +91,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -128,27 +128,27 @@ STAGE PLANS: TableScan alias: sales filterExpr: ((store_number = customer_id) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((store_number = customer_id) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TableScan alias: store filterExpr: (store_id is not null and salad_bar) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (salad_bar and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -156,12 +156,12 @@ STAGE PLANS: keys: 0 store_id (type: int) 1 store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -175,7 +175,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -183,10 +183,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -220,27 +220,27 @@ STAGE PLANS: TableScan alias: sales filterExpr: ((store_number = customer_id) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((store_number = customer_id) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TableScan alias: store filterExpr: (store_id is not null and (salad_bar = true)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((salad_bar = true) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -248,12 +248,12 @@ STAGE PLANS: keys: 0 store_id (type: int) 1 store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -267,7 +267,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -275,10 +275,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -312,27 +312,27 @@ STAGE PLANS: TableScan alias: sales filterExpr: (store_id is not null and (store_number > customer_id)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((store_number > customer_id) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TableScan alias: store filterExpr: (store_id is not null and (salad_bar = false)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((salad_bar = false) and store_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: store_id (type: int) sort order: + Map-reduce partition columns: store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -340,12 +340,12 @@ STAGE PLANS: keys: 0 store_id (type: int) 1 store_id (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -359,7 +359,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -367,10 +367,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/filter_in_or_dup.q.out b/ql/src/test/results/clientpositive/filter_in_or_dup.q.out index f96298c65a..45d7c55a65 100644 --- a/ql/src/test/results/clientpositive/filter_in_or_dup.q.out +++ b/ql/src/test/results/clientpositive/filter_in_or_dup.q.out @@ -21,17 +21,17 @@ STAGE PLANS: TableScan alias: f filterExpr: (key) IN ('1', '2') (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1615 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key) IN ('1', '2') (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -67,17 +67,17 @@ STAGE PLANS: TableScan alias: f filterExpr: (key) IN ('1', '2') (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1615 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key) IN ('1', '2') (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -113,17 +113,17 @@ STAGE PLANS: TableScan alias: f filterExpr: (key) IN ('1', '2') (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1615 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key) IN ('1', '2') (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out index 07843d0667..c38e32a087 100644 --- a/ql/src/test/results/clientpositive/filter_join_breaktask.q.out +++ b/ql/src/test/results/clientpositive/filter_join_breaktask.q.out @@ -50,43 +50,43 @@ STAGE PLANS: TableScan alias: f filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 1450 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 1450 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan alias: m filterExpr: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2289 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((value <> '') and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2785 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -152,7 +152,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 - Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -182,29 +182,29 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int) auto parallelism: false TableScan alias: g filterExpr: ((ds = '2008-04-08') and (value <> '')) (type: boolean) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (value <> '') (type: boolean) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 auto parallelism: false Path -> Alias: @@ -292,17 +292,17 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col5 - Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col5 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/filter_numeric.q.out b/ql/src/test/results/clientpositive/filter_numeric.q.out index 6c7cc50116..b7aab01d75 100644 --- a/ql/src/test/results/clientpositive/filter_numeric.q.out +++ b/ql/src/test/results/clientpositive/filter_numeric.q.out @@ -39,14 +39,14 @@ STAGE PLANS: TableScan alias: partint filterExpr: (hr < 11) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (hr < 11) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select key, value, hr from partint where hr < 11 @@ -73,11 +73,11 @@ STAGE PLANS: TableScan alias: partint filterExpr: ((hr <= 12) and (hr > 11)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 91000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 91000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key, value, hr from partint where hr <= 12 and hr > 11 @@ -606,11 +606,11 @@ STAGE PLANS: TableScan alias: partint filterExpr: hr BETWEEN 11 AND 12 (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key, value, hr from partint where hr between 11 and 12 @@ -1641,11 +1641,11 @@ STAGE PLANS: TableScan alias: partint filterExpr: (not hr BETWEEN 12 AND 14) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 91000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 91000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key, value, hr from partint where hr not between 12 and 14 @@ -2174,11 +2174,11 @@ STAGE PLANS: TableScan alias: partint filterExpr: (hr < 13) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key, value, hr from partint where hr < 13 diff --git a/ql/src/test/results/clientpositive/filter_union.q.out b/ql/src/test/results/clientpositive/filter_union.q.out index a7cd8c1589..4d4036c5c0 100644 --- a/ql/src/test/results/clientpositive/filter_union.q.out +++ b/ql/src/test/results/clientpositive/filter_union.q.out @@ -43,24 +43,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -125,11 +125,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), 3 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -155,13 +155,13 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -181,13 +181,13 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -259,24 +259,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -341,11 +341,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), 4 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -407,22 +407,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -431,14 +431,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), 1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -486,22 +486,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -510,14 +510,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), 4 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -565,21 +565,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -588,14 +588,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), 4 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 99 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 99 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/flatten_and_or.q.out b/ql/src/test/results/clientpositive/flatten_and_or.q.out index 04b4a1db9c..e295f9be8c 100644 --- a/ql/src/test/results/clientpositive/flatten_and_or.q.out +++ b/ql/src/test/results/clientpositive/flatten_and_or.q.out @@ -43,17 +43,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key = '0') and (value = '8')) or ((key = '1') and (value = '5')) or ((key = '2') and (value = '6')) or ((key = '3') and (value = '8')) or ((key = '4') and (value = '1')) or ((key = '5') and (value = '6')) or ((key = '6') and (value = '1')) or ((key = '7') and (value = '1')) or ((key = '8') and (value = '1')) or ((key = '9') and (value = '1')) or ((key = '10') and (value = '3'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = '0') and (value = '8')) or ((key = '1') and (value = '5')) or ((key = '10') and (value = '3')) or ((key = '2') and (value = '6')) or ((key = '3') and (value = '8')) or ((key = '4') and (value = '1')) or ((key = '5') and (value = '6')) or ((key = '6') and (value = '1')) or ((key = '7') and (value = '1')) or ((key = '8') and (value = '1')) or ((key = '9') and (value = '1'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/floor_time.q.out b/ql/src/test/results/clientpositive/floor_time.q.out index e4ae6664cd..16c38914d2 100644 --- a/ql/src/test/results/clientpositive/floor_time.q.out +++ b/ql/src/test/results/clientpositive/floor_time.q.out @@ -52,14 +52,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: extract_udf_n0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: floor_day(t) (type: timestamp) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -101,14 +101,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: extract_udf_n0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: floor_day(t) (type: timestamp) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/fm-sketch.q.out b/ql/src/test/results/clientpositive/fm-sketch.q.out index f6f248d96c..52c4cc1d6c 100644 --- a/ql/src/test/results/clientpositive/fm-sketch.q.out +++ b/ql/src/test/results/clientpositive/fm-sketch.q.out @@ -29,29 +29,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: n_n0 - Statistics: Num rows: 500 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 500 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'fm', 16) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,29 +125,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: i_n1 - Statistics: Num rows: 500 Data size: 1406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 500 Data size: 1406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'fm', 16) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/fold_case.q.out b/ql/src/test/results/clientpositive/fold_case.q.out index 438829b9b1..359af7aecd 100644 --- a/ql/src/test/results/clientpositive/fold_case.q.out +++ b/ql/src/test/results/clientpositive/fold_case.q.out @@ -15,20 +15,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -36,10 +36,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -68,20 +68,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (not NVL((key = '238'),false)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not NVL((key = '238'),false)) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -89,10 +89,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -189,20 +189,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -210,10 +210,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -294,20 +294,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -315,10 +315,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -347,17 +347,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (not NVL((key = '238'),false)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not NVL((key = '238'),false)) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CASE WHEN ((key = '238')) THEN (null) ELSE (false) END (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 1000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 1000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -428,20 +428,20 @@ STAGE PLANS: TableScan alias: src filterExpr: CASE WHEN ((key = '238')) THEN (null) ELSE (true) END (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((key = '238')) THEN (null) ELSE (true) END (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -449,10 +449,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -507,14 +507,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CASE WHEN ((key = value)) THEN ('1') ELSE ('0') END (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -543,10 +543,10 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out b/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out index cb4d65c0c9..55d1f937cb 100644 --- a/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out +++ b/ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out @@ -41,25 +41,25 @@ STAGE PLANS: TableScan alias: lineitem filterExpr: ((DATE'1996-03-30' = to_date(l_shipdate)) and (l_shipmode = 'RAIL')) (type: boolean) - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 19000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((DATE'1996-03-30' = to_date(l_shipdate)) and (l_shipmode = 'RAIL')) (type: boolean) - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_orderkey (type: int), (UDFToDouble(l_partkey) / 1000000.0D) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -68,14 +68,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: double), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -102,17 +102,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '238' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -140,17 +140,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key) IN ('238', '94') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key) IN ('238', '94') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2175 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2175 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2175 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,17 +178,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '238' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -216,17 +216,17 @@ STAGE PLANS: TableScan alias: src filterExpr: CASE WHEN ((key <> '238')) THEN ((key = '238')) WHEN ((key = '23')) THEN ((key = '238')) ELSE (null) END (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((key <> '238')) THEN ((key = '238')) WHEN ((key = '23')) THEN ((key = '238')) ELSE (null) END (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/fold_when.q.out b/ql/src/test/results/clientpositive/fold_when.q.out index dfc49efb94..50a6385340 100644 --- a/ql/src/test/results/clientpositive/fold_when.q.out +++ b/ql/src/test/results/clientpositive/fold_when.q.out @@ -14,17 +14,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -53,17 +53,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -92,11 +92,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain @@ -115,17 +115,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -155,17 +155,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '238' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -195,17 +195,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '238' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -234,11 +234,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain @@ -257,17 +257,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -297,17 +297,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '238' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -337,17 +337,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (not NVL((key = '238'),false)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not NVL((key = '238'),false)) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -376,11 +376,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain @@ -399,11 +399,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain @@ -422,11 +422,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain @@ -446,17 +446,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (not NVL((key = '11'),false)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not NVL((key = '11'),false)) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -485,10 +485,10 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/folder_predicate.q.out b/ql/src/test/results/clientpositive/folder_predicate.q.out index 64d2693cc7..422427eb49 100644 --- a/ql/src/test/results/clientpositive/folder_predicate.q.out +++ b/ql/src/test/results/clientpositive/folder_predicate.q.out @@ -36,17 +36,17 @@ STAGE PLANS: TableScan alias: predicate_fold_tb filterExpr: (value is null or (value <> 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value <> 3) or value is null) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -89,17 +89,17 @@ STAGE PLANS: TableScan alias: predicate_fold_tb filterExpr: (value is null or (value < 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value < 3) or value is null) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -140,17 +140,17 @@ STAGE PLANS: TableScan alias: predicate_fold_tb filterExpr: (value is null or (value > 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 3) or value is null) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -191,17 +191,17 @@ STAGE PLANS: TableScan alias: predicate_fold_tb filterExpr: (value is null or (value <= 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value <= 3) or value is null) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -243,17 +243,17 @@ STAGE PLANS: TableScan alias: predicate_fold_tb filterExpr: (value is null or (value >= 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value >= 3) or value is null) (type: boolean) - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -295,17 +295,17 @@ STAGE PLANS: TableScan alias: predicate_fold_tb filterExpr: (value is null or (value = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value = 3) or value is null) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -345,17 +345,17 @@ STAGE PLANS: TableScan alias: predicate_fold_tb filterExpr: (value is null or (value <= 1) or (value > 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value <= 1) or (value > 3) or value is null) (type: boolean) - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/foldts.q.out b/ql/src/test/results/clientpositive/foldts.q.out index 83a6481601..e32c0346e3 100644 --- a/ql/src/test/results/clientpositive/foldts.q.out +++ b/ql/src/test/results/clientpositive/foldts.q.out @@ -14,17 +14,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 491520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), to_unix_timestamp(ctimestamp1) (type: bigint), to_unix_timestamp(ctimestamp1) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 688128 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -72,17 +72,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 491520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: from_unixtime(to_unix_timestamp(ctimestamp1), 'EEEE') (type: string) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2260992 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -120,17 +120,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 491520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: from_unixtime(to_unix_timestamp(ctimestamp1), 'EEEE') (type: string) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2260992 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out b/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out index a6be90476c..d50f191136 100644 --- a/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/fp_literal_arithmetic.q.out @@ -17,22 +17,22 @@ STAGE PLANS: TableScan alias: q0 filterExpr: l_discount BETWEEN 0.05D AND 0.07D (type: boolean) - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: l_discount BETWEEN 0.05D AND 0.07D (type: boolean) - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_extendedprice (type: double) outputColumnNames: l_extendedprice - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(l_extendedprice) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -40,10 +40,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -85,22 +85,22 @@ STAGE PLANS: TableScan alias: q1 filterExpr: l_discount BETWEEN 0.05D AND 0.07D (type: boolean) - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: l_discount BETWEEN 0.05D AND 0.07D (type: boolean) - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_extendedprice (type: double) outputColumnNames: l_extendedprice - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(l_extendedprice) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -108,10 +108,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -190,22 +190,22 @@ STAGE PLANS: TableScan alias: q10 filterExpr: l_discount BETWEEN CAST( '0.05' AS decimal(3,2)) AND CAST( '0.07' AS decimal(3,2)) (type: boolean) - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: l_discount BETWEEN CAST( '0.05' AS decimal(3,2)) AND CAST( '0.07' AS decimal(3,2)) (type: boolean) - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_extendedprice (type: double) outputColumnNames: l_extendedprice - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(l_extendedprice) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -213,10 +213,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -258,22 +258,22 @@ STAGE PLANS: TableScan alias: q11 filterExpr: l_discount BETWEEN (0.06 - 0.01) AND (0.06 + 0.01) (type: boolean) - Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: l_discount BETWEEN (0.06 - 0.01) AND (0.06 + 0.01) (type: boolean) - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: l_extendedprice (type: double) outputColumnNames: l_extendedprice - Statistics: Num rows: 11 Data size: 1319 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(l_extendedprice) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -281,10 +281,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/gby_star.q.out b/ql/src/test/results/clientpositive/gby_star.q.out index fe2cb82b53..75c2c8d6e6 100644 --- a/ql/src/test/results/clientpositive/gby_star.q.out +++ b/ql/src/test/results/clientpositive/gby_star.q.out @@ -14,22 +14,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(key) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: double) Reduce Operator Tree: @@ -38,13 +38,13 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -91,21 +91,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(key) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: double) Reduce Operator Tree: @@ -114,13 +114,13 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -167,21 +167,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double) Reduce Operator Tree: @@ -190,13 +190,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -246,35 +246,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -283,13 +283,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -305,7 +305,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double) Execution mode: vectorized @@ -315,13 +315,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/gen_udf_example_add10.q.out b/ql/src/test/results/clientpositive/gen_udf_example_add10.q.out index cc4642d377..5c3789dca7 100644 --- a/ql/src/test/results/clientpositive/gen_udf_example_add10.q.out +++ b/ql/src/test/results/clientpositive/gen_udf_example_add10.q.out @@ -34,28 +34,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n102 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: add10(x) (type: int), add10(y) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: double) sort order: -+ - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby1.q.out b/ql/src/test/results/clientpositive/groupby1.q.out index 70b39d887d..f85da90eb8 100644 --- a/ql/src/test/results/clientpositive/groupby1.q.out +++ b/ql/src/test/results/clientpositive/groupby1.q.out @@ -24,16 +24,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -42,7 +42,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -58,7 +58,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -67,14 +67,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby10.q.out b/ql/src/test/results/clientpositive/groupby10.q.out index 665bf929b5..53b2840e9d 100644 --- a/ql/src/test/results/clientpositive/groupby10.q.out +++ b/ql/src/test/results/clientpositive/groupby10.q.out @@ -60,20 +60,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: input - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -87,7 +87,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -103,7 +103,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -112,14 +112,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -128,7 +128,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -161,7 +161,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -169,7 +169,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -183,7 +183,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -191,10 +191,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -216,7 +216,7 @@ STAGE PLANS: key expressions: key (type: int), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -224,7 +224,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -240,7 +240,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -249,14 +249,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -265,7 +265,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -290,7 +290,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -298,7 +298,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -312,7 +312,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -320,10 +320,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -435,20 +435,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: input - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -462,7 +462,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -478,7 +478,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -487,14 +487,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -503,7 +503,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -536,7 +536,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -544,7 +544,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -558,7 +558,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -566,10 +566,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -591,7 +591,7 @@ STAGE PLANS: key expressions: key (type: int), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -599,7 +599,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -615,7 +615,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -624,14 +624,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -640,7 +640,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -665,7 +665,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -673,7 +673,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -687,7 +687,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1460 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -695,10 +695,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -805,33 +805,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: input - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: int) - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -840,7 +840,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -852,14 +852,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -868,7 +868,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -900,7 +900,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -908,10 +908,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -941,7 +941,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -949,10 +949,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1508 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby11.q.out b/ql/src/test/results/clientpositive/groupby11.q.out index fd13d3a7bb..429940bf91 100644 --- a/ql/src/test/results/clientpositive/groupby11.q.out +++ b/ql/src/test/results/clientpositive/groupby11.q.out @@ -48,20 +48,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string), key (type: string) sort order: ++ Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -75,7 +75,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 53500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -91,7 +91,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 53500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -100,14 +100,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 32849 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -116,7 +116,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 57102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -152,7 +152,7 @@ STAGE PLANS: key expressions: '111' (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 57102 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -161,7 +161,7 @@ STAGE PLANS: keys: '111' (type: string) mode: partial1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 422125 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -177,7 +177,7 @@ STAGE PLANS: key expressions: '111' (type: string) sort order: + Map-reduce partition columns: '111' (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 422125 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -186,14 +186,14 @@ STAGE PLANS: keys: '111' (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1407 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), '111' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1407 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1407 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -215,7 +215,7 @@ STAGE PLANS: key expressions: substr(value, 5) (type: string), key (type: string) sort order: ++ Map-reduce partition columns: substr(value, 5) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -223,7 +223,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -239,7 +239,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -248,14 +248,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 61400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 58944 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 58944 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -264,7 +264,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) outputColumnNames: key, val1, val2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 85653 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -292,7 +292,7 @@ STAGE PLANS: key expressions: '111' (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 85653 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), val1 (type: int), val2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -301,7 +301,7 @@ STAGE PLANS: keys: '111' (type: string) mode: partial1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 422125 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -317,7 +317,7 @@ STAGE PLANS: key expressions: '111' (type: string) sort order: + Map-reduce partition columns: '111' (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 422125 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -326,14 +326,14 @@ STAGE PLANS: keys: '111' (type: string) mode: final outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1407 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), '111' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1407 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1407 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby12.q.out b/ql/src/test/results/clientpositive/groupby12.q.out index 43fdf6ac54..9104067a11 100644 --- a/ql/src/test/results/clientpositive/groupby12.q.out +++ b/ql/src/test/results/clientpositive/groupby12.q.out @@ -26,16 +26,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -43,14 +43,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 32548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col1) (type: int), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -59,7 +59,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -91,7 +91,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -99,10 +99,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby13.q.out b/ql/src/test/results/clientpositive/groupby13.q.out index 0747cfabbf..92590b6991 100644 --- a/ql/src/test/results/clientpositive/groupby13.q.out +++ b/ql/src/test/results/clientpositive/groupby13.q.out @@ -42,22 +42,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: grpby_test - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: int_col_7 (type: int), int_col_7 (type: int), least(COALESCE(int_col_5,-279),COALESCE(int_col_7,476)) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col2) keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -66,14 +66,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby1_limit.q.out b/ql/src/test/results/clientpositive/groupby1_limit.q.out index 8b3757bc9a..586266e6d2 100644 --- a/ql/src/test/results/clientpositive/groupby1_limit.q.out +++ b/ql/src/test/results/clientpositive/groupby1_limit.q.out @@ -24,22 +24,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double) Reduce Operator Tree: @@ -48,10 +48,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -65,7 +65,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: double) Execution mode: vectorized @@ -73,17 +73,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby1_map.q.out b/ql/src/test/results/clientpositive/groupby1_map.q.out index bb942e6aa7..d6d9d5b5d1 100644 --- a/ql/src/test/results/clientpositive/groupby1_map.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map.q.out @@ -24,22 +24,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Reduce Operator Tree: Group By Operator @@ -47,14 +47,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -63,12 +63,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: double) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -100,7 +100,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -108,10 +108,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out index f201f3fed6..1073d4574e 100644 --- a/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map_nomap.q.out @@ -24,22 +24,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Reduce Operator Tree: Group By Operator @@ -47,14 +47,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -63,12 +63,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: double) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -100,7 +100,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -108,10 +108,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby1_map_skew.q.out b/ql/src/test/results/clientpositive/groupby1_map_skew.q.out index 91bfc00648..88b3a66124 100644 --- a/ql/src/test/results/clientpositive/groupby1_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby1_map_skew.q.out @@ -25,22 +25,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Reduce Operator Tree: Group By Operator @@ -48,7 +48,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -64,7 +64,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -73,14 +73,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -89,12 +89,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: double) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 3000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -126,7 +126,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -134,10 +134,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby1_noskew.q.out b/ql/src/test/results/clientpositive/groupby1_noskew.q.out index d1f78682d1..a3e9a1d649 100644 --- a/ql/src/test/results/clientpositive/groupby1_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby1_noskew.q.out @@ -24,16 +24,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -42,14 +42,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -58,7 +58,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: double) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -90,7 +90,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -98,10 +98,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby2_limit.q.out b/ql/src/test/results/clientpositive/groupby2_limit.q.out index f99a99a572..9eee1c7f56 100644 --- a/ql/src/test/results/clientpositive/groupby2_limit.q.out +++ b/ql/src/test/results/clientpositive/groupby2_limit.q.out @@ -15,22 +15,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double) Reduce Operator Tree: @@ -39,7 +39,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -54,7 +54,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double) Execution mode: vectorized @@ -62,13 +62,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby2_map.q.out b/ql/src/test/results/clientpositive/groupby2_map.q.out index bc69a13d65..beb6eec954 100644 --- a/ql/src/test/results/clientpositive/groupby2_map.q.out +++ b/ql/src/test/results/clientpositive/groupby2_map.q.out @@ -26,22 +26,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col1), sum(_col1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double) Reduce Operator Tree: Group By Operator @@ -49,14 +49,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -65,12 +65,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) outputColumnNames: key, c1, c2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -102,7 +102,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -110,10 +110,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out index da3443cb09..bf76d76456 100644 --- a/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby2_map_multi_distinct.q.out @@ -26,22 +26,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col1), sum(_col1), sum(DISTINCT _col1), count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -49,14 +49,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 54000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -65,12 +65,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -102,7 +102,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -110,10 +110,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -172,22 +172,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col0), sum(_col1), sum(DISTINCT _col1), count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -195,14 +195,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 54000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -211,12 +211,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -248,7 +248,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -256,10 +256,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby2_map_skew.q.out b/ql/src/test/results/clientpositive/groupby2_map_skew.q.out index e137bd65d7..182acdbec7 100644 --- a/ql/src/test/results/clientpositive/groupby2_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby2_map_skew.q.out @@ -27,22 +27,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col1), sum(_col1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double) Reduce Operator Tree: Group By Operator @@ -50,7 +50,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -66,7 +66,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 50000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -91,12 +91,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) outputColumnNames: key, c1, c2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -128,7 +128,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -136,10 +136,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby2_noskew.q.out b/ql/src/test/results/clientpositive/groupby2_noskew.q.out index 583885c186..605b0f8688 100644 --- a/ql/src/test/results/clientpositive/groupby2_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby2_noskew.q.out @@ -26,16 +26,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -43,14 +43,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 63200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -59,7 +59,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) outputColumnNames: key, c1, c2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -91,7 +91,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), c1 (type: int), c2 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -99,10 +99,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out index 6998b8311b..07066d8ad9 100644 --- a/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby2_noskew_multi_distinct.q.out @@ -26,16 +26,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -44,14 +44,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -60,7 +60,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -92,7 +92,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), c1 (type: int), c2 (type: string), c3 (type: int), c4 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -100,10 +100,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll'), compute_stats(VALUE._col4, 'hll'), compute_stats(VALUE._col5, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby3.q.out b/ql/src/test/results/clientpositive/groupby3.q.out index aff57704d8..8532e4eeaa 100644 --- a/ql/src/test/results/clientpositive/groupby3.q.out +++ b/ql/src/test/results/clientpositive/groupby3.q.out @@ -45,23 +45,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(value, 5) (type: string) sort order: + Map-reduce partition columns: substr(value, 5) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(KEY._col0:0._col0), avg(KEY._col0:0._col0), avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), std(KEY._col0:0._col0), stddev_samp(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) mode: partial1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -76,7 +76,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: struct), _col2 (type: struct), _col3 (type: string), _col4 (type: string), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -84,14 +84,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8) mode: final outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -100,12 +100,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9 - Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -137,7 +137,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -145,10 +145,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8) mode: final outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby3_map.q.out b/ql/src/test/results/clientpositive/groupby3_map.q.out index a5ec308176..131775e151 100644 --- a/ql/src/test/results/clientpositive/groupby3_map.q.out +++ b/ql/src/test/results/clientpositive/groupby3_map.q.out @@ -43,35 +43,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(DISTINCT _col0), count(DISTINCT _col0), max(_col0), min(_col0), sum(_col2), sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: bigint), _col5 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: double) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(VALUE._col4), min(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -80,19 +80,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9 - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out index d8fe780662..a5ef548006 100644 --- a/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby3_map_multi_distinct.q.out @@ -47,35 +47,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(DISTINCT _col0), count(DISTINCT _col0), max(_col0), min(_col0), sum(_col2), sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 150000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: bigint), _col5 (type: string), _col6 (type: string), _col7 (type: double), _col8 (type: double) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(VALUE._col4), min(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -84,19 +84,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 - Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll'), compute_stats(c10, 'hll'), compute_stats(c11, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 4832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4664 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 4832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4664 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4664 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby3_map_skew.q.out b/ql/src/test/results/clientpositive/groupby3_map_skew.q.out index 02317a2b6e..386546e39f 100644 --- a/ql/src/test/results/clientpositive/groupby3_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby3_map_skew.q.out @@ -44,29 +44,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(substr(value, 5)), avg(substr(value, 5)), avg(DISTINCT substr(value, 5)), max(substr(value, 5)), min(substr(value, 5)), std(substr(value, 5)), stddev_samp(substr(value, 5)), variance(substr(value, 5)), var_samp(substr(value, 5)) keys: substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 348000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 348000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: struct), _col4 (type: string), _col5 (type: string), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(DISTINCT KEY._col0:0._col0), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8) mode: partials outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -80,7 +80,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: struct), _col2 (type: struct), _col3 (type: string), _col4 (type: string), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -88,14 +88,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), max(VALUE._col3), min(VALUE._col4), std(VALUE._col5), stddev_samp(VALUE._col6), variance(VALUE._col7), var_samp(VALUE._col8) mode: final outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double), UDFToDouble(_col4) (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,19 +104,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9 - Statistics: Num rows: 1 Data size: 1464 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 4064 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 4064 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4064 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby3_noskew.q.out b/ql/src/test/results/clientpositive/groupby3_noskew.q.out index a870fc1326..4a9bc4b20c 100644 --- a/ql/src/test/results/clientpositive/groupby3_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby3_noskew.q.out @@ -43,15 +43,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double), _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -59,14 +59,14 @@ STAGE PLANS: aggregations: sum(KEY._col0:0._col0), count(KEY._col0:0._col0), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), sum(VALUE._col0), sum(VALUE._col1) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -75,15 +75,15 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out index 7801a6c66f..27b2bb4482 100644 --- a/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby3_noskew_multi_distinct.q.out @@ -47,15 +47,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5) (type: string), UDFToDouble(substr(value, 5)) (type: double), (UDFToDouble(substr(value, 5)) * UDFToDouble(substr(value, 5))) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double), _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -63,14 +63,14 @@ STAGE PLANS: aggregations: sum(KEY._col0:0._col0), count(KEY._col0:0._col0), sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), max(KEY._col0:0._col0), min(KEY._col0:0._col0), sum(VALUE._col0), sum(VALUE._col1) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), (_col0 / _col1) (type: double), (_col2 / _col3) (type: double), UDFToDouble(_col4) (type: double), UDFToDouble(_col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / _col1), 0.5) (type: double), power(((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / _col1) (type: double), ((_col6 - ((_col7 * _col7) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), _col2 (type: double), UDFToDouble(_col3) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -79,15 +79,15 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 - Statistics: Num rows: 1 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll'), compute_stats(c10, 'hll'), compute_stats(c11, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1 Data size: 5008 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4840 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5008 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4840 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby4.q.out b/ql/src/test/results/clientpositive/groupby4.q.out index 976376118a..183b793370 100644 --- a/ql/src/test/results/clientpositive/groupby4.q.out +++ b/ql/src/test/results/clientpositive/groupby4.q.out @@ -28,23 +28,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -60,17 +60,17 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -79,7 +79,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -112,7 +112,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE value expressions: c1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -120,7 +120,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll') mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -134,7 +134,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -142,10 +142,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby4_noskew.q.out b/ql/src/test/results/clientpositive/groupby4_noskew.q.out index c3bbb20e9d..4dcd253b05 100644 --- a/ql/src/test/results/clientpositive/groupby4_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby4_noskew.q.out @@ -26,26 +26,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(key, 1, 1) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -54,7 +54,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -86,7 +86,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE value expressions: c1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -94,10 +94,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll') mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby5.q.out b/ql/src/test/results/clientpositive/groupby5.q.out index 7e9d928545..aee20f517e 100644 --- a/ql/src/test/results/clientpositive/groupby5.q.out +++ b/ql/src/test/results/clientpositive/groupby5.q.out @@ -32,16 +32,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -50,7 +50,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -66,7 +66,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -91,7 +91,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -124,7 +124,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -132,7 +132,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -146,7 +146,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -154,10 +154,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby5_map.q.out b/ql/src/test/results/clientpositive/groupby5_map.q.out index ea4d7c52ed..a23d69fac5 100644 --- a/ql/src/test/results/clientpositive/groupby5_map.q.out +++ b/ql/src/test/results/clientpositive/groupby5_map.q.out @@ -23,33 +23,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -58,19 +58,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: key - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out index 9634b2c517..7c10e55db1 100644 --- a/ql/src/test/results/clientpositive/groupby5_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby5_map_skew.q.out @@ -23,33 +23,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -58,19 +58,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: key - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby5_noskew.q.out b/ql/src/test/results/clientpositive/groupby5_noskew.q.out index 8a7b1aad5f..acb081c4c9 100644 --- a/ql/src/test/results/clientpositive/groupby5_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby5_noskew.q.out @@ -30,16 +30,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -48,14 +48,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -64,7 +64,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -96,7 +96,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -104,10 +104,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby6.q.out b/ql/src/test/results/clientpositive/groupby6.q.out index 5928da6411..8bb5b891f4 100644 --- a/ql/src/test/results/clientpositive/groupby6.q.out +++ b/ql/src/test/results/clientpositive/groupby6.q.out @@ -28,23 +28,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5, 1) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -60,17 +60,17 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -79,7 +79,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -112,7 +112,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE value expressions: c1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -120,7 +120,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll') mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -134,7 +134,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -142,10 +142,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby6_map.q.out b/ql/src/test/results/clientpositive/groupby6_map.q.out index 3e6c10cdb5..d2aa1989f9 100644 --- a/ql/src/test/results/clientpositive/groupby6_map.q.out +++ b/ql/src/test/results/clientpositive/groupby6_map.q.out @@ -26,31 +26,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5, 1) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -59,12 +59,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -96,7 +96,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -104,10 +104,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby6_map_skew.q.out b/ql/src/test/results/clientpositive/groupby6_map_skew.q.out index 71aa30c8bf..cb0498c54c 100644 --- a/ql/src/test/results/clientpositive/groupby6_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby6_map_skew.q.out @@ -27,28 +27,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5, 1) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -64,17 +64,17 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -83,12 +83,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -120,7 +120,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -128,10 +128,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby6_noskew.q.out b/ql/src/test/results/clientpositive/groupby6_noskew.q.out index 5a999619a8..1de384e854 100644 --- a/ql/src/test/results/clientpositive/groupby6_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby6_noskew.q.out @@ -26,26 +26,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(value, 5, 1) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -54,7 +54,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -86,7 +86,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE value expressions: c1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -94,10 +94,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll') mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby7_map.q.out b/ql/src/test/results/clientpositive/groupby7_map.q.out index c27f02e8a8..75d1bbc73d 100644 --- a/ql/src/test/results/clientpositive/groupby7_map.q.out +++ b/ql/src/test/results/clientpositive/groupby7_map.q.out @@ -40,33 +40,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(substr(value, 5)) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(substr(value, 5)) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -79,14 +79,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -95,12 +95,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -132,7 +132,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -140,10 +140,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -165,7 +165,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -174,14 +174,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -190,12 +190,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -219,7 +219,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -227,10 +227,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out index 294d2ec0b6..a0738847e8 100644 --- a/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/groupby7_map_multi_single_reducer.q.out @@ -39,34 +39,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: substr(value, 5) (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -75,12 +75,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -92,14 +92,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -108,12 +108,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -145,7 +145,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -153,10 +153,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -186,7 +186,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -194,10 +194,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby7_map_skew.q.out b/ql/src/test/results/clientpositive/groupby7_map_skew.q.out index 10a3ae48b7..82726bfc92 100644 --- a/ql/src/test/results/clientpositive/groupby7_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby7_map_skew.q.out @@ -42,33 +42,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(substr(value, 5)) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(substr(value, 5)) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -81,7 +81,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -97,7 +97,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -106,14 +106,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -122,12 +122,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -159,7 +159,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -167,10 +167,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -192,7 +192,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -201,7 +201,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -217,7 +217,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -226,14 +226,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -242,12 +242,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -271,7 +271,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -279,10 +279,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby7_noskew.q.out b/ql/src/test/results/clientpositive/groupby7_noskew.q.out index aaa09b8f9a..1e19b449ee 100644 --- a/ql/src/test/results/clientpositive/groupby7_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby7_noskew.q.out @@ -40,21 +40,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: substr(value, 5) (type: string) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -68,14 +68,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -84,7 +84,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -116,7 +116,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -124,10 +124,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -149,7 +149,7 @@ STAGE PLANS: key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: substr(value, 5) (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -158,14 +158,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -174,7 +174,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -198,7 +198,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -206,10 +206,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out index abe4ff9edc..603fa0ddc0 100644 --- a/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/groupby7_noskew_multi_single_reducer.q.out @@ -41,27 +41,27 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: substr(value, 5) (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -73,7 +73,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -88,7 +88,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double) Execution mode: vectorized @@ -96,17 +96,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -115,7 +115,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -147,7 +147,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -155,10 +155,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -179,7 +179,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double) Execution mode: vectorized @@ -187,17 +187,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -206,7 +206,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -230,7 +230,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -238,10 +238,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby8.q.out b/ql/src/test/results/clientpositive/groupby8.q.out index ceb8a5b61a..65c4a97da7 100644 --- a/ql/src/test/results/clientpositive/groupby8.q.out +++ b/ql/src/test/results/clientpositive/groupby8.q.out @@ -44,20 +44,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -71,7 +71,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -87,7 +87,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -96,14 +96,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -112,7 +112,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -145,7 +145,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -153,7 +153,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -167,7 +167,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -175,10 +175,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -200,7 +200,7 @@ STAGE PLANS: key expressions: key (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -208,7 +208,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -224,7 +224,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -233,14 +233,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -249,7 +249,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -274,7 +274,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -282,7 +282,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -296,7 +296,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -304,10 +304,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -995,20 +995,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1022,7 +1022,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1038,7 +1038,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1047,14 +1047,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1063,7 +1063,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1096,7 +1096,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -1104,7 +1104,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1118,7 +1118,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1126,10 +1126,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1151,7 +1151,7 @@ STAGE PLANS: key expressions: key (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -1159,7 +1159,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1175,7 +1175,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1184,14 +1184,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1200,7 +1200,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1225,7 +1225,7 @@ STAGE PLANS: Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -1233,7 +1233,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1247,7 +1247,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1255,10 +1255,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby8_map.q.out b/ql/src/test/results/clientpositive/groupby8_map.q.out index 529970cf70..1bd94fb06b 100644 --- a/ql/src/test/results/clientpositive/groupby8_map.q.out +++ b/ql/src/test/results/clientpositive/groupby8_map.q.out @@ -39,33 +39,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -74,12 +74,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -91,14 +91,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -107,12 +107,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -144,7 +144,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -152,10 +152,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -185,7 +185,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -193,10 +193,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby8_map_skew.q.out b/ql/src/test/results/clientpositive/groupby8_map_skew.q.out index f5bcc5a655..f0adfcff18 100644 --- a/ql/src/test/results/clientpositive/groupby8_map_skew.q.out +++ b/ql/src/test/results/clientpositive/groupby8_map_skew.q.out @@ -42,32 +42,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -80,7 +80,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -96,7 +96,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -105,14 +105,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -121,12 +121,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -158,7 +158,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -166,10 +166,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -191,7 +191,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -199,7 +199,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -215,7 +215,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -224,14 +224,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -240,12 +240,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -269,7 +269,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -277,10 +277,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby8_noskew.q.out b/ql/src/test/results/clientpositive/groupby8_noskew.q.out index ed6c3a5c1c..fbd1860905 100644 --- a/ql/src/test/results/clientpositive/groupby8_noskew.q.out +++ b/ql/src/test/results/clientpositive/groupby8_noskew.q.out @@ -39,33 +39,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -74,7 +74,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -86,14 +86,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -102,7 +102,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -134,7 +134,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -142,10 +142,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -175,7 +175,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 59408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: int), value (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -183,10 +183,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby9.q.out b/ql/src/test/results/clientpositive/groupby9.q.out index 98d437f8a1..af579c728a 100644 --- a/ql/src/test/results/clientpositive/groupby9.q.out +++ b/ql/src/test/results/clientpositive/groupby9.q.out @@ -40,32 +40,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), value (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -78,14 +78,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -94,12 +94,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -131,7 +131,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -139,10 +139,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -164,7 +164,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -172,14 +172,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -188,12 +188,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -217,7 +217,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -225,10 +225,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -913,32 +913,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: value (type: string), key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -951,14 +951,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -967,12 +967,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1004,7 +1004,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1012,10 +1012,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1037,7 +1037,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -1045,14 +1045,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col1) (type: int), _col0 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1061,12 +1061,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1090,7 +1090,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1098,10 +1098,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1786,32 +1786,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), value (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1824,14 +1824,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1840,12 +1840,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1877,7 +1877,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1885,10 +1885,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1910,7 +1910,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -1918,14 +1918,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1934,12 +1934,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1963,7 +1963,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1971,10 +1971,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2659,33 +2659,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(substr(value, 5)) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(substr(value, 5)) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2699,14 +2699,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2715,12 +2715,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2752,7 +2752,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2760,10 +2760,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2785,7 +2785,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -2794,14 +2794,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2810,12 +2810,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2839,7 +2839,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2847,10 +2847,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3535,32 +3535,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: value (type: string), key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3573,14 +3573,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3589,12 +3589,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3626,7 +3626,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -3634,10 +3634,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3659,7 +3659,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 185000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -3667,14 +3667,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col1) (type: int), _col0 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3683,12 +3683,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3712,7 +3712,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -3720,10 +3720,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_complex_types.q.out b/ql/src/test/results/clientpositive/groupby_complex_types.q.out index e40d26ab65..d51d1a44bd 100644 --- a/ql/src/test/results/clientpositive/groupby_complex_types.q.out +++ b/ql/src/test/results/clientpositive/groupby_complex_types.q.out @@ -51,33 +51,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: array(key) (type: array) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: array) sort order: + Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: map(key:value) (type: map) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -87,13 +87,13 @@ STAGE PLANS: Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: struct(key,value) (type: struct) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 106000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -106,10 +106,10 @@ STAGE PLANS: keys: KEY._col0 (type: array) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -138,7 +138,7 @@ STAGE PLANS: key expressions: _col0 (type: map) sort order: + Map-reduce partition columns: _col0 (type: map) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -147,10 +147,10 @@ STAGE PLANS: keys: KEY._col0 (type: map) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -179,7 +179,7 @@ STAGE PLANS: key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 106000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -188,10 +188,10 @@ STAGE PLANS: keys: KEY._col0 (type: struct) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 106000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 106000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out index d52b2776b5..985640469f 100644 --- a/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/groupby_complex_types_multi_single_reducer.q.out @@ -40,34 +40,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: array(key) (type: array) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: array) sort order: + Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: map(key:value) (type: map) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -80,7 +80,7 @@ STAGE PLANS: keys: KEY._col0 (type: array) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -95,7 +95,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: array) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -103,13 +103,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: array), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 482000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 19280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 19280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -138,7 +138,7 @@ STAGE PLANS: key expressions: _col0 (type: map) sort order: + Map-reduce partition columns: _col0 (type: map) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -148,7 +148,7 @@ STAGE PLANS: keys: KEY._col0 (type: map) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -163,7 +163,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: map) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -171,13 +171,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: map), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 232000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 9280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 9280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_cube1.q.out b/ql/src/test/results/clientpositive/groupby_cube1.q.out index da87cbf4a2..c91ea26208 100644 --- a/ql/src/test/results/clientpositive/groupby_cube1.q.out +++ b/ql/src/test/results/clientpositive/groupby_cube1.q.out @@ -30,22 +30,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n82 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -53,15 +53,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -89,22 +89,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n82 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -112,15 +112,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -174,22 +174,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n82 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -197,14 +197,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -258,37 +258,37 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n82 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT val) keys: key (type: string), 0L (type: bigint), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0) keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -331,22 +331,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n82 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -354,7 +354,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -370,7 +370,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -378,15 +378,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,29 +441,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n82 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT val) keys: key (type: string), 0L (type: bigint), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0) keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -479,7 +479,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -487,15 +487,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: final outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -565,33 +565,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n82 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(1) keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -604,7 +604,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -620,7 +620,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -628,15 +628,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -645,12 +645,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key1, key2, val - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(val, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -682,17 +682,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -714,7 +714,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -722,7 +722,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -738,7 +738,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -746,15 +746,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -763,12 +763,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key1, key2, val - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(val, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -792,17 +792,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_cube_multi_gby.q.out b/ql/src/test/results/clientpositive/groupby_cube_multi_gby.q.out index caa031b734..c89c872330 100644 --- a/ql/src/test/results/clientpositive/groupby_cube_multi_gby.q.out +++ b/ql/src/test/results/clientpositive/groupby_cube_multi_gby.q.out @@ -46,30 +46,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 186000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 186000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -82,14 +82,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 186000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 271000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 271000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -98,12 +98,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 271000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -135,7 +135,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -143,10 +143,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -168,18 +168,18 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -188,12 +188,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -217,7 +217,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -225,10 +225,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out index 7c11b8adc5..bdea99ce2b 100644 --- a/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out +++ b/ql/src/test/results/clientpositive/groupby_distinct_samekey.q.out @@ -32,32 +32,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n60 - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: int1_n60 (type: int) outputColumnNames: int1_n60 - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(DISTINCT int1_n60) keys: int1_n60 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: sum(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -83,32 +83,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n60 - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: int1_n60 (type: int) outputColumnNames: int1_n60 - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(DISTINCT int1_n60) keys: int1_n60 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: sum(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out b/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out index cb6a647dde..15b6cb039a 100644 --- a/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out +++ b/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out @@ -15,35 +15,35 @@ STAGE PLANS: TableScan alias: src Row Limit Per Split: 10 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), '' (type: string), '' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 63750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), '' (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), '' (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 63750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), '' (type: string), '' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 63750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), '' (type: string), '' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 63750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 63750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -94,35 +94,35 @@ STAGE PLANS: TableScan alias: src Row Limit Per Split: 10 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), 'X' (type: string), 'X' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 64250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), 'X' (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), 'X' (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 64250 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), 'X' (type: string), 'X' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 64250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), 'X' (type: string), 'X' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 64250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 64250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -197,22 +197,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max('pants'), max('pANTS') keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 113750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 113750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized @@ -222,17 +222,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 113750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_id3.q.out b/ql/src/test/results/clientpositive/groupby_grouping_id3.q.out index 018c7da321..f7b60f835b 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_id3.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_id3.q.out @@ -38,25 +38,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n86 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col2 = 1L) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), 1L (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), 1L (type: bigint) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -64,15 +64,15 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), 1L (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: int), _col1 (type: int), 1L (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -128,22 +128,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n86 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -151,17 +151,17 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col2 = 1L) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), 1L (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets1.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets1.q.out index 5eda07637f..587cae9391 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets1.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets1.q.out @@ -46,22 +46,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n41 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -69,15 +69,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -130,22 +130,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n41 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -153,15 +153,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -214,22 +214,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n41 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -237,15 +237,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -298,22 +298,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n41 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -321,15 +321,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -378,35 +378,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n41 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) outputColumnNames: a, b, c - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - Statistics: Num rows: 3 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -458,30 +458,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n41 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string) outputColumnNames: a - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -524,22 +524,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n41 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(a) + UDFToDouble(b)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -547,10 +547,10 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out index 196d9b6864..6b972c1dfd 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets2.q.out @@ -32,22 +32,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n81 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -55,7 +55,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -71,7 +71,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -79,15 +79,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -117,22 +117,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n81 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -140,7 +140,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -156,7 +156,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -164,15 +164,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -226,22 +226,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n81 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) outputColumnNames: a, b, c - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(c) keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double) Reduce Operator Tree: Group By Operator @@ -249,7 +249,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -265,7 +265,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: double) Reduce Operator Tree: Group By Operator @@ -273,15 +273,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -358,22 +358,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n50 - Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: string), b (type: string), (c + d) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -381,7 +381,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 24 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -397,7 +397,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 24 Data size: 168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -405,15 +405,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out index 8ad784cd8b..4051789e24 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets3.q.out @@ -39,22 +39,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n118 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) outputColumnNames: a, b, c - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(c), count(c), count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4 Data size: 2880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 2880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: double), _col4 (type: bigint), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -62,15 +62,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: double), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -99,22 +99,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n118 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) outputColumnNames: a, b, c - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(c), count(c), count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4 Data size: 2880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 2880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: double), _col4 (type: bigint), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -122,15 +122,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: double), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -185,22 +185,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n118 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) outputColumnNames: a, b, c - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(c), count(c), count() keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint) Reduce Operator Tree: Group By Operator @@ -208,7 +208,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4 Data size: 2880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -224,7 +224,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 2880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: double), _col4 (type: bigint), _col5 (type: bigint) Reduce Operator Tree: Group By Operator @@ -232,15 +232,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: double), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out index 02da8fcff6..8b917dbbb6 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out @@ -41,21 +41,21 @@ STAGE PLANS: TableScan alias: t1_n143 filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -63,15 +63,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -87,14 +87,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -104,10 +104,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 792 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 792 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -119,21 +119,21 @@ STAGE PLANS: TableScan alias: t1_n143 filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -141,15 +141,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -190,21 +190,21 @@ STAGE PLANS: TableScan alias: t1_n143 filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -212,15 +212,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -236,14 +236,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -253,10 +253,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 792 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 792 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -268,21 +268,21 @@ STAGE PLANS: TableScan alias: t1_n143 filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -290,15 +290,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -370,21 +370,21 @@ STAGE PLANS: TableScan alias: t1_n143 filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -392,7 +392,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -408,7 +408,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -416,15 +416,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -440,14 +440,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -457,10 +457,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 792 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 792 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -472,21 +472,21 @@ STAGE PLANS: TableScan alias: t1_n143 filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) < 3.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -494,7 +494,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -510,7 +510,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -518,15 +518,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out index b6754dbe7c..11175532b0 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets5.q.out @@ -33,33 +33,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n24 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -75,7 +75,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -83,15 +83,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -122,33 +122,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n24 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -164,7 +164,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -172,15 +172,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -237,33 +237,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n24 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string), b (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -279,7 +279,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -287,7 +287,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -303,7 +303,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -311,15 +311,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out index 38c1cb0a17..80e8bb730b 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets6.q.out @@ -34,30 +34,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n75 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) = 5.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -103,30 +103,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n75 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(a) = 5.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out index d5945eaa0f..ab21e3f17f 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets_grouping.q.out @@ -34,34 +34,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1) (type: bigint), grouping(_col2, 0) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -116,34 +116,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1) (type: bigint), grouping(_col2, 0) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -205,37 +205,37 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (grouping(_col2, 1) = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -292,34 +292,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((grouping(_col2, 0) = 1) or (grouping(_col2, 1) = 1)) (type: boolean) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: bigint), CASE WHEN (((grouping(_col2, 1) + grouping(_col2, 0)) = 1)) THEN (_col0) ELSE (null) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -334,16 +334,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col2 (type: bigint), _col3 (type: int) sort order: -+ - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -401,34 +401,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L) (type: bigint), grouping(_col2, 0L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -483,34 +483,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L) (type: bigint), grouping(_col2, 0L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -572,34 +572,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (grouping(_col2, 1L) = 1) (type: boolean) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -656,34 +656,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((grouping(_col2, 0L) = 1) or (grouping(_col2, 1L) = 1)) (type: boolean) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1L) + grouping(_col2, 0L)) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -698,16 +698,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col2 (type: bigint), CASE WHEN ((_col2 = 1L)) THEN (_col0) END (type: int) sort order: -+ - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -765,34 +765,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), 0L (type: bigint), 0L (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -842,34 +842,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), 0L (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -921,30 +921,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -996,34 +996,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L, 0L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1083,34 +1083,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 0L, 1L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1170,34 +1170,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L, 0L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1252,34 +1252,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n64 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int), value (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 0L, 1L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_sets_limit.q.out b/ql/src/test/results/clientpositive/groupby_grouping_sets_limit.q.out index 241dfb987e..269f88408a 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_sets_limit.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_sets_limit.q.out @@ -30,22 +30,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n141 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint) Execution mode: vectorized @@ -55,18 +55,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -112,22 +112,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n141 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint) Execution mode: vectorized @@ -137,18 +137,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -194,22 +194,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n141 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: a, b - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: a (type: string), b (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint) Execution mode: vectorized @@ -219,18 +219,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -276,21 +276,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n141 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string) outputColumnNames: a, b, c - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - Statistics: Num rows: 3 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1656 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -298,18 +298,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -355,21 +355,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n141 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string) outputColumnNames: a - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: a (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -377,13 +377,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -424,22 +424,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n141 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(a) + UDFToDouble(b)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -449,13 +449,13 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_grouping_window.q.out b/ql/src/test/results/clientpositive/groupby_grouping_window.q.out index f50b8dc662..3a89233430 100644 --- a/ql/src/test/results/clientpositive/groupby_grouping_window.q.out +++ b/ql/src/test/results/clientpositive/groupby_grouping_window.q.out @@ -42,22 +42,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n33 - Statistics: Num rows: 3 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: category (type: int), live (type: int), comments (type: int) outputColumnNames: category, live, comments - Statistics: Num rows: 3 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(live), max(comments) keys: category (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: bigint) - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -66,11 +66,11 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 3 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Filter Operator predicate: (_col3 > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -86,14 +86,14 @@ STAGE PLANS: key expressions: _col0 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -114,14 +114,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out b/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out index d99657b02f..276179acc5 100644 --- a/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out +++ b/ql/src/test/results/clientpositive/groupby_join_pushdown.q.out @@ -21,25 +21,25 @@ STAGE PLANS: TableScan alias: f filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -48,7 +48,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -64,14 +64,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -81,14 +81,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string), (_col1 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -100,25 +100,25 @@ STAGE PLANS: TableScan alias: g filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -127,7 +127,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -164,31 +164,31 @@ STAGE PLANS: TableScan alias: f filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -204,13 +204,13 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -219,10 +219,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -234,31 +234,31 @@ STAGE PLANS: TableScan alias: g filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -293,31 +293,31 @@ STAGE PLANS: TableScan alias: f filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -333,13 +333,13 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -348,10 +348,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -363,31 +363,31 @@ STAGE PLANS: TableScan alias: g filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -424,25 +424,25 @@ STAGE PLANS: TableScan alias: f filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -451,7 +451,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -467,14 +467,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -484,14 +484,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string), (_col1 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -503,25 +503,25 @@ STAGE PLANS: TableScan alias: g filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -530,7 +530,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -566,36 +566,36 @@ STAGE PLANS: TableScan alias: f filterExpr: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146784 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), cbigint (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col2 (type: bigint) TableScan alias: g filterExpr: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint) Reduce Operator Tree: Join Operator @@ -605,13 +605,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18464 Data size: 258240 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col0 (type: tinyint), _col3 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9232 Data size: 138416 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -627,7 +627,7 @@ STAGE PLANS: key expressions: _col0 (type: tinyint), _col1 (type: tinyint) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: tinyint) - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9232 Data size: 138416 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -636,10 +636,10 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9232 Data size: 138416 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9232 Data size: 138416 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -674,25 +674,25 @@ STAGE PLANS: TableScan alias: f filterExpr: cbigint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110088 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cbigint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cbigint (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col0) keys: _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 44076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 44076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -701,7 +701,7 @@ STAGE PLANS: keys: KEY._col0 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 44076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -717,14 +717,14 @@ STAGE PLANS: key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 44076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 26400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -733,14 +733,14 @@ STAGE PLANS: 0 _col0 (type: bigint) 1 _col0 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4420 Data size: 70496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col2 (type: bigint), _col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4420 Data size: 70496 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4420 Data size: 70496 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -752,31 +752,31 @@ STAGE PLANS: TableScan alias: g filterExpr: cbigint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cbigint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 26400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 26400 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: bigint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4419 Data size: 26400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -813,25 +813,25 @@ STAGE PLANS: TableScan alias: f filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col0) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint) Execution mode: vectorized Reduce Operator Tree: @@ -840,7 +840,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -856,14 +856,14 @@ STAGE PLANS: key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint) TableScan Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -872,14 +872,14 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: tinyint), _col2 (type: tinyint), _col1 (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1008 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -891,31 +891,31 @@ STAGE PLANS: TableScan alias: g filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -952,25 +952,25 @@ STAGE PLANS: TableScan alias: f filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col1) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -979,7 +979,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -995,14 +995,14 @@ STAGE PLANS: key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1011,14 +1011,14 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col1 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1030,31 +1030,31 @@ STAGE PLANS: TableScan alias: g filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1091,25 +1091,25 @@ STAGE PLANS: TableScan alias: f filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1118,7 +1118,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1134,14 +1134,14 @@ STAGE PLANS: key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -1151,14 +1151,14 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col1, _col3 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col1 * _col3) (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1170,25 +1170,25 @@ STAGE PLANS: TableScan alias: g filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1197,7 +1197,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1234,25 +1234,25 @@ STAGE PLANS: TableScan alias: f filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1261,7 +1261,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1277,14 +1277,14 @@ STAGE PLANS: key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -1294,14 +1294,14 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col1 * _col3) (type: bigint), _col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1313,25 +1313,25 @@ STAGE PLANS: TableScan alias: g filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1340,7 +1340,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1377,25 +1377,25 @@ STAGE PLANS: TableScan alias: f filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1404,7 +1404,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1420,14 +1420,14 @@ STAGE PLANS: key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -1437,14 +1437,14 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1904 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col1 * _col3) (type: bigint), _col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1456,25 +1456,25 @@ STAGE PLANS: TableScan alias: g filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1483,7 +1483,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 99 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1522,29 +1522,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: f - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: g - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1553,13 +1553,13 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1161499 Data size: 13900620 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: tinyint), _col2 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17161 Data size: 274216 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1575,7 +1575,7 @@ STAGE PLANS: key expressions: _col0 (type: tinyint), _col1 (type: tinyint) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: tinyint) - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17161 Data size: 274216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1584,14 +1584,14 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17161 Data size: 274216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint), _col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17161 Data size: 205752 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17161 Data size: 205752 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1633,36 +1633,36 @@ STAGE PLANS: TableScan alias: f filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: g filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1671,13 +1671,13 @@ STAGE PLANS: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 858611 Data size: 10275444 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: tinyint), _col2 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9801 Data size: 156608 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1693,7 +1693,7 @@ STAGE PLANS: key expressions: _col0 (type: tinyint), _col1 (type: tinyint) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: tinyint) - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9801 Data size: 156608 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1702,14 +1702,14 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9801 Data size: 156608 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint), _col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9801 Data size: 117508 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9801 Data size: 117508 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_map_ppr.q.out b/ql/src/test/results/clientpositive/groupby_map_ppr.q.out index fd4fd47671..7514c79260 100644 --- a/ql/src/test/results/clientpositive/groupby_map_ppr.q.out +++ b/ql/src/test/results/clientpositive/groupby_map_ppr.q.out @@ -33,24 +33,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col1), sum(_col1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 192000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 192000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col3 (type: double) auto parallelism: false @@ -165,17 +165,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 63200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -206,12 +206,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) outputColumnNames: key, c1, c2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -278,7 +278,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -316,13 +316,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out index cd5d59007f..e6a8fa8c8a 100644 --- a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out @@ -33,24 +33,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col1), sum(_col1), sum(DISTINCT _col1), count(DISTINCT _col2) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 491000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 491000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col4 (type: double) auto parallelism: false @@ -165,17 +165,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -206,12 +206,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -278,7 +278,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 2168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2152 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) auto parallelism: false @@ -316,13 +316,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 2216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out b/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out index e01aa07f2f..5555e3f318 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_insert_common_distinct.q.out @@ -40,32 +40,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value) keys: (key + key) (type: double), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -78,14 +78,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -94,12 +94,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -131,7 +131,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -139,10 +139,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -164,7 +164,7 @@ STAGE PLANS: key expressions: _col0 (type: double), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -172,14 +172,14 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -188,12 +188,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -217,7 +217,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 856 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -225,10 +225,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out index c13665b3a9..c4afddbf9a 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer.q.out @@ -65,34 +65,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: substr(key, 1, 1) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -100,20 +100,20 @@ STAGE PLANS: name: default.dest_g4 Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -121,20 +121,20 @@ STAGE PLANS: name: default.dest_g2 Filter Operator predicate: (KEY._col0 < 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -297,21 +297,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) sort order: ++ Map-reduce partition columns: substr(key, 1, 1) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -321,20 +321,20 @@ STAGE PLANS: Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -342,20 +342,20 @@ STAGE PLANS: name: default.dest_g4 Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -363,20 +363,20 @@ STAGE PLANS: name: default.dest_g2 Filter Operator predicate: (KEY._col0 < 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 22680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 39900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -433,22 +433,22 @@ STAGE PLANS: key expressions: substr(key, 1, 1) (type: string), substr(key, 2, 1) (type: string), substr(value, 5) (type: string) sort order: +++ Map-reduce partition columns: substr(key, 1, 1) (type: string), substr(key, 2, 1) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0), sum(KEY._col2:0._col0), count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: bigint), concat(_col0, _col3) (type: string), _col3 (type: double), _col4 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -457,20 +457,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 76194 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0), sum(KEY._col2:0._col0), count(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 65072 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col2) (type: int), concat(_col0, _col3) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 63080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 63080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -484,7 +484,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: string), _col3 (type: double), _col4 (type: bigint) Execution mode: vectorized @@ -492,17 +492,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: string), VALUE._col1 (type: double), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 196000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out index cb74a38adb..2174edb9da 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer2.q.out @@ -40,36 +40,36 @@ STAGE PLANS: TableScan alias: src filterExpr: ((substr(key, 1, 1) < 5) or (substr(key, 1, 1) >= 5)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((substr(key, 1, 1) < 5) or (substr(key, 1, 1) >= 5)) (type: boolean) - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(key, 1, 1) (type: string), key (type: string) sort order: ++ Map-reduce partition columns: substr(key, 1, 1) (type: string) - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 30250 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 19740 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 19740 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -78,12 +78,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, c1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 19740 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -92,20 +92,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 < 5) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 30250 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 21000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -114,12 +114,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) outputColumnNames: key, c1, c2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 20160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -151,7 +151,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -159,10 +159,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -192,7 +192,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -200,10 +200,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out index 53ddde0809..c871ca2c5f 100644 --- a/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out +++ b/ql/src/test/results/clientpositive/groupby_multi_single_reducer3.q.out @@ -52,35 +52,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (((value) IN ('val_400', 'val_500') and (key) IN (400, 450)) or ((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200)) or ((value) IN ('val_400', 'val_500') and (key) IN (400, 450))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((KEY._col0) IN (100, 150, 200) and (VALUE._col0) IN ('val_100', 'val_200', 'val_300')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -89,12 +89,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -103,20 +103,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((KEY._col0) IN (400, 450) and (VALUE._col0) IN ('val_400', 'val_500')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -125,12 +125,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -162,7 +162,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -170,10 +170,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -203,7 +203,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -211,10 +211,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -307,36 +307,36 @@ STAGE PLANS: TableScan alias: src filterExpr: ((((key + key) = 400) or (((key - 100) = 500) and value is not null)) or (((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null)) or (((key + key) = 400) or (((key - 100) = 500) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -345,12 +345,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -359,20 +359,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((((VALUE._col0 - 100) = 500) and KEY._col0 is not null) or ((VALUE._col0 + VALUE._col0) = 400)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -381,12 +381,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -418,7 +418,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -426,10 +426,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -459,7 +459,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -467,10 +467,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -562,35 +562,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value) IN ('val_100', 'val_200', 'val_300') and (key) IN (100, 150, 200)) or ((value) IN ('val_400', 'val_500') and (key) IN (400, 450))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((KEY._col0) IN (100, 150, 200) and (VALUE._col0) IN ('val_100', 'val_200', 'val_300')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -599,12 +599,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -613,20 +613,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((KEY._col0) IN (400, 450) and (VALUE._col0) IN ('val_400', 'val_500')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -635,12 +635,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -672,7 +672,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -680,10 +680,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -713,7 +713,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -721,10 +721,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -816,36 +816,36 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((key + key) = 200) or ((key - 100) = 100) or ((key = 300) and value is not null)) or (((key + key) = 400) or (((key - 100) = 500) and value is not null))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((VALUE._col0 + VALUE._col0) = 200) or ((VALUE._col0 - 100) = 100) or ((VALUE._col0 = 300) and KEY._col0 is not null)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -854,12 +854,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -868,20 +868,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((((VALUE._col0 - 100) = 500) and KEY._col0 is not null) or ((VALUE._col0 + VALUE._col0) = 400)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -890,12 +890,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -927,7 +927,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -935,10 +935,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -968,7 +968,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -976,10 +976,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_multialias.q.out b/ql/src/test/results/clientpositive/groupby_multialias.q.out index 1b15ef0635..0622363a76 100644 --- a/ql/src/test/results/clientpositive/groupby_multialias.q.out +++ b/ql/src/test/results/clientpositive/groupby_multialias.q.out @@ -26,22 +26,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n150 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: a - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(a) keys: a (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -50,10 +50,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_position.q.out b/ql/src/test/results/clientpositive/groupby_position.q.out index 86a2dcba7d..b4ea66fd83 100644 --- a/ql/src/test/results/clientpositive/groupby_position.q.out +++ b/ql/src/test/results/clientpositive/groupby_position.q.out @@ -40,30 +40,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 20) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 20) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), value (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -76,14 +76,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -92,12 +92,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -129,7 +129,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -137,10 +137,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -162,7 +162,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -170,14 +170,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -186,12 +186,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -215,7 +215,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -223,10 +223,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -319,30 +319,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 20) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 20) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(value, 5)) keys: value (type: string), key (type: string), substr(value, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -355,14 +355,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -371,12 +371,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -408,7 +408,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -416,10 +416,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,7 +441,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -449,14 +449,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col1) (type: int), _col0 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -465,12 +465,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -494,7 +494,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -502,10 +502,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -594,21 +594,21 @@ STAGE PLANS: TableScan alias: b filterExpr: (UDFToDouble(key) <= 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) <= 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -617,7 +617,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -632,16 +632,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: string) sort order: -+ - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -725,27 +725,27 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -761,14 +761,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -778,7 +778,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -793,16 +793,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: --++ - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -814,27 +814,27 @@ STAGE PLANS: TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -901,24 +901,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1455,28 +1455,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1491,16 +1491,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_ppd.q.out b/ql/src/test/results/clientpositive/groupby_ppd.q.out index daebac40b0..a4355a3340 100644 --- a/ql/src/test/results/clientpositive/groupby_ppd.q.out +++ b/ql/src/test/results/clientpositive/groupby_ppd.q.out @@ -21,62 +21,62 @@ STAGE PLANS: TableScan alias: c filterExpr: (bar = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (bar = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE TableScan alias: d filterExpr: (bar = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (bar = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_ppr.q.out b/ql/src/test/results/clientpositive/groupby_ppr.q.out index d3484eb022..123c132e1f 100644 --- a/ql/src/test/results/clientpositive/groupby_ppr.q.out +++ b/ql/src/test/results/clientpositive/groupby_ppr.q.out @@ -33,18 +33,18 @@ STAGE PLANS: TableScan alias: src filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -159,17 +159,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 63200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -200,7 +200,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) outputColumnNames: key, c1, c2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -267,7 +267,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: key (type: string), c1 (type: int), c2 (type: string) auto parallelism: false @@ -305,13 +305,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out index 530e797e1b..b1875be1b1 100644 --- a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out @@ -33,18 +33,18 @@ STAGE PLANS: TableScan alias: src filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -159,17 +159,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -200,7 +200,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -267,7 +267,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: key (type: string), c1 (type: int), c2 (type: string), c3 (type: int), c4 (type: int) auto parallelism: false @@ -305,13 +305,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll'), compute_stats(VALUE._col4, 'hll'), compute_stats(VALUE._col5, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -399,18 +399,18 @@ STAGE PLANS: TableScan alias: src filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string) outputColumnNames: $f0, $f1, $f2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 459000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: $f0 (type: string), $f1 (type: string), $f2 (type: string) null sort order: aaa sort order: +++ Map-reduce partition columns: $f0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 459000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -525,17 +525,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: $f0, $f1, $f2, $f3, $f4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string), UDFToInteger($f3) (type: int), UDFToInteger($f4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -566,7 +566,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key, c1, c2, c3, c4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -633,7 +633,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: key (type: string), c1 (type: int), c2 (type: string), c3 (type: int), c4 (type: int) auto parallelism: false @@ -671,17 +671,17 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll'), compute_stats(VALUE._col4, 'hll'), compute_stats(VALUE._col5, 'hll') mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 2232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/groupby_rollup1.q.out b/ql/src/test/results/clientpositive/groupby_rollup1.q.out index 5f9d2d5691..5ea5ba9b81 100644 --- a/ql/src/test/results/clientpositive/groupby_rollup1.q.out +++ b/ql/src/test/results/clientpositive/groupby_rollup1.q.out @@ -30,22 +30,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n91 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -53,15 +53,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -109,37 +109,37 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n91 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT val) keys: key (type: string), 0L (type: bigint), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0) keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -182,22 +182,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n91 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -205,7 +205,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -221,7 +221,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -229,15 +229,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -286,29 +286,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n91 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT val) keys: key (type: string), 0L (type: bigint), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col2:0._col0) keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -324,7 +324,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -332,15 +332,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: final outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -410,33 +410,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n91 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(1) keys: key (type: string), val (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -449,7 +449,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -465,7 +465,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -473,15 +473,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -490,12 +490,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key1, key2, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(val, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -527,17 +527,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -559,7 +559,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -567,7 +567,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: partials outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -583,7 +583,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -591,15 +591,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: final outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -608,12 +608,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key1, key2, val - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(val, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -637,17 +637,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out b/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out index 06dc2b3ef1..6a4ba8181a 100644 --- a/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out +++ b/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out @@ -160,25 +160,25 @@ STAGE PLANS: TableScan alias: tx2_n1 filterExpr: (a < 0) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (a < 0) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col2) keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -187,14 +187,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col3 (type: bigint), grouping(_col2, 0) (type: bigint), 'NULL,1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_10.q.out b/ql/src/test/results/clientpositive/groupby_sort_10.q.out index f0d91feae9..82d3d2305c 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_10.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_10.q.out @@ -34,19 +34,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n149 - Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -97,32 +97,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n149 - Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 680 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 680 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_11.q.out b/ql/src/test/results/clientpositive/groupby_sort_11.q.out index e5931bd9bc..86fdb9d112 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_11.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_11.q.out @@ -34,32 +34,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n18 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT key) bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -96,32 +96,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n18 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT key), count(), count(key), sum(DISTINCT key) bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: double) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), sum(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -158,23 +158,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n18 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT key), count(), count(key), sum(DISTINCT key) bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -182,14 +182,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -231,23 +231,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n18 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT key), count(), count(key), sum(DISTINCT key) bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -255,10 +255,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -301,32 +301,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n18 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: double) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -340,17 +340,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -387,28 +387,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n18 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT 1) keys: 1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -445,24 +445,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n18 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out b/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out index 033d00b886..3bb1cae52e 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out @@ -61,28 +61,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -113,16 +113,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -189,13 +189,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -503,24 +503,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -589,17 +589,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -630,12 +630,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: key1, key2, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -702,7 +702,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1656 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -740,13 +740,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -818,28 +818,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -870,16 +870,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -946,13 +946,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1256,28 +1256,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1308,16 +1308,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -1384,13 +1384,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1702,28 +1702,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int), UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1754,16 +1754,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key1, key2, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -1830,13 +1830,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2145,24 +2145,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -2231,17 +2231,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2272,12 +2272,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -2344,7 +2344,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -2382,13 +2382,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2128 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2128 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2457,24 +2457,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -2543,17 +2543,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2584,12 +2584,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key1, key2, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -2656,7 +2656,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -2694,13 +2694,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2771,34 +2771,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(_col0) + UDFToDouble(_col0)) (type: double), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -2867,17 +2867,17 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2908,12 +2908,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -2980,7 +2980,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -3018,13 +3018,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3110,30 +3110,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3164,45 +3164,45 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3233,16 +3233,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -3309,13 +3309,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3645,24 +3645,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -3731,11 +3731,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -3760,30 +3760,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n80 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3814,33 +3814,33 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false TableScan GatherStats: false Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3871,16 +3871,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -3970,13 +3970,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4304,48 +4304,48 @@ STAGE PLANS: TableScan alias: t1_n80 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: bigint) auto parallelism: false TableScan alias: t1_n80 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -4415,17 +4415,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger((_col1 + _col3)) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4456,7 +4456,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash @@ -4658,24 +4658,24 @@ STAGE PLANS: TableScan alias: t1_n80 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -4744,7 +4744,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -4770,24 +4770,24 @@ STAGE PLANS: TableScan alias: t1_n80 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: bigint) auto parallelism: false @@ -4798,7 +4798,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string), _col2 (type: bigint) auto parallelism: false @@ -4891,13 +4891,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4964,25 +4964,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n49 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -5051,17 +5051,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -5092,12 +5092,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -5164,7 +5164,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -5202,13 +5202,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -5278,28 +5278,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n49 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -5330,16 +5330,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -5406,13 +5406,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -5727,28 +5727,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n49 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), 2 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -5779,16 +5779,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key1, key2, key3, key4, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(key4, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) auto parallelism: false @@ -5855,13 +5855,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -6175,28 +6175,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n49 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -6227,16 +6227,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -6303,13 +6303,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -6630,28 +6630,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n49 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 2 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -6682,16 +6682,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -6758,13 +6758,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -7095,41 +7095,41 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n49 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7138,12 +7138,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7156,14 +7156,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7172,12 +7172,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7209,7 +7209,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -7217,10 +7217,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7250,7 +7250,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -7258,10 +7258,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7339,44 +7339,44 @@ STAGE PLANS: TableScan alias: t2_n49 filterExpr: (UDFToDouble(key) = 8.0D) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 8.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 513 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 513 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 513 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) bucketGroup: true keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Group By Operator aggregations: count(1) keys: _col0 (type: string), _col1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7385,12 +7385,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7403,14 +7403,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7419,12 +7419,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7456,7 +7456,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -7464,10 +7464,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7497,7 +7497,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -7505,10 +7505,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_2.q.out b/ql/src/test/results/clientpositive/groupby_sort_2.q.out index d75dafd8c9..a3af018a01 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_2.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_2.q.out @@ -54,23 +54,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n51 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val (type: string) outputColumnNames: val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() bucketGroup: true keys: val (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -79,14 +79,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -95,12 +95,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -132,7 +132,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -140,10 +140,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_3.q.out b/ql/src/test/results/clientpositive/groupby_sort_3.q.out index 2054597037..6a6e17759b 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_3.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_3.q.out @@ -58,24 +58,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n89 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -84,25 +84,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -224,24 +224,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n89 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -250,25 +250,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_4.q.out b/ql/src/test/results/clientpositive/groupby_sort_4.q.out index 043d51b5a2..6d16985683 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_4.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_4.q.out @@ -54,23 +54,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n133 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -79,14 +79,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -95,12 +95,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -132,7 +132,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -140,10 +140,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -202,22 +202,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n133 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -226,14 +226,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -242,12 +242,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -279,7 +279,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -287,10 +287,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_5.q.out b/ql/src/test/results/clientpositive/groupby_sort_5.q.out index 04b9ceee3b..c4e704a6b0 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_5.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_5.q.out @@ -58,24 +58,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n6 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -84,25 +84,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -252,24 +252,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n6 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -278,25 +278,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -450,23 +450,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n6 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -475,14 +475,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -491,12 +491,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -528,7 +528,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -536,10 +536,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_6.q.out b/ql/src/test/results/clientpositive/groupby_sort_6.q.out index bc31a57182..0ebf179313 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_6.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_6.q.out @@ -39,28 +39,28 @@ STAGE PLANS: TableScan alias: t1_n61 filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (ds = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -72,17 +72,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -113,12 +113,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -185,7 +185,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -223,13 +223,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -301,28 +301,28 @@ STAGE PLANS: TableScan alias: t1_n61 filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (ds = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -334,17 +334,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -375,12 +375,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -447,7 +447,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -485,13 +485,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -554,24 +554,24 @@ STAGE PLANS: TableScan alias: t1_n61 filterExpr: (ds = '2') (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -635,17 +635,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -676,12 +676,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 1 Data size: 300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 484 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -748,7 +748,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: PARTIAL Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -786,13 +786,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_7.q.out b/ql/src/test/results/clientpositive/groupby_sort_7.q.out index 7c407dbdb0..abbcb7e1ab 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_7.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_7.q.out @@ -62,24 +62,24 @@ STAGE PLANS: TableScan alias: t1_n104 filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2232 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2232 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -88,25 +88,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1116 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1672 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_8.q.out b/ql/src/test/results/clientpositive/groupby_sort_8.q.out index fabca6eac5..c06826a6f7 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_8.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_8.q.out @@ -45,32 +45,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n45 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT key) bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_9.q.out b/ql/src/test/results/clientpositive/groupby_sort_9.q.out index 595e1470ce..ed1d0548e9 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_9.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_9.q.out @@ -57,23 +57,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n96 - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2256 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -82,10 +82,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out b/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out index 1eddcf57c7..08800c8d18 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out @@ -61,28 +61,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -113,16 +113,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -189,13 +189,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -504,24 +504,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -590,7 +590,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: partials outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -620,7 +620,7 @@ STAGE PLANS: null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -659,17 +659,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -700,12 +700,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: key1, key2, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -772,7 +772,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1656 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -810,13 +810,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -888,28 +888,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -940,16 +940,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -1016,13 +1016,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1326,28 +1326,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1378,16 +1378,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -1454,13 +1454,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1772,28 +1772,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 1 (type: int), UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1824,16 +1824,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key1, key2, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -1900,13 +1900,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2216,24 +2216,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -2302,7 +2302,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: partials outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -2332,7 +2332,7 @@ STAGE PLANS: null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -2371,17 +2371,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2412,12 +2412,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -2484,7 +2484,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -2522,13 +2522,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: final outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2128 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2128 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2598,24 +2598,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double) null sort order: aa sort order: ++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -2684,7 +2684,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double) mode: partials outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -2714,7 +2714,7 @@ STAGE PLANS: null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -2753,17 +2753,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2794,12 +2794,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key1, key2, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -2866,7 +2866,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -2904,13 +2904,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1504 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2982,34 +2982,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(_col0) + UDFToDouble(_col0)) (type: double), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) null sort order: a sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -3078,7 +3078,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -3108,7 +3108,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -3147,17 +3147,17 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(CAST( _col0 AS STRING)) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3188,12 +3188,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -3260,7 +3260,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -3298,13 +3298,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3390,30 +3390,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3444,45 +3444,45 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3513,16 +3513,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -3589,13 +3589,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3926,24 +3926,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: (UDFToDouble(key) + UDFToDouble(key)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) null sort order: a sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -4012,7 +4012,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -4042,7 +4042,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -4081,11 +4081,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( _col0 AS STRING) (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -4110,30 +4110,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n56 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4164,33 +4164,33 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false TableScan GatherStats: false Union - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4221,16 +4221,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -4320,13 +4320,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4654,48 +4654,48 @@ STAGE PLANS: TableScan alias: t1_n56 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: bigint) auto parallelism: false TableScan alias: t1_n56 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -4765,17 +4765,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger((_col1 + _col3)) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4806,7 +4806,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash @@ -5009,24 +5009,24 @@ STAGE PLANS: TableScan alias: t1_n56 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -5095,7 +5095,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: partials outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -5125,7 +5125,7 @@ STAGE PLANS: null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: bigint) auto parallelism: false @@ -5164,7 +5164,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -5190,24 +5190,24 @@ STAGE PLANS: TableScan alias: t1_n56 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: bigint) auto parallelism: false @@ -5218,7 +5218,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string), _col2 (type: bigint) auto parallelism: false @@ -5311,13 +5311,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 607 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -5385,25 +5385,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n34 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -5472,7 +5472,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -5502,7 +5502,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -5541,17 +5541,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -5582,12 +5582,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -5654,7 +5654,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -5692,13 +5692,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -5768,28 +5768,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n34 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -5820,16 +5820,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -5896,13 +5896,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: final outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -6217,28 +6217,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n34 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), 2 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -6269,16 +6269,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int) outputColumnNames: key1, key2, key3, key4, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 612 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(key4, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) auto parallelism: false @@ -6345,13 +6345,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: final outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -6665,28 +6665,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n34 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 1 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -6717,16 +6717,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -6793,13 +6793,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: final outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -7120,28 +7120,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n34 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), 2 (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -7172,16 +7172,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) outputColumnNames: key1, key2, key3, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(key3, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -7248,13 +7248,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: final outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -7586,41 +7586,41 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n34 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) bucketGroup: true keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: key (type: string), val (type: string) outputColumnNames: key, val - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7629,12 +7629,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7647,7 +7647,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7663,7 +7663,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -7672,14 +7672,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7688,12 +7688,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7725,7 +7725,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -7733,10 +7733,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7766,7 +7766,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -7774,10 +7774,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7856,44 +7856,44 @@ STAGE PLANS: TableScan alias: t2_n34 filterExpr: (UDFToDouble(key) = 8.0D) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 8.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 513 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 513 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 513 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) bucketGroup: true keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Group By Operator aggregations: count(1) keys: _col0 (type: string), _col1 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7902,12 +7902,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: key, val, cnt - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7920,7 +7920,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7936,7 +7936,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -7945,14 +7945,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -7961,12 +7961,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true table: @@ -7998,7 +7998,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -8006,10 +8006,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -8039,7 +8039,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -8047,10 +8047,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: true - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out b/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out index dbd9c1225a..db13a7c5b3 100644 --- a/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out +++ b/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out @@ -58,24 +58,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n164 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -84,25 +84,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1032 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/having.q.out b/ql/src/test/results/clientpositive/having.q.out index baaca58661..b540a7c27d 100644 --- a/ql/src/test/results/clientpositive/having.q.out +++ b/ql/src/test/results/clientpositive/having.q.out @@ -12,22 +12,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -36,21 +36,21 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint) outputColumnNames: _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 3L) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -95,21 +95,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) <> 302.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) <> 302.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -118,10 +118,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -463,22 +463,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -487,17 +487,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 'val_255') (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -731,21 +731,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 300.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 300.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -754,17 +754,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 'val_255') (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2349 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2349 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -923,22 +923,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -947,13 +947,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 'val_255') (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1186,22 +1186,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1210,13 +1210,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 >= 4L) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/having2.q.out b/ql/src/test/results/clientpositive/having2.q.out index a63c659782..764378b002 100644 --- a/ql/src/test/results/clientpositive/having2.q.out +++ b/ql/src/test/results/clientpositive/having2.q.out @@ -130,22 +130,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: order_quantity (type: double), discount (type: double), customer_name (type: string), customer_balance (type: double) outputColumnNames: order_quantity, discount, customer_name, customer_balance - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(customer_balance), sum(order_quantity), count(discount) keys: customer_name (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -154,17 +154,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 <= 4074689.000000041D) and (_col3 <= 822L)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -198,22 +198,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: order_quantity (type: double), discount (type: double), customer_name (type: string), customer_balance (type: double) outputColumnNames: order_quantity, discount, customer_name, customer_balance - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(customer_balance), sum(order_quantity), count(discount) keys: customer_name (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -222,17 +222,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 <= 4074689.000000041D) and (_col3 <= 822L)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -274,36 +274,36 @@ STAGE PLANS: TableScan alias: s1 filterExpr: customer_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: customer_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: discount (type: double), customer_name (type: string), customer_balance (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: double), _col2 (type: double) TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -313,13 +313,13 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col2), sum(_col0), count(_col0), count(_col4) keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -335,7 +335,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -344,17 +344,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 48950 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col2 / _col3) <= 822.0D) and (_col1 <= 4074689.000000041D) and (_col4 > 4L)) (type: boolean) - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -396,36 +396,36 @@ STAGE PLANS: TableScan alias: s1 filterExpr: customer_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: customer_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: discount (type: double), customer_name (type: string), customer_balance (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: double), _col2 (type: double) TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -435,13 +435,13 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col2), sum(_col0), count(_col0), count(_col4) keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -457,7 +457,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -466,21 +466,21 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 48950 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 48950 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col3 / _col4) <= 822.0D) and (_col2 <= 4074689.000000041D) and (_col5 > 4L)) (type: boolean) - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -522,36 +522,36 @@ STAGE PLANS: TableScan alias: s1 filterExpr: customer_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: customer_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: discount (type: double), customer_name (type: string), customer_balance (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: double), _col2 (type: double) TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -561,13 +561,13 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col2), sum(_col0), count(_col0), count(_col4) keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -583,7 +583,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -592,21 +592,21 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 48950 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 275 Data size: 2921 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 275 Data size: 48950 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((_col3 / _col4) <= 822.0D) and (_col2 <= 4074689.000000041D) and (_col5 > 4L)) (type: boolean) - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 106 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/hll.q.out b/ql/src/test/results/clientpositive/hll.q.out index 4b445eadf3..4e1c54357e 100644 --- a/ql/src/test/results/clientpositive/hll.q.out +++ b/ql/src/test/results/clientpositive/hll.q.out @@ -29,29 +29,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: n - Statistics: Num rows: 500 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 500 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,29 +125,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: i - Statistics: Num rows: 500 Data size: 1406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 500 Data size: 1406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out b/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out index a4908fceb1..692f89669e 100644 --- a/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out +++ b/ql/src/test/results/clientpositive/identity_project_remove_skip.q.out @@ -33,12 +33,12 @@ STAGE PLANS: TableScan alias: src filterExpr: ((value = 'val_105') and (key = '105')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = '105') and (value = 'val_105')) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 '105' (type: string) @@ -50,26 +50,26 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '105') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '105') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 '105' (type: string) 1 '105' (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '105' (type: string), 'val_105' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/implicit_cast1.q.out b/ql/src/test/results/clientpositive/implicit_cast1.q.out index d7d7b8c65a..604e2b2ed6 100644 --- a/ql/src/test/results/clientpositive/implicit_cast1.q.out +++ b/ql/src/test/results/clientpositive/implicit_cast1.q.out @@ -27,17 +27,17 @@ STAGE PLANS: TableScan alias: implicit_test1 filterExpr: (a <> 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (a <> 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: bigint), b (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out b/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out index f2f1a50ff0..d023ad4fec 100644 --- a/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out +++ b/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out @@ -30,28 +30,28 @@ STAGE PLANS: TableScan alias: src filterExpr: (key) IN (0, 1) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key) IN (0, 1) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(KEY.reducesinkkey0) (type: int), VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4550 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4550 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -60,20 +60,20 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: c1, c2, p1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4550 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll') keys: p1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 15216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 15216 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 15216 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/implicit_decimal.q.out b/ql/src/test/results/clientpositive/implicit_decimal.q.out index 5628249a66..edf8fd1231 100644 --- a/ql/src/test/results/clientpositive/implicit_decimal.q.out +++ b/ql/src/test/results/clientpositive/implicit_decimal.q.out @@ -36,17 +36,17 @@ STAGE PLANS: TableScan alias: decimal_test filterExpr: (dc = 4327269606205.029297) (type: boolean) - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (dc = 4327269606205.029297) (type: boolean) - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 4327269606205.029297 (type: decimal(38,18)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out index aceb845a89..b93967f3af 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out @@ -428,22 +428,22 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -452,14 +452,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string), if(((UDFToDouble(_col0) % 100.0D) = 0.0D), '11', '12') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 143780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 143780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -468,13 +468,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 173484 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158 Data size: 182964 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -540,7 +540,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158 Data size: 182964 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -549,14 +549,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158 Data size: 182964 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158 Data size: 182964 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158 Data size: 182964 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out index cfd190feb6..ce556b0d4b 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out @@ -32,22 +32,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 145500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 145500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -56,15 +56,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 145500 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), CAST( _col3 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 271500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 271500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -73,13 +73,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '1' (type: string) outputColumnNames: key, value, agg, part - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 335250 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(agg, 'hll') keys: part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -115,7 +115,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -124,14 +124,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1513,22 +1513,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 194000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 194000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1537,15 +1537,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 194000 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), CAST( _col3 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1554,13 +1554,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '1' (type: string) outputColumnNames: key, value, agg, part - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 447000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(agg, 'hll') keys: part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1596,7 +1596,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1605,14 +1605,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1740,22 +1740,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1764,15 +1764,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), CAST( _col3 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1781,13 +1781,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '1' (type: string) outputColumnNames: key, value, agg, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(agg, 'hll') keys: part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1823,7 +1823,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1832,14 +1832,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out index 178eb941b6..19519addec 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out @@ -68,24 +68,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1_n14 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 85636 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 85636 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -94,18 +94,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, part - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 112496 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -113,14 +113,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -263,42 +263,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1_n14 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col1) (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: bigint) TableScan alias: src filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -307,14 +307,14 @@ STAGE PLANS: 0 UDFToDouble(_col1) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -323,13 +323,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, part - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -365,7 +365,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -374,14 +374,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -471,10 +471,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -652,10 +652,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out index 4062fcaa41..b7e1e03652 100644 --- a/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out +++ b/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out @@ -35,25 +35,25 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: if(((key % 3) < 2), 0, 1) (type: int), value (type: string), UDFToInteger((key % 2)) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -62,13 +62,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 373000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: '2008-04-08' (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 360872 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -105,7 +105,7 @@ STAGE PLANS: key expressions: '2008-04-08' (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: '2008-04-08' (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 360872 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -114,14 +114,14 @@ STAGE PLANS: keys: '2008-04-08' (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), '2008-04-08' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/infer_const_type.q.out b/ql/src/test/results/clientpositive/infer_const_type.q.out index 4129bd0c71..82887f45dc 100644 --- a/ql/src/test/results/clientpositive/infer_const_type.q.out +++ b/ql/src/test/results/clientpositive/infer_const_type.q.out @@ -58,17 +58,17 @@ STAGE PLANS: TableScan alias: infertypes filterExpr: ((ti = 127Y) and (si = 32767S) and (i = 12345) and (bi = -12345L) and (fl = 906) and (db = -307.0D) and (UDFToDouble(str) = 1234.0D)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(str) = 1234.0D) and (bi = -12345L) and (db = -307.0D) and (fl = 906) and (i = 12345) and (si = 32767S) and (ti = 127Y)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 127Y (type: tinyint), 32767S (type: smallint), 12345 (type: int), -12345L (type: bigint), 906.0 (type: float), -307.0D (type: double), str (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -132,17 +132,17 @@ STAGE PLANS: TableScan alias: infertypes filterExpr: ((UDFToDouble(ti) = 128.0D) or (UDFToInteger(si) = 32768) or (UDFToDouble(i) = 2.147483648E9D) or (UDFToDouble(bi) = 9.223372036854776E18D)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(bi) = 9.223372036854776E18D) or (UDFToDouble(i) = 2.147483648E9D) or (UDFToDouble(ti) = 128.0D) or (UDFToInteger(si) = 32768)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), str (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -197,17 +197,17 @@ STAGE PLANS: TableScan alias: infertypes filterExpr: ((UDFToDouble(ti) = 127.0D) or (CAST( si AS decimal(5,0)) = 327) or (UDFToDouble(i) = -100.0D)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((CAST( si AS decimal(5,0)) = 327) or (UDFToDouble(i) = -100.0D) or (UDFToDouble(ti) = 127.0D)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), str (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -256,17 +256,17 @@ STAGE PLANS: TableScan alias: infertypes filterExpr: ((UDFToDouble(ti) < 127.0D) and (UDFToDouble(i) > 100.0D) and (UDFToDouble(str) = 1.57D)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(i) > 100.0D) and (UDFToDouble(str) = 1.57D) and (UDFToDouble(ti) < 127.0D)) (type: boolean) - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: smallint), i (type: int), bi (type: bigint), fl (type: float), db (type: double), str (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 216 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/infer_join_preds.q.out b/ql/src/test/results/clientpositive/infer_join_preds.q.out index 57f651168c..94de9e504f 100644 --- a/ql/src/test/results/clientpositive/infer_join_preds.q.out +++ b/ql/src/test/results/clientpositive/infer_join_preds.q.out @@ -15,36 +15,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -54,10 +54,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -138,35 +138,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -176,10 +176,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -229,32 +229,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -264,10 +264,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -317,32 +317,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -352,10 +352,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4731 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4731 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -430,32 +430,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -465,10 +465,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 706 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 706 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -543,32 +543,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -578,10 +578,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -626,35 +626,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (4.0D BETWEEN UDFToDouble(key) AND UDFToDouble(value) and key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (4.0D BETWEEN UDFToDouble(key) AND UDFToDouble(value) and key is not null and value is not null) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src1 filterExpr: (4.0D BETWEEN UDFToDouble(key) AND UDFToDouble(value) and key is not null and value is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (4.0D BETWEEN UDFToDouble(key) AND UDFToDouble(value) and key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -663,10 +663,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 706 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 706 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1125,52 +1125,52 @@ STAGE PLANS: TableScan alias: s filterExpr: prid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 668 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: prid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 668 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: idp_warehouse_id (type: bigint), prid (type: bigint), prtimesheetid (type: bigint), prassignmentid (type: bigint), prchargecodeid (type: bigint), prtypecodeid (type: bigint), prsequence (type: bigint), prmodby (type: varchar(96)), prmodtime (type: timestamp), prrmexported (type: bigint), prrmckdel (type: bigint), slice_status (type: int), role_id (type: bigint), user_lov1 (type: varchar(30)), user_lov2 (type: varchar(30)), incident_id (type: bigint), incident_investment_id (type: bigint), odf_ss_actuals (type: bigint), practsum (type: decimal(38,20)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 668 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 668 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: varchar(96)), _col8 (type: timestamp), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: int), _col12 (type: bigint), _col13 (type: varchar(30)), _col14 (type: varchar(30)), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: decimal(38,20)) TableScan alias: e filterExpr: prid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: prid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: prid (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TableScan alias: d filterExpr: prid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 776 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: prid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 776 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: pruid (type: varchar(32)), prid (type: bigint), prtimesheetid (type: bigint), prassignmentid (type: bigint), prchargecodeid (type: bigint), prtypecodeid (type: bigint), prsequence (type: bigint), prmodby (type: varchar(96)), prmodtime (type: timestamp), prrmexported (type: bigint), prrmckdel (type: bigint), slice_status (type: int), role_id (type: bigint), user_lov1 (type: varchar(30)), user_lov2 (type: varchar(30)), incident_id (type: bigint), incident_investment_id (type: bigint), odf_ss_actuals (type: bigint), practsum (type: decimal(38,20)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 776 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 776 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: varchar(32)), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: varchar(96)), _col8 (type: timestamp), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: int), _col12 (type: bigint), _col13 (type: varchar(30)), _col14 (type: varchar(30)), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: decimal(38,20)) Reduce Operator Tree: Join Operator @@ -1182,17 +1182,17 @@ STAGE PLANS: 1 _col0 (type: bigint) 2 _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1469 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (concat(CAST( _col1 AS STRING), ',', CASE WHEN (_col2 is null) THEN (1) ELSE (_col2) END, ',', CASE WHEN (_col3 is null) THEN (1) ELSE (_col3) END, ',', CASE WHEN (_col4 is null) THEN (1) ELSE (_col4) END, ',', CASE WHEN (_col5 is null) THEN ('') ELSE (_col5) END, ',', CASE WHEN (_col18 is null) THEN (1) ELSE (_col18) END, ',', CASE WHEN (_col6 is null) THEN (1) ELSE (_col6) END, ',', CASE WHEN (length(_col7) is null) THEN ('') ELSE (_col7) END, ',', CASE WHEN (_col8 is null) THEN (TIMESTAMP'2017-12-08 00:00:00') ELSE (_col8) END, ',', CASE WHEN (_col9 is null) THEN (1) ELSE (_col9) END, ',', CASE WHEN (_col10 is null) THEN (1) ELSE (_col10) END, ',', CASE WHEN (_col11 is null) THEN (1) ELSE (_col11) END, ',', CASE WHEN (_col12 is null) THEN (1) ELSE (_col12) END, ',', CASE WHEN (length(_col13) is null) THEN ('') ELSE (_col13) END, ',', CASE WHEN (length(_col14) is null) THEN ('') ELSE (_col14) END, ',', CASE WHEN (_col15 is null) THEN (1) ELSE (_col15) END, ',', CASE WHEN (_col16 is null) THEN (1) ELSE (_col16) END, ',', CASE WHEN (_col17 is null) THEN (1) ELSE (_col17) END) <> concat(CASE WHEN (length(_col20) is null) THEN ('') ELSE (_col20) END, ',', _col21, ',', CASE WHEN (_col22 is null) THEN (1) ELSE (_col22) END, ',', CASE WHEN (_col23 is null) THEN (1) ELSE (_col23) END, ',', CASE WHEN (_col24 is null) THEN (1) ELSE (_col24) END, ',', CASE WHEN (_col25 is null) THEN ('') ELSE (_col25) END, ',', CASE WHEN (_col38 is null) THEN (1) ELSE (_col38) END, ',', CASE WHEN (_col26 is null) THEN (1) ELSE (_col26) END, ',', CASE WHEN (length(_col27) is null) THEN ('') ELSE (_col27) END, ',', CASE WHEN (_col28 is null) THEN (TIMESTAMP'2017-12-08 00:00:00') ELSE (_col28) END, ',', CASE WHEN (_col29 is null) THEN (1) ELSE (_col29) END, ',', CASE WHEN (_col30 is null) THEN (1) ELSE (_col30) END, ',', CASE WHEN (_col31 is null) THEN (1) ELSE (_col31) END, ',', CASE WHEN (_col32 is null) THEN (1) ELSE (_col32) END, ',', CASE WHEN (length(_col33) is null) THEN ('') ELSE (_col33) END, ',', CASE WHEN (length(_col34) is null) THEN ('') ELSE (_col34) END, ',', CASE WHEN (_col35 is null) THEN (1) ELSE (_col35) END, ',', CASE WHEN (_col36 is null) THEN (1) ELSE (_col36) END, ',', CASE WHEN (_col37 is null) THEN (1) ELSE (_col37) END)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1469 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1469 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1469 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/innerjoin.q.out b/ql/src/test/results/clientpositive/innerjoin.q.out index 6dab117d5b..575faa06d9 100644 --- a/ql/src/test/results/clientpositive/innerjoin.q.out +++ b/ql/src/test/results/clientpositive/innerjoin.q.out @@ -27,35 +27,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -65,14 +65,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -81,12 +81,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -118,7 +118,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -126,10 +126,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1231,29 +1231,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1263,10 +1263,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/innerjoin1.q.out b/ql/src/test/results/clientpositive/innerjoin1.q.out index d17ed26c8d..6ced729a45 100644 --- a/ql/src/test/results/clientpositive/innerjoin1.q.out +++ b/ql/src/test/results/clientpositive/innerjoin1.q.out @@ -77,36 +77,36 @@ STAGE PLANS: TableScan alias: c1 filterExpr: COALESCE(a1,a2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: COALESCE(a1,a2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a1 (type: string), a2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: COALESCE(_col0,_col1) (type: string) sort order: + Map-reduce partition columns: COALESCE(_col0,_col1) (type: string) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: c2 filterExpr: COALESCE(b1,b2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: COALESCE(b1,b2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: b1 (type: string), b2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: COALESCE(_col0,_col1) (type: string) sort order: + Map-reduce partition columns: COALESCE(_col0,_col1) (type: string) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -116,10 +116,10 @@ STAGE PLANS: 0 COALESCE(_col0,_col1) (type: string) 1 COALESCE(_col0,_col1) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -158,36 +158,36 @@ STAGE PLANS: TableScan alias: c1 filterExpr: COALESCE(a1,a2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: COALESCE(a1,a2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a1 (type: string), a2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: COALESCE(_col0,_col1) (type: string) sort order: + Map-reduce partition columns: COALESCE(_col0,_col1) (type: string) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: c2 filterExpr: COALESCE(b1,b2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: COALESCE(b1,b2) is not null (type: boolean) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: b1 (type: string), b2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: COALESCE(_col0,_col1) (type: string) sort order: + Map-reduce partition columns: COALESCE(_col0,_col1) (type: string) - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -197,10 +197,10 @@ STAGE PLANS: 0 COALESCE(_col0,_col1) (type: string) 1 COALESCE(_col0,_col1) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input.q.out b/ql/src/test/results/clientpositive/input.q.out index 286cd19726..be184872e3 100644 --- a/ql/src/test/results/clientpositive/input.q.out +++ b/ql/src/test/results/clientpositive/input.q.out @@ -14,11 +14,11 @@ STAGE PLANS: Processor Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRC x diff --git a/ql/src/test/results/clientpositive/input0.q.out b/ql/src/test/results/clientpositive/input0.q.out index 4d66253e56..e88400a773 100644 --- a/ql/src/test/results/clientpositive/input0.q.out +++ b/ql/src/test/results/clientpositive/input0.q.out @@ -14,11 +14,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT * FROM src diff --git a/ql/src/test/results/clientpositive/input11.q.out b/ql/src/test/results/clientpositive/input11.q.out index e103787e19..65c35d76e8 100644 --- a/ql/src/test/results/clientpositive/input11.q.out +++ b/ql/src/test/results/clientpositive/input11.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -50,25 +50,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input11_limit.q.out b/ql/src/test/results/clientpositive/input11_limit.q.out index ee09d80094..32e9ff54b5 100644 --- a/ql/src/test/results/clientpositive/input11_limit.q.out +++ b/ql/src/test/results/clientpositive/input11_limit.q.out @@ -26,20 +26,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -47,17 +47,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/input12.q.out b/ql/src/test/results/clientpositive/input12.q.out index b2dad20b2e..b539e34a43 100644 --- a/ql/src/test/results/clientpositive/input12.q.out +++ b/ql/src/test/results/clientpositive/input12.q.out @@ -56,17 +56,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -75,26 +75,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 200) and (key >= 100)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -103,12 +103,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -117,14 +117,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (key >= 200) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -133,13 +133,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: key - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30544 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') keys: '2008-04-08' (type: string), '12' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -151,10 +151,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -241,7 +241,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -249,10 +249,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -287,7 +287,7 @@ STAGE PLANS: key expressions: '2008-04-08' (type: string), '12' (type: string) sort order: ++ Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -296,14 +296,14 @@ STAGE PLANS: keys: '2008-04-08' (type: string), '12' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input13.q.out b/ql/src/test/results/clientpositive/input13.q.out index 6e3f3094e7..4e6d19973f 100644 --- a/ql/src/test/results/clientpositive/input13.q.out +++ b/ql/src/test/results/clientpositive/input13.q.out @@ -59,17 +59,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -78,26 +78,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 200) and (key >= 100)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -106,12 +106,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -120,14 +120,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((key < 300) and (key >= 200)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 220 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 220 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -136,13 +136,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: key - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') keys: '2008-04-08' (type: string), '12' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -151,14 +151,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (key >= 300) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -168,10 +168,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -258,7 +258,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -266,10 +266,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,7 +304,7 @@ STAGE PLANS: key expressions: '2008-04-08' (type: string), '12' (type: string) sort order: ++ Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -313,14 +313,14 @@ STAGE PLANS: keys: '2008-04-08' (type: string), '12' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input14.q.out b/ql/src/test/results/clientpositive/input14.q.out index 597d29da41..b0f2964e07 100644 --- a/ql/src/test/results/clientpositive/input14.q.out +++ b/ql/src/test/results/clientpositive/input14.q.out @@ -36,35 +36,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -73,12 +73,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -110,7 +110,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -118,10 +118,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input14_limit.q.out b/ql/src/test/results/clientpositive/input14_limit.q.out index 151d6d6c6d..4191d66096 100644 --- a/ql/src/test/results/clientpositive/input14_limit.q.out +++ b/ql/src/test/results/clientpositive/input14_limit.q.out @@ -36,33 +36,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -78,7 +78,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -86,20 +86,20 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/input17.q.out b/ql/src/test/results/clientpositive/input17.q.out index c506a628a3..e2cf4ad42b 100644 --- a/ql/src/test/results/clientpositive/input17.q.out +++ b/ql/src/test/results/clientpositive/input17.q.out @@ -36,32 +36,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (aint + lint[0]) (type: int), lintstring[0] (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -70,12 +70,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3548 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -107,7 +107,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3548 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -115,10 +115,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3564 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3564 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input18.q.out b/ql/src/test/results/clientpositive/input18.q.out index 4a1c0d888e..7cf6974d93 100644 --- a/ql/src/test/results/clientpositive/input18.q.out +++ b/ql/src/test/results/clientpositive/input18.q.out @@ -36,35 +36,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), regexp_replace(VALUE._col1, ' ', '+') (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -73,12 +73,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -110,7 +110,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -118,10 +118,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input1_limit.q.out b/ql/src/test/results/clientpositive/input1_limit.q.out index 53f4e89692..7940335e70 100644 --- a/ql/src/test/results/clientpositive/input1_limit.q.out +++ b/ql/src/test/results/clientpositive/input1_limit.q.out @@ -40,31 +40,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Filter Operator predicate: (key < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -76,17 +76,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -95,12 +95,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -132,7 +132,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -140,10 +140,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -163,24 +163,24 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -189,12 +189,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -218,7 +218,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -226,10 +226,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input20.q.out b/ql/src/test/results/clientpositive/input20.q.out index 9f8d612dd6..4de66df9c7 100644 --- a/ql/src/test/results/clientpositive/input20.q.out +++ b/ql/src/test/results/clientpositive/input20.q.out @@ -42,42 +42,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: python input20_script.py output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -86,12 +86,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -123,7 +123,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -131,10 +131,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input21.q.out b/ql/src/test/results/clientpositive/input21.q.out index 528a74fb03..b06e8abbd8 100644 --- a/ql/src/test/results/clientpositive/input21.q.out +++ b/ql/src/test/results/clientpositive/input21.q.out @@ -28,26 +28,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_null - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string), c (type: string), d (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input22.q.out b/ql/src/test/results/clientpositive/input22.q.out index 23845ec10c..2755fdc43c 100644 --- a/ql/src/test/results/clientpositive/input22.q.out +++ b/ql/src/test/results/clientpositive/input22.q.out @@ -36,28 +36,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: input4 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input23.q.out b/ql/src/test/results/clientpositive/input23.q.out index 4c8524775c..b2dc554eee 100644 --- a/ql/src/test/results/clientpositive/input23.q.out +++ b/ql/src/test/results/clientpositive/input23.q.out @@ -24,36 +24,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 548 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 548 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -120,20 +120,20 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col4, _col5 - Statistics: Num rows: 500 Data size: 5812 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 500 Data size: 273000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string), _col4 (type: string), _col5 (type: string), '2008-04-08' (type: string), '14' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 500 Data size: 5812 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 500 Data size: 453000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 55 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4530 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 5 Data size: 55 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4530 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/input25.q.out b/ql/src/test/results/clientpositive/input25.q.out index 16354ebb98..3392ccfbde 100644 --- a/ql/src/test/results/clientpositive/input25.q.out +++ b/ql/src/test/results/clientpositive/input25.q.out @@ -47,17 +47,17 @@ STAGE PLANS: TableScan alias: x filterExpr: (d = '2009-01-01') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: int), _col1 (type: int) Execution mode: vectorized @@ -65,14 +65,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), '2009-01-01' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -85,20 +85,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -110,17 +110,17 @@ STAGE PLANS: TableScan alias: x filterExpr: (d = '2009-02-02') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: int), _col1 (type: int) Execution mode: vectorized @@ -128,14 +128,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), '2009-02-02' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/input26.q.out b/ql/src/test/results/clientpositive/input26.q.out index 6b4a711416..38992e1cf4 100644 --- a/ql/src/test/results/clientpositive/input26.q.out +++ b/ql/src/test/results/clientpositive/input26.q.out @@ -25,15 +25,15 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -41,14 +41,14 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -61,28 +61,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 1774 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 50 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 6 Data size: 3288 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -94,20 +94,20 @@ STAGE PLANS: TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2008-04-08') and (hr = '14')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -115,14 +115,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '14' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 454 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/input2_limit.q.out b/ql/src/test/results/clientpositive/input2_limit.q.out index 6cb4480cf1..5520634642 100644 --- a/ql/src/test/results/clientpositive/input2_limit.q.out +++ b/ql/src/test/results/clientpositive/input2_limit.q.out @@ -15,20 +15,20 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 300.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 300.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 890 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input33.q.out b/ql/src/test/results/clientpositive/input33.q.out index bff22484fa..8022cf7cc7 100644 --- a/ql/src/test/results/clientpositive/input33.q.out +++ b/ql/src/test/results/clientpositive/input33.q.out @@ -42,42 +42,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: python input20_script.py output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -86,12 +86,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -123,7 +123,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -131,10 +131,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input34.q.out b/ql/src/test/results/clientpositive/input34.q.out index 76517c6153..0398005810 100644 --- a/ql/src/test/results/clientpositive/input34.q.out +++ b/ql/src/test/results/clientpositive/input34.q.out @@ -40,25 +40,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -67,25 +67,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input35.q.out b/ql/src/test/results/clientpositive/input35.q.out index c07128fa25..e3ad120444 100644 --- a/ql/src/test/results/clientpositive/input35.q.out +++ b/ql/src/test/results/clientpositive/input35.q.out @@ -40,25 +40,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -67,25 +67,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input36.q.out b/ql/src/test/results/clientpositive/input36.q.out index b05d0b8146..374c5aabbc 100644 --- a/ql/src/test/results/clientpositive/input36.q.out +++ b/ql/src/test/results/clientpositive/input36.q.out @@ -40,25 +40,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -67,25 +67,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input38.q.out b/ql/src/test/results/clientpositive/input38.q.out index 4eec97d547..7281cb97df 100644 --- a/ql/src/test/results/clientpositive/input38.q.out +++ b/ql/src/test/results/clientpositive/input38.q.out @@ -38,21 +38,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -61,25 +61,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input39.q.out b/ql/src/test/results/clientpositive/input39.q.out index 51dde78c18..cf0799ccf3 100644 --- a/ql/src/test/results/clientpositive/input39.q.out +++ b/ql/src/test/results/clientpositive/input39.q.out @@ -67,40 +67,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n121 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hash(rand(460476415)) & 2147483647) % 32) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43000 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2_n71 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hash(rand(460476415)) & 2147483647) % 32) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -108,12 +108,12 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -127,7 +127,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -135,10 +135,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input3_limit.q.out b/ql/src/test/results/clientpositive/input3_limit.q.out index 191c3e7a81..d9d87df6fe 100644 --- a/ql/src/test/results/clientpositive/input3_limit.q.out +++ b/ql/src/test/results/clientpositive/input3_limit.q.out @@ -49,22 +49,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n78 - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -79,19 +79,19 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -100,12 +100,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -137,7 +137,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -145,10 +145,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input4.q.out b/ql/src/test/results/clientpositive/input4.q.out index 508a02bcc4..08e8862410 100644 --- a/ql/src/test/results/clientpositive/input4.q.out +++ b/ql/src/test/results/clientpositive/input4.q.out @@ -45,7 +45,7 @@ PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FORMATTED SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4_n0 AS Input4Alias POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT `value`, `key`\nFROM `default`.`input4_n0`","cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}},"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"TableScan":{"alias:":"input4alias","columns:":["value","key"],"database:":"default","Statistics:":"Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE","table:":"input4_n0","isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"value (type: string), key (type: string)","columnExprMap:":{"_col0":"value","_col1":"key"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_1","children":{"ListSink":{"OperatorId:":"LIST_SINK_3"}}}}}}}}}} +{"optimizedSQL":"SELECT `value`, `key`\nFROM `default`.`input4_n0`","cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}},"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"TableScan":{"alias:":"input4alias","columns:":["value","key"],"database:":"default","Statistics:":"Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE","table:":"input4_n0","isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"value (type: string), key (type: string)","columnExprMap:":{"_col0":"value","_col1":"key"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_1","children":{"ListSink":{"OperatorId:":"LIST_SINK_3"}}}}}}}}}} PREHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4_n0 AS Input4Alias PREHOOK: type: QUERY PREHOOK: Input: default@input4_n0 diff --git a/ql/src/test/results/clientpositive/input42.q.out b/ql/src/test/results/clientpositive/input42.q.out index 98c2fd0109..1416104624 100644 --- a/ql/src/test/results/clientpositive/input42.q.out +++ b/ql/src/test/results/clientpositive/input42.q.out @@ -113,12 +113,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from srcpart a where a.ds='2008-04-08' @@ -1153,22 +1153,22 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (UDFToDouble(key) < 200.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1706,22 +1706,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (rand(100) < 0.1D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/input4_limit.q.out b/ql/src/test/results/clientpositive/input4_limit.q.out index eb66d9566e..ae5f98fad6 100644 --- a/ql/src/test/results/clientpositive/input4_limit.q.out +++ b/ql/src/test/results/clientpositive/input4_limit.q.out @@ -15,15 +15,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -31,10 +31,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -49,7 +49,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -57,13 +57,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input5.q.out b/ql/src/test/results/clientpositive/input5.q.out index ef4f6fd391..4ff8ffa5f0 100644 --- a/ql/src/test/results/clientpositive/input5.q.out +++ b/ql/src/test/results/clientpositive/input5.q.out @@ -36,32 +36,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint (type: array), lintstring (type: array>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -70,12 +70,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 29480 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -107,7 +107,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -115,10 +115,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3560 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input6.q.out b/ql/src/test/results/clientpositive/input6.q.out index de9e798c23..14eb87eb95 100644 --- a/ql/src/test/results/clientpositive/input6.q.out +++ b/ql/src/test/results/clientpositive/input6.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is null (type: boolean) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -50,25 +50,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input7.q.out b/ql/src/test/results/clientpositive/input7.q.out index 26add5b4c2..1d27e4f310 100644 --- a/ql/src/test/results/clientpositive/input7.q.out +++ b/ql/src/test/results/clientpositive/input7.q.out @@ -30,14 +30,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: double), UDFToInteger(key) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -46,25 +46,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double), _col1 (type: int) outputColumnNames: c1, c2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input8.q.out b/ql/src/test/results/clientpositive/input8.q.out index da3e42d319..14fd67a668 100644 --- a/ql/src/test/results/clientpositive/input8.q.out +++ b/ql/src/test/results/clientpositive/input8.q.out @@ -30,14 +30,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: string), UDFToInteger((UDFToDouble(key) - null)) (type: int), null (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -46,25 +46,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) outputColumnNames: c1, c2, c3 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input9.q.out b/ql/src/test/results/clientpositive/input9.q.out index 1424957a4f..ab61418607 100644 --- a/ql/src/test/results/clientpositive/input9.q.out +++ b/ql/src/test/results/clientpositive/input9.q.out @@ -30,17 +30,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: string), UDFToInteger(key) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -49,25 +49,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: value, key - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(value, 'hll'), compute_stats(key, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input_columnarserde.q.out b/ql/src/test/results/clientpositive/input_columnarserde.q.out index ae51d74a28..155a75e46b 100644 --- a/ql/src/test/results/clientpositive/input_columnarserde.q.out +++ b/ql/src/test/results/clientpositive/input_columnarserde.q.out @@ -35,25 +35,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint (type: array), lstring (type: array), mstringstring (type: map), aint (type: int), astring (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array), _col1 (type: array), _col2 (type: map), _col3 (type: int), _col4 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: array), VALUE._col1 (type: array), VALUE._col2 (type: map), VALUE._col3 (type: int), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input_dynamicserde.q.out b/ql/src/test/results/clientpositive/input_dynamicserde.q.out index 52f667feb5..5adcb8f98c 100644 --- a/ql/src/test/results/clientpositive/input_dynamicserde.q.out +++ b/ql/src/test/results/clientpositive/input_dynamicserde.q.out @@ -42,14 +42,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint (type: array), lstring (type: array), mstringstring (type: map), aint (type: int), astring (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/input_lazyserde.q.out b/ql/src/test/results/clientpositive/input_lazyserde.q.out index 0216bf6f4b..3246b6512f 100644 --- a/ql/src/test/results/clientpositive/input_lazyserde.q.out +++ b/ql/src/test/results/clientpositive/input_lazyserde.q.out @@ -41,24 +41,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint (type: array), lstring (type: array), mstringstring (type: map), aint (type: int), astring (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array), _col1 (type: array), _col2 (type: map), _col3 (type: int), _col4 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: array), VALUE._col1 (type: array), VALUE._col2 (type: map), VALUE._col3 (type: int), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/input_lazyserde2.q.out b/ql/src/test/results/clientpositive/input_lazyserde2.q.out index 80922d9a4f..5da50ee601 100644 --- a/ql/src/test/results/clientpositive/input_lazyserde2.q.out +++ b/ql/src/test/results/clientpositive/input_lazyserde2.q.out @@ -41,24 +41,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint (type: array), lstring (type: array), mstringstring (type: map), aint (type: int), astring (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array), _col1 (type: array), _col2 (type: map), _col3 (type: int), _col4 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: array), VALUE._col1 (type: array), VALUE._col2 (type: map), VALUE._col3 (type: int), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 34628 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/input_limit.q.out b/ql/src/test/results/clientpositive/input_limit.q.out index d1d62ec591..3ea535b376 100644 --- a/ql/src/test/results/clientpositive/input_limit.q.out +++ b/ql/src/test/results/clientpositive/input_limit.q.out @@ -14,14 +14,14 @@ STAGE PLANS: Processor Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRC x LIMIT 20 diff --git a/ql/src/test/results/clientpositive/input_part0.q.out b/ql/src/test/results/clientpositive/input_part0.q.out index aa25c46086..1c7b992622 100644 --- a/ql/src/test/results/clientpositive/input_part0.q.out +++ b/ql/src/test/results/clientpositive/input_part0.q.out @@ -15,11 +15,11 @@ STAGE PLANS: TableScan alias: x filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRCPART x WHERE x.ds = '2008-04-08' diff --git a/ql/src/test/results/clientpositive/input_part1.q.out b/ql/src/test/results/clientpositive/input_part1.q.out index 4c271068ad..27135efa16 100644 --- a/ql/src/test/results/clientpositive/input_part1.q.out +++ b/ql/src/test/results/clientpositive/input_part1.q.out @@ -34,22 +34,22 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((UDFToDouble(key) < 100.0D) and (ds = '2008-04-08') and (hr = '12')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), '12' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -80,16 +80,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, hr, ds - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 45650 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(hr, 'hll'), compute_stats(ds, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -153,13 +153,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/input_part2.q.out b/ql/src/test/results/clientpositive/input_part2.q.out index 30a8d9f2d4..42d358bef9 100644 --- a/ql/src/test/results/clientpositive/input_part2.q.out +++ b/ql/src/test/results/clientpositive/input_part2.q.out @@ -43,22 +43,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-08') and (key < 100)) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 90576 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), '12' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 91575 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 91575 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -89,33 +89,33 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '12' (type: string), '2008-04-08' (type: string) outputColumnNames: key, value, hr, ds - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 91575 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(hr, 'hll'), compute_stats(ds, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-09') and (key < 100)) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 90576 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), '12' (type: string), '2008-04-09' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 91575 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 91575 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -146,12 +146,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '12' (type: string), '2008-04-09' (type: string) outputColumnNames: key, value, hr, ds - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 91575 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(hr, 'hll'), compute_stats(ds, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -280,13 +280,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -585,7 +585,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -623,13 +623,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/input_part3.q.out b/ql/src/test/results/clientpositive/input_part3.q.out index 375fec9131..4d6f17aada 100644 --- a/ql/src/test/results/clientpositive/input_part3.q.out +++ b/ql/src/test/results/clientpositive/input_part3.q.out @@ -15,11 +15,11 @@ STAGE PLANS: TableScan alias: x filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRCPART x WHERE x.ds = '2008-04-08' and x.hr = 11 diff --git a/ql/src/test/results/clientpositive/input_part4.q.out b/ql/src/test/results/clientpositive/input_part4.q.out index cdae542d4a..5a8d38463d 100644 --- a/ql/src/test/results/clientpositive/input_part4.q.out +++ b/ql/src/test/results/clientpositive/input_part4.q.out @@ -15,14 +15,14 @@ STAGE PLANS: TableScan alias: x filterExpr: ((ds = '2008-04-08') and (UDFToDouble(hr) = 15.0D)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((UDFToDouble(hr) = 15.0D) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 646 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: SELECT x.* FROM SRCPART x WHERE x.ds = '2008-04-08' and x.hr = 15 diff --git a/ql/src/test/results/clientpositive/input_part5.q.out b/ql/src/test/results/clientpositive/input_part5.q.out index 75c44ae892..83f1791c38 100644 --- a/ql/src/test/results/clientpositive/input_part5.q.out +++ b/ql/src/test/results/clientpositive/input_part5.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: x filterExpr: ((ds = '2008-04-08') and (UDFToDouble(key) < 100.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -50,25 +50,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, hr, ds - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(hr, 'hll'), compute_stats(ds, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input_part6.q.out b/ql/src/test/results/clientpositive/input_part6.q.out index 2392ce018c..ee5a83c3a6 100644 --- a/ql/src/test/results/clientpositive/input_part6.q.out +++ b/ql/src/test/results/clientpositive/input_part6.q.out @@ -15,14 +15,14 @@ STAGE PLANS: TableScan alias: x filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRCPART x WHERE x.ds = "2008-04-08" LIMIT 10 diff --git a/ql/src/test/results/clientpositive/input_part7.q.out b/ql/src/test/results/clientpositive/input_part7.q.out index 23f3fd7c05..abddfb2771 100644 --- a/ql/src/test/results/clientpositive/input_part7.q.out +++ b/ql/src/test/results/clientpositive/input_part7.q.out @@ -25,53 +25,53 @@ STAGE PLANS: TableScan alias: x filterExpr: ((ds = '2008-04-08') and (key < 100)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key < 100) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false TableScan alias: y filterExpr: ((ds = '2008-04-08') and (key < 100)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key < 100) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Path -> Alias: @@ -183,13 +183,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/input_part8.q.out b/ql/src/test/results/clientpositive/input_part8.q.out index a35d6cf3b5..4c2d11a1a2 100644 --- a/ql/src/test/results/clientpositive/input_part8.q.out +++ b/ql/src/test/results/clientpositive/input_part8.q.out @@ -15,14 +15,14 @@ STAGE PLANS: TableScan alias: x filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4560 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRCPART x WHERE ds = '2008-04-08' LIMIT 10 diff --git a/ql/src/test/results/clientpositive/input_part9.q.out b/ql/src/test/results/clientpositive/input_part9.q.out index 5ecaeb10f5..f8f186e9c9 100644 --- a/ql/src/test/results/clientpositive/input_part9.q.out +++ b/ql/src/test/results/clientpositive/input_part9.q.out @@ -18,22 +18,22 @@ STAGE PLANS: TableScan alias: x filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/input_testsequencefile.q.out b/ql/src/test/results/clientpositive/input_testsequencefile.q.out index 847d045d59..098283c8d3 100644 --- a/ql/src/test/results/clientpositive/input_testsequencefile.q.out +++ b/ql/src/test/results/clientpositive/input_testsequencefile.q.out @@ -30,14 +30,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -46,25 +46,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input_testxpath.q.out b/ql/src/test/results/clientpositive/input_testxpath.q.out index c0ba678252..26d2e37df6 100644 --- a/ql/src/test/results/clientpositive/input_testxpath.q.out +++ b/ql/src/test/results/clientpositive/input_testxpath.q.out @@ -30,14 +30,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint[1] (type: int), lintstring[0].mystring (type: string), mstringstring['key_2'] (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -46,25 +46,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, mapvalue - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(mapvalue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4904 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input_testxpath2.q.out b/ql/src/test/results/clientpositive/input_testxpath2.q.out index 858492376e..883959a025 100644 --- a/ql/src/test/results/clientpositive/input_testxpath2.q.out +++ b/ql/src/test/results/clientpositive/input_testxpath2.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: src_thrift filterExpr: (lint is not null and mstringstring is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (lint is not null and mstringstring is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: size(lint) (type: int), size(lintstring) (type: int), size(mstringstring) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -50,25 +50,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: lint_size, lintstring_size, mstringstring_size - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(lint_size, 'hll'), compute_stats(lintstring_size, 'hll'), compute_stats(mstringstring_size, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4872 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4872 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input_testxpath3.q.out b/ql/src/test/results/clientpositive/input_testxpath3.q.out index 8244cebe63..012ed5c630 100644 --- a/ql/src/test/results/clientpositive/input_testxpath3.q.out +++ b/ql/src/test/results/clientpositive/input_testxpath3.q.out @@ -16,14 +16,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: mstringstring['key_9'] (type: string), lintstring.myint (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/input_testxpath4.q.out b/ql/src/test/results/clientpositive/input_testxpath4.q.out index faaaa621a6..32ded465bb 100644 --- a/ql/src/test/results/clientpositive/input_testxpath4.q.out +++ b/ql/src/test/results/clientpositive/input_testxpath4.q.out @@ -22,17 +22,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (lintstring is not null and lintstring.myint is not null and mstringstring['key_9'] is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: mstringstring['key_9'] (type: string), lintstring.myint (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -95,17 +95,17 @@ STAGE PLANS: TableScan alias: src_thrift filterExpr: (mstringstring['key_9'] is not null and lintstring.myint is not null and lintstring is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (lintstring is not null and lintstring.myint is not null and mstringstring['key_9'] is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: mstringstring['key_9'] (type: string), lintstring.myint (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 38280 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert1.q.out b/ql/src/test/results/clientpositive/insert1.q.out index 7d3305ed5a..a0bb639b78 100644 --- a/ql/src/test/results/clientpositive/insert1.q.out +++ b/ql/src/test/results/clientpositive/insert1.q.out @@ -45,17 +45,17 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -64,25 +64,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -166,17 +166,17 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -185,25 +185,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -301,17 +301,17 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -320,25 +320,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -422,17 +422,17 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = -1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: -1 (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -441,25 +441,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -551,17 +551,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: insert2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -570,26 +570,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -598,12 +598,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -615,10 +615,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -705,7 +705,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -713,10 +713,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out b/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out index 822a4b4033..96f7343c69 100644 --- a/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out +++ b/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out @@ -62,27 +62,27 @@ STAGE PLANS: TableScan alias: sourcetable filterExpr: (ds = '2011-11-11') (type: boolean) - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: one (type: string), two (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: -- - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -91,13 +91,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string) outputColumnNames: one, two, ds - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -133,7 +133,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -142,14 +142,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 972 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1678 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 972 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1678 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 972 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1678 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -203,27 +203,27 @@ STAGE PLANS: TableScan alias: sourcetable filterExpr: (ds = '2011-11-11') (type: boolean) - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: one (type: string), two (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: -- - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 124 Data size: 104072 Basic stats: PARTIAL Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -232,13 +232,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string) outputColumnNames: one, two, ds - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false table: @@ -274,7 +274,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 2430 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 4195 Basic stats: PARTIAL Column stats: NONE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -283,14 +283,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 972 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1678 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 972 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1678 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 972 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1678 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert_into1.q.out b/ql/src/test/results/clientpositive/insert_into1.q.out index 09a497664b..65904a2d9d 100644 --- a/ql/src/test/results/clientpositive/insert_into1.q.out +++ b/ql/src/test/results/clientpositive/insert_into1.q.out @@ -26,32 +26,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -60,12 +60,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,7 +97,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -105,10 +105,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,32 +178,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -212,12 +212,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -249,7 +249,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -257,10 +257,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -330,32 +330,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -364,12 +364,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -401,7 +401,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -409,10 +409,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert_into2.q.out b/ql/src/test/results/clientpositive/insert_into2.q.out index fff6076410..fe9495d55a 100644 --- a/ql/src/test/results/clientpositive/insert_into2.q.out +++ b/ql/src/test/results/clientpositive/insert_into2.q.out @@ -30,32 +30,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -64,13 +64,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -106,7 +106,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -115,14 +115,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -231,32 +231,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -265,13 +265,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 18000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -307,7 +307,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -316,14 +316,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -401,32 +401,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -435,13 +435,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 9000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -477,7 +477,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -486,14 +486,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -580,17 +580,17 @@ STAGE PLANS: TableScan alias: insert_into2 filterExpr: (ds = '2') (type: boolean) - Statistics: Num rows: 50 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 50 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -598,10 +598,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert_into3.q.out b/ql/src/test/results/clientpositive/insert_into3.q.out index 2212fb17c3..04a795de11 100644 --- a/ql/src/test/results/clientpositive/insert_into3.q.out +++ b/ql/src/test/results/clientpositive/insert_into3.q.out @@ -44,19 +44,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -68,17 +68,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 8900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -87,12 +87,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -124,7 +124,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -132,10 +132,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -156,23 +156,23 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -181,12 +181,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -210,7 +210,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -218,10 +218,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -291,25 +291,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -321,17 +321,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -340,12 +340,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -377,7 +377,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -385,10 +385,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -408,24 +408,24 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -434,12 +434,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -463,7 +463,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -471,10 +471,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert_into4.q.out b/ql/src/test/results/clientpositive/insert_into4.q.out index fee5dfd422..9dc2d76b52 100644 --- a/ql/src/test/results/clientpositive/insert_into4.q.out +++ b/ql/src/test/results/clientpositive/insert_into4.q.out @@ -38,34 +38,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -74,12 +74,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -111,7 +111,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -119,10 +119,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -167,34 +167,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -203,12 +203,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -240,7 +240,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -248,10 +248,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -300,14 +300,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: insert_into4a - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -316,25 +316,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert_into5.q.out b/ql/src/test/results/clientpositive/insert_into5.q.out index e61499eefd..1f1a183735 100644 --- a/ql/src/test/results/clientpositive/insert_into5.q.out +++ b/ql/src/test/results/clientpositive/insert_into5.q.out @@ -167,14 +167,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: insert_into5a - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -183,25 +183,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -309,14 +309,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: insert_into5a - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -325,18 +325,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3520 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -344,14 +344,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -463,14 +463,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: insert_into5b - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -479,18 +479,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3520 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -498,14 +498,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insert_into6.q.out b/ql/src/test/results/clientpositive/insert_into6.q.out index ad23cbb79a..e1055611f0 100644 --- a/ql/src/test/results/clientpositive/insert_into6.q.out +++ b/ql/src/test/results/clientpositive/insert_into6.q.out @@ -40,34 +40,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 150 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 150 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26700 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 14250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 14250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -76,13 +76,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 27000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -118,7 +118,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -127,14 +127,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 75 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 75 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 75 Data size: 750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -199,14 +199,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: insert_into6a - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -215,18 +215,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -234,14 +234,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1340 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1340 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1340 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out b/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out index 63eaf015e0..4ca095cf4d 100644 --- a/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out +++ b/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out @@ -114,25 +114,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: bucketinput - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: data (type: string) outputColumnNames: _col1 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 576 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 576 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 576 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 576 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -141,12 +141,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: change, num - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 576 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(change, 'hll'), compute_stats(num, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -178,7 +178,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -186,10 +186,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -237,26 +237,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: temp1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: change (type: string), num (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -265,12 +265,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: create_ts, change, num - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(create_ts, 'hll'), compute_stats(change, 'hll'), compute_stats(num, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -302,7 +302,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -310,10 +310,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1688 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/interval_alt.q.out b/ql/src/test/results/clientpositive/interval_alt.q.out index 6adf4cc2bb..ad2cc82fe2 100644 --- a/ql/src/test/results/clientpositive/interval_alt.q.out +++ b/ql/src/test/results/clientpositive/interval_alt.q.out @@ -137,14 +137,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n18 - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (DATE'2012-01-01' + IntervalDayLiteralProcessor(((- dt) * dt))) (type: timestamp), (DATE'2012-01-01' - IntervalDayLiteralProcessor(((- dt) * dt))) (type: timestamp), TIMESTAMP'2012-01-04 00:00:00' (type: timestamp), (DATE'2012-01-01' + IntervalYearMonthLiteralProcessor(concat(CAST( dt AS STRING), '-1'))) (type: date) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/interval_arithmetic.q.out b/ql/src/test/results/clientpositive/interval_arithmetic.q.out index 819f1fee77..07b6abdfe2 100644 --- a/ql/src/test/results/clientpositive/interval_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/interval_arithmetic.q.out @@ -52,17 +52,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1_n0 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), (dateval - INTERVAL'2-2') (type: date), (dateval - INTERVAL'-2-2') (type: date), (dateval + INTERVAL'2-2') (type: date), (dateval + INTERVAL'-2-2') (type: date), (INTERVAL'-2-2' + dateval) (type: date), (INTERVAL'2-2' + dateval) (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 106 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 106 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -131,17 +131,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1_n0 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), (dateval - DATE'1999-06-07') (type: interval_day_time), (DATE'1999-06-07' - dateval) (type: interval_day_time), (dateval - dateval) (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 106 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 106 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -210,17 +210,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1_n0 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 467000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: tsval (type: timestamp), (tsval - INTERVAL'2-2') (type: timestamp), (tsval - INTERVAL'-2-2') (type: timestamp), (tsval + INTERVAL'2-2') (type: timestamp), (tsval + INTERVAL'-2-2') (type: timestamp), (INTERVAL'-2-2' + tsval) (type: timestamp), (INTERVAL'2-2' + tsval) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 467000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 76 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 76 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -347,17 +347,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1_n0 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), (dateval - INTERVAL'99 11:22:33.123456789') (type: timestamp), (dateval - INTERVAL'-99 11:22:33.123456789') (type: timestamp), (dateval + INTERVAL'99 11:22:33.123456789') (type: timestamp), (dateval + INTERVAL'-99 11:22:33.123456789') (type: timestamp), (INTERVAL'-99 11:22:33.123456789' + dateval) (type: timestamp), (INTERVAL'99 11:22:33.123456789' + dateval) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 106 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 106 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -428,17 +428,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1_n0 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1120800 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dateval (type: date), tsval (type: timestamp), (dateval - tsval) (type: interval_day_time), (tsval - dateval) (type: interval_day_time), (tsval - tsval) (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1120800 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -509,17 +509,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1_n0 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 467000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: tsval (type: timestamp), (tsval - INTERVAL'99 11:22:33.123456789') (type: timestamp), (tsval - INTERVAL'-99 11:22:33.123456789') (type: timestamp), (tsval + INTERVAL'99 11:22:33.123456789') (type: timestamp), (tsval + INTERVAL'-99 11:22:33.123456789') (type: timestamp), (INTERVAL'-99 11:22:33.123456789' + tsval) (type: timestamp), (INTERVAL'99 11:22:33.123456789' + tsval) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 326837 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 467000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 2 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 76 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 76 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join0.q.out b/ql/src/test/results/clientpositive/join0.q.out index 44709bf4b4..23591fcc27 100644 --- a/ql/src/test/results/clientpositive/join0.q.out +++ b/ql/src/test/results/clientpositive/join0.q.out @@ -27,32 +27,32 @@ STAGE PLANS: TableScan alias: src filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -62,7 +62,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -77,15 +77,15 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -114,7 +114,7 @@ SELECT src1.key as k1, src1.value as v1, (SELECT * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 POSTHOOK: type: QUERY -{"cboInfo":"Plan not optimized by CBO.","STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE","table:":"src","isTempTable:":"false","OperatorId:":"TS_0","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"FIL_13","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_2","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_6"}}}}}}}},{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE","table:":"src","isTempTable:":"false","OperatorId:":"TS_3","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"FIL_14","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_7"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"columnExprMap:":{"_col0":"0:VALUE._col0","_col1":"0:VALUE._col1","_col2":"1:VALUE._col0","_col3":"1:VALUE._col1"},"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"JOIN_8","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"},"OperatorId:":"FS_15"}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"columns:":["_col0","_col1","_col2","_col3"],"OperatorId:":"TS_16","children":{"Reduce Output Operator":{"columnExprMap:":{"KEY.reducesinkkey0":"_col0","KEY.reducesinkkey1":"_col1","KEY.reducesinkkey2":"_col2","KEY.reducesinkkey3":"_col3"},"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","sort order:":"++++","Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"RS_10"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","columnExprMap:":{"_col0":"KEY.reducesinkkey0","_col1":"KEY.reducesinkkey1","_col2":"KEY.reducesinkkey2","_col3":"KEY.reducesinkkey3"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_11","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_12"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_17"}}}}}} +{"cboInfo":"Plan not optimized by CBO.","STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE","table:":"src","isTempTable:":"false","OperatorId:":"TS_0","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_13","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_2","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_6"}}}}}}}},{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE","table:":"src","isTempTable:":"false","OperatorId:":"TS_3","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_14","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_5","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_7"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"columnExprMap:":{"_col0":"0:VALUE._col0","_col1":"0:VALUE._col1","_col2":"1:VALUE._col0","_col3":"1:VALUE._col1"},"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"JOIN_8","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"},"OperatorId:":"FS_15"}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"columns:":["_col0","_col1","_col2","_col3"],"OperatorId:":"TS_16","children":{"Reduce Output Operator":{"columnExprMap:":{"KEY.reducesinkkey0":"_col0","KEY.reducesinkkey1":"_col1","KEY.reducesinkkey2":"_col2","KEY.reducesinkkey3":"_col3"},"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","sort order:":"++++","Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"RS_10"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","columnExprMap:":{"_col0":"KEY.reducesinkkey0","_col1":"KEY.reducesinkkey1","_col2":"KEY.reducesinkkey2","_col3":"KEY.reducesinkkey3"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_11","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_12"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_17"}}}}}} Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM diff --git a/ql/src/test/results/clientpositive/join10.q.out b/ql/src/test/results/clientpositive/join10.q.out index 385d2a27a7..d6bf73706f 100644 --- a/ql/src/test/results/clientpositive/join10.q.out +++ b/ql/src/test/results/clientpositive/join10.q.out @@ -23,35 +23,35 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -61,14 +61,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join11.q.out b/ql/src/test/results/clientpositive/join11.q.out index 7cfff509db..b8827d779f 100644 --- a/ql/src/test/results/clientpositive/join11.q.out +++ b/ql/src/test/results/clientpositive/join11.q.out @@ -25,35 +25,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -63,14 +63,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join12.q.out b/ql/src/test/results/clientpositive/join12.q.out index 964fa1beb0..9fa5bde335 100644 --- a/ql/src/test/results/clientpositive/join12.q.out +++ b/ql/src/test/results/clientpositive/join12.q.out @@ -31,51 +31,51 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 80.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -87,14 +87,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join13.q.out b/ql/src/test/results/clientpositive/join13.q.out index ca41e22c8d..80ca1e24d0 100644 --- a/ql/src/test/results/clientpositive/join13.q.out +++ b/ql/src/test/results/clientpositive/join13.q.out @@ -32,36 +32,36 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -70,7 +70,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -86,24 +86,24 @@ STAGE PLANS: key expressions: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: src filterExpr: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 200.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -112,14 +112,14 @@ STAGE PLANS: 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col1, _col2 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join14.q.out b/ql/src/test/results/clientpositive/join14.q.out index 631b3354b2..d7b334756a 100644 --- a/ql/src/test/results/clientpositive/join14.q.out +++ b/ql/src/test/results/clientpositive/join14.q.out @@ -27,35 +27,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (UDFToDouble(key) > 100.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 90576 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 90576 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -65,14 +65,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 30972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -81,12 +81,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: c1, c2 - Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 16530 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -118,7 +118,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -126,10 +126,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join15.q.out b/ql/src/test/results/clientpositive/join15.q.out index 8fe9bb1d27..576631c9a7 100644 --- a/ql/src/test/results/clientpositive/join15.q.out +++ b/ql/src/test/results/clientpositive/join15.q.out @@ -16,28 +16,28 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -47,11 +47,11 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -66,16 +66,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join16.q.out b/ql/src/test/results/clientpositive/join16.q.out index 686b8129b2..765e5cf16d 100644 --- a/ql/src/test/results/clientpositive/join16.q.out +++ b/ql/src/test/results/clientpositive/join16.q.out @@ -13,35 +13,35 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: tab filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(value) < 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -50,14 +50,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join17.q.out b/ql/src/test/results/clientpositive/join17.q.out index f70c760177..112dc33b0a 100644 --- a/ql/src/test/results/clientpositive/join17.q.out +++ b/ql/src/test/results/clientpositive/join17.q.out @@ -34,44 +34,44 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -137,17 +137,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -178,12 +178,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: key1, value1, key2, value2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 150290 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key1, 'hll'), compute_stats(value1, 'hll'), compute_stats(key2, 'hll'), compute_stats(value2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -250,7 +250,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -288,13 +288,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/join18.q.out b/ql/src/test/results/clientpositive/join18.q.out index 9d82aa012e..6816a1562d 100644 --- a/ql/src/test/results/clientpositive/join18.q.out +++ b/ql/src/test/results/clientpositive/join18.q.out @@ -36,22 +36,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -60,7 +60,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -76,14 +76,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -93,10 +93,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2457 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2457 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -107,29 +107,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2196 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2196 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join18_multi_distinct.q.out b/ql/src/test/results/clientpositive/join18_multi_distinct.q.out index a95e9b16c4..43553cf206 100644 --- a/ql/src/test/results/clientpositive/join18_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/join18_multi_distinct.q.out @@ -38,22 +38,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -62,7 +62,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -78,14 +78,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -95,10 +95,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2561 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 2561 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -109,29 +109,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value), count(DISTINCT key) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2292 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2292 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join19.q.out b/ql/src/test/results/clientpositive/join19.q.out index a34f4caffa..4724fce10c 100644 --- a/ql/src/test/results/clientpositive/join19.q.out +++ b/ql/src/test/results/clientpositive/join19.q.out @@ -133,36 +133,36 @@ STAGE PLANS: TableScan alias: t5 filterExpr: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and subject is not null and object is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_to') and object is not null and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan alias: t6 filterExpr: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -172,7 +172,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 607 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -188,14 +188,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 607 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col3 (type: string) TableScan Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 607 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -205,7 +205,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col2 (type: string) outputColumnNames: _col1, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 667 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -221,14 +221,14 @@ STAGE PLANS: key expressions: _col5 (type: string) sort order: + Map-reduce partition columns: _col5 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 667 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string) TableScan Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 607 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -238,14 +238,14 @@ STAGE PLANS: 0 _col5 (type: string) 1 _col2 (type: string) outputColumnNames: _col1, _col3, _col4, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 733 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col8 (type: string), _col4 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 733 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 733 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -257,36 +257,36 @@ STAGE PLANS: TableScan alias: t3 filterExpr: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((predicate = 'http://www.ontosearch.com/2007/12/ontosofa-ns#_from') and object is not null and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: t4 filterExpr: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Author') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((object = 'http://ontos/OntosMiner/Common.English/ontology#Author') and (predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: subject (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -295,7 +295,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 607 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -309,36 +309,36 @@ STAGE PLANS: TableScan alias: t2 filterExpr: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: t1 filterExpr: ((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((object = 'http://ontos/OntosMiner/Common.English/ontology#Citation') and (predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and subject is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: subject (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -347,7 +347,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 607 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join2.q.out b/ql/src/test/results/clientpositive/join2.q.out index 4b8060732e..6a7284be71 100644 --- a/ql/src/test/results/clientpositive/join2.q.out +++ b/ql/src/test/results/clientpositive/join2.q.out @@ -27,35 +27,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -64,7 +64,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -80,24 +80,24 @@ STAGE PLANS: key expressions: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -107,14 +107,14 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col3 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/join20.q.out b/ql/src/test/results/clientpositive/join20.q.out index 6a072e07f3..ab7ac08cb3 100644 --- a/ql/src/test/results/clientpositive/join20.q.out +++ b/ql/src/test/results/clientpositive/join20.q.out @@ -18,37 +18,37 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src2 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -64,11 +64,11 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -83,16 +83,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -682,37 +682,37 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key < 15) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src2 filterExpr: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -728,11 +728,11 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -747,16 +747,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join21.q.out b/ql/src/test/results/clientpositive/join21.q.out index 4886609317..b7498652f1 100644 --- a/ql/src/test/results/clientpositive/join21.q.out +++ b/ql/src/test/results/clientpositive/join21.q.out @@ -15,34 +15,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src2 filterExpr: (key > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -58,11 +58,11 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -77,16 +77,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join22.q.out b/ql/src/test/results/clientpositive/join22.q.out index f4b9472d79..fc0a5501d1 100644 --- a/ql/src/test/results/clientpositive/join22.q.out +++ b/ql/src/test/results/clientpositive/join22.q.out @@ -16,36 +16,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -54,7 +54,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -70,24 +70,24 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src4 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -96,14 +96,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 113841 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 113841 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 113841 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join23.q.out b/ql/src/test/results/clientpositive/join23.q.out index c76118a46b..3dde5d5233 100644 --- a/ql/src/test/results/clientpositive/join23.q.out +++ b/ql/src/test/results/clientpositive/join23.q.out @@ -17,24 +17,24 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) TableScan alias: src2 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) Reduce Operator Tree: Join Operator @@ -44,11 +44,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -63,16 +63,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join25.q.out b/ql/src/test/results/clientpositive/join25.q.out index 2cf39a4461..a08028672a 100644 --- a/ql/src/test/results/clientpositive/join25.q.out +++ b/ql/src/test/results/clientpositive/join25.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,14 +69,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,12 +85,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -124,7 +124,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -132,10 +132,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join26.q.out b/ql/src/test/results/clientpositive/join26.q.out index 088b741b74..c2e6194506 100644 --- a/ql/src/test/results/clientpositive/join26.q.out +++ b/ql/src/test/results/clientpositive/join26.q.out @@ -50,16 +50,16 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -70,16 +70,16 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -93,16 +93,16 @@ STAGE PLANS: TableScan alias: z filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -113,17 +113,17 @@ STAGE PLANS: 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 Position of Big Table: 2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 16616 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col4 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 16616 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 16616 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -154,12 +154,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 16616 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -378,7 +378,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -416,13 +416,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/join27.q.out b/ql/src/test/results/clientpositive/join27.q.out index 13d8f72151..28b2626470 100644 --- a/ql/src/test/results/clientpositive/join27.q.out +++ b/ql/src/test/results/clientpositive/join27.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: x filterExpr: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: y filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,14 +69,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 10640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,12 +85,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7360 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -124,7 +124,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -132,10 +132,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join28.q.out b/ql/src/test/results/clientpositive/join28.q.out index ed1ab26e90..b0bf874076 100644 --- a/ql/src/test/results/clientpositive/join28.q.out +++ b/ql/src/test/results/clientpositive/join28.q.out @@ -44,14 +44,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -61,14 +61,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -81,14 +81,14 @@ STAGE PLANS: TableScan alias: z filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -98,14 +98,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -114,12 +114,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -153,7 +153,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -161,10 +161,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join29.q.out b/ql/src/test/results/clientpositive/join29.q.out index 9bb10b769e..5e7466e106 100644 --- a/ql/src/test/results/clientpositive/join29.q.out +++ b/ql/src/test/results/clientpositive/join29.q.out @@ -38,21 +38,21 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -61,7 +61,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,14 +97,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -113,12 +113,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) outputColumnNames: key, cnt1, cnt2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt1, 'hll'), compute_stats(cnt2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -152,7 +152,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -160,10 +160,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -194,14 +194,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -210,12 +210,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) outputColumnNames: key, cnt1, cnt2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt1, 'hll'), compute_stats(cnt2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -233,14 +233,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -250,14 +250,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -266,12 +266,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int) outputColumnNames: key, cnt1, cnt2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt1, 'hll'), compute_stats(cnt2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -285,21 +285,21 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -308,7 +308,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join3.q.out b/ql/src/test/results/clientpositive/join3.q.out index 800202bfcf..1217a9437f 100644 --- a/ql/src/test/results/clientpositive/join3.q.out +++ b/ql/src/test/results/clientpositive/join3.q.out @@ -27,51 +27,51 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -83,14 +83,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 118845 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 118845 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -99,12 +99,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 118845 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -136,7 +136,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -144,10 +144,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join30.q.out b/ql/src/test/results/clientpositive/join30.q.out index 059b263b09..cb07ab36c4 100644 --- a/ql/src/test/results/clientpositive/join30.q.out +++ b/ql/src/test/results/clientpositive/join30.q.out @@ -33,14 +33,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -52,14 +52,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -67,18 +67,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Local Work: @@ -89,14 +89,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -105,12 +105,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -142,7 +142,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -150,10 +150,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join31.q.out b/ql/src/test/results/clientpositive/join31.q.out index 8fda64584b..7fb56e7281 100644 --- a/ql/src/test/results/clientpositive/join31.q.out +++ b/ql/src/test/results/clientpositive/join31.q.out @@ -35,27 +35,27 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -74,19 +74,19 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -103,18 +103,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Local Work: @@ -125,14 +125,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -141,12 +141,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -178,7 +178,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -186,10 +186,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join32.q.out b/ql/src/test/results/clientpositive/join32.q.out index 1f586275ff..e80c6a0377 100644 --- a/ql/src/test/results/clientpositive/join32.q.out +++ b/ql/src/test/results/clientpositive/join32.q.out @@ -99,16 +99,16 @@ STAGE PLANS: TableScan alias: z filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col3 (type: string) @@ -118,16 +118,16 @@ STAGE PLANS: TableScan alias: x filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -140,16 +140,16 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -158,7 +158,7 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -167,17 +167,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col4 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -208,12 +208,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -432,7 +432,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -470,13 +470,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/join33.q.out b/ql/src/test/results/clientpositive/join33.q.out index d40bb049cb..bcd9d63b93 100644 --- a/ql/src/test/results/clientpositive/join33.q.out +++ b/ql/src/test/results/clientpositive/join33.q.out @@ -99,16 +99,16 @@ STAGE PLANS: TableScan alias: z filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 184500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col3 (type: string) @@ -118,16 +118,16 @@ STAGE PLANS: TableScan alias: x filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -140,16 +140,16 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -158,7 +158,7 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -167,17 +167,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col4 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -208,12 +208,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -432,7 +432,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -470,13 +470,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/join34.q.out b/ql/src/test/results/clientpositive/join34.q.out index 6181b39418..3c8ad750b1 100644 --- a/ql/src/test/results/clientpositive/join34.q.out +++ b/ql/src/test/results/clientpositive/join34.q.out @@ -56,16 +56,16 @@ STAGE PLANS: TableScan alias: x filterExpr: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -78,18 +78,18 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -98,17 +98,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -139,12 +139,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -166,18 +166,18 @@ STAGE PLANS: TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -186,17 +186,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -227,12 +227,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 8512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -402,7 +402,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -440,13 +440,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/join35.q.out b/ql/src/test/results/clientpositive/join35.q.out index 6a52d9d9d9..fcdf00d28a 100644 --- a/ql/src/test/results/clientpositive/join35.q.out +++ b/ql/src/test/results/clientpositive/join35.q.out @@ -55,24 +55,24 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -137,7 +137,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -168,16 +168,16 @@ STAGE PLANS: TableScan alias: x filterExpr: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((UDFToDouble(key) < 20.0D) or (UDFToDouble(key) > 100.0D)) and key is not null) (type: boolean) - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 16 Data size: 122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -190,7 +190,7 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -199,17 +199,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col3 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5728 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -240,12 +240,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key, value, val2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5728 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -267,7 +267,7 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -276,17 +276,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col3 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5728 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -317,12 +317,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) outputColumnNames: key, value, val2 - Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 32 Data size: 5728 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -488,7 +488,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -526,13 +526,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -556,24 +556,24 @@ STAGE PLANS: TableScan alias: x1 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -638,7 +638,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 diff --git a/ql/src/test/results/clientpositive/join36.q.out b/ql/src/test/results/clientpositive/join36.q.out index 76737acc55..aec170b316 100644 --- a/ql/src/test/results/clientpositive/join36.q.out +++ b/ql/src/test/results/clientpositive/join36.q.out @@ -75,14 +75,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 2472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 2472 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), cnt (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 2472 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -94,14 +94,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 2472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 2472 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), cnt (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 2472 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -109,14 +109,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 339 Data size: 1630 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 315 Data size: 3780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 339 Data size: 1630 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 315 Data size: 3780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 339 Data size: 1630 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 315 Data size: 3780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -125,12 +125,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: key, value, val2 - Statistics: Num rows: 339 Data size: 1630 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 315 Data size: 3780 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -164,7 +164,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -172,10 +172,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join37.q.out b/ql/src/test/results/clientpositive/join37.q.out index 8f9c8a446f..9af9a2a42e 100644 --- a/ql/src/test/results/clientpositive/join37.q.out +++ b/ql/src/test/results/clientpositive/join37.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -54,14 +54,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,14 +69,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,12 +85,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 7176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -124,7 +124,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -132,10 +132,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join38.q.out b/ql/src/test/results/clientpositive/join38.q.out index c4ddd7ac02..7761e48e95 100644 --- a/ql/src/test/results/clientpositive/join38.q.out +++ b/ql/src/test/results/clientpositive/join38.q.out @@ -65,14 +65,14 @@ STAGE PLANS: TableScan alias: b filterExpr: (UDFToDouble(col11) = 111.0D) (type: boolean) - Statistics: Num rows: 2 Data size: 126 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(col11) = 111.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col5 (type: string), col11 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -84,14 +84,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(key) = 111.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 111.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -99,18 +99,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Local Work: @@ -121,10 +121,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join39.q.out b/ql/src/test/results/clientpositive/join39.q.out index 00c37cd3a7..2106c40bf6 100644 --- a/ql/src/test/results/clientpositive/join39.q.out +++ b/ql/src/test/results/clientpositive/join39.q.out @@ -35,14 +35,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) <= 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) <= 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -53,11 +53,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -65,10 +65,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -77,12 +77,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, key1, val2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(key1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -116,7 +116,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -124,10 +124,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join4.q.out b/ql/src/test/results/clientpositive/join4.q.out index 916ffbb0e3..043553f96e 100644 --- a/ql/src/test/results/clientpositive/join4.q.out +++ b/ql/src/test/results/clientpositive/join4.q.out @@ -49,36 +49,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -88,14 +88,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,12 +104,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -141,7 +141,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -149,10 +149,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join40.q.out b/ql/src/test/results/clientpositive/join40.q.out index 86cc7403c1..ff8dac1227 100644 --- a/ql/src/test/results/clientpositive/join40.q.out +++ b/ql/src/test/results/clientpositive/join40.q.out @@ -14,33 +14,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: (UDFToDouble(key) <= 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) <= 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -50,10 +50,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -658,35 +658,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -696,14 +696,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1773,37 +1773,37 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src2 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -1819,11 +1819,11 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1838,16 +1838,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2437,37 +2437,37 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key < 15) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src2 filterExpr: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 15)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: src3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -2483,11 +2483,11 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2502,16 +2502,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3106,14 +3106,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) <= 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) <= 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -3124,11 +3124,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -3136,10 +3136,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135814 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3753,14 +3753,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -3772,29 +3772,29 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 6328 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -3804,10 +3804,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join41.q.out b/ql/src/test/results/clientpositive/join41.q.out index 08d6e365c5..deb9d396f9 100644 --- a/ql/src/test/results/clientpositive/join41.q.out +++ b/ql/src/test/results/clientpositive/join41.q.out @@ -26,33 +26,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: (UDFToDouble(key) > 10.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 10.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -62,10 +62,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -104,33 +104,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: (UDFToDouble(key) > 10.0D) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 10.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -140,10 +140,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join42.q.out b/ql/src/test/results/clientpositive/join42.q.out index 83287ca8e6..0261c82d63 100644 --- a/ql/src/test/results/clientpositive/join42.q.out +++ b/ql/src/test/results/clientpositive/join42.q.out @@ -131,17 +131,17 @@ STAGE PLANS: TableScan alias: acct filterExpr: (aid is not null and brn is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (aid is not null and brn is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: aid (type: int), acc_n (type: int), brn (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) TableScan alias: l @@ -177,7 +177,7 @@ STAGE PLANS: 1 2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -193,14 +193,14 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) TableScan Reduce Output Operator key expressions: _col3 (type: int) sort order: + Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -209,14 +209,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col3 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 69 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 69 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 69 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -228,19 +228,19 @@ STAGE PLANS: TableScan alias: la_n11 filterExpr: ((loan_id = 4436) and aid is not null and pi_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((loan_id = 4436) and aid is not null and pi_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: aid (type: int), pi_id (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: int) TableScan alias: a_n11 @@ -266,7 +266,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -282,7 +282,7 @@ STAGE PLANS: key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: int) TableScan alias: pi @@ -308,7 +308,7 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join43.q.out b/ql/src/test/results/clientpositive/join43.q.out index 5880856c58..776b3fa018 100644 --- a/ql/src/test/results/clientpositive/join43.q.out +++ b/ql/src/test/results/clientpositive/join43.q.out @@ -253,36 +253,36 @@ STAGE PLANS: TableScan alias: cart_history filterExpr: s is not null (type: boolean) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: purchase_history filterExpr: s is not null (type: boolean) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -292,16 +292,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 > _col1) (type: boolean) - Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1) keys: _col2 (type: string), _col3 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -317,7 +317,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -326,14 +326,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -347,25 +347,25 @@ STAGE PLANS: TableScan alias: events filterExpr: (s is not null and time is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s is not null and time is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -374,14 +374,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: int) 1 _col0 (type: string), _col2 (type: int) outputColumnNames: _col2 - Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -479,36 +479,36 @@ STAGE PLANS: TableScan alias: cart_history filterExpr: s is not null (type: boolean) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: purchase_history filterExpr: s is not null (type: boolean) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s is not null (type: boolean) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), time (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -518,16 +518,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 > _col1) (type: boolean) - Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1) keys: _col2 (type: string), _col3 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -543,7 +543,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) Execution mode: vectorized Reduce Operator Tree: @@ -552,10 +552,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -569,26 +569,26 @@ STAGE PLANS: TableScan alias: events filterExpr: (s is not null and time is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s is not null and time is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string), st2 (type: string), n (type: int), time (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col3 (type: int) - Statistics: Num rows: 6 Data size: 79 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int) TableScan Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -598,14 +598,14 @@ STAGE PLANS: 0 _col0 (type: string), _col3 (type: int) 1 _col0 (type: string), _col2 (type: int) outputColumnNames: _col1, _col2, _col4, _col5, _col6 - Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: string), _col5 (type: int), _col6 (type: int), _col1 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 86 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join44.q.out b/ql/src/test/results/clientpositive/join44.q.out index 470a03bf0b..dfeb36c8bf 100644 --- a/ql/src/test/results/clientpositive/join44.q.out +++ b/ql/src/test/results/clientpositive/join44.q.out @@ -31,28 +31,28 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (val1 is not null and val2 BETWEEN 2450816 AND 2451500) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (val1 is not null and val2 BETWEEN 2450816 AND 2451500) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: val1 (type: int) sort order: + Map-reduce partition columns: val1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: val2 (type: int), val3 (type: int) TableScan alias: src2 filterExpr: (val1 is not null and val2 BETWEEN 2450816 AND 2451500) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (val1 is not null and val2 BETWEEN 2450816 AND 2451500) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: val1 (type: int) sort order: + Map-reduce partition columns: val1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: val2 (type: int), val3 (type: int) Reduce Operator Tree: Join Operator @@ -62,17 +62,17 @@ STAGE PLANS: 0 val1 (type: int) 1 val1 (type: int) outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col0 = _col6) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join45.q.out b/ql/src/test/results/clientpositive/join45.q.out index cbabf7fa1a..e27dc8e602 100644 --- a/ql/src/test/results/clientpositive/join45.q.out +++ b/ql/src/test/results/clientpositive/join45.q.out @@ -25,36 +25,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -64,13 +64,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,36 +125,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -164,13 +164,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -236,32 +236,32 @@ STAGE PLANS: TableScan alias: src1 filterExpr: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src filterExpr: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -271,13 +271,13 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 110 Data size: 2103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 38830 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -337,25 +337,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -365,16 +365,16 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 4412500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0D AND 102.0D or UDFToDouble(_col3) BETWEEN 100.0D AND 102.0D) (type: boolean) - Statistics: Num rows: 9026 Data size: 173876 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9026 Data size: 3186178 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -442,25 +442,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -470,16 +470,16 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 4412500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D) and ((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D)) (type: boolean) - Statistics: Num rows: 1388 Data size: 26738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1388 Data size: 489964 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -541,25 +541,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -569,16 +569,16 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 4412500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D) or ((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D)) (type: boolean) - Statistics: Num rows: 8332 Data size: 160507 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8332 Data size: 2941196 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -642,25 +642,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -670,16 +670,16 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 4412500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (struct(_col0,_col2)) IN (const struct(100,100), const struct(101,101), const struct(102,102)) (type: boolean) - Statistics: Num rows: 9375 Data size: 180600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 625 Data size: 220625 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -734,29 +734,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -766,7 +766,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -780,18 +780,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -801,20 +801,20 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 13750 Data size: 264875 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 6519500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col4) + UDFToDouble(_col0)) >= 100.0D) (type: boolean) - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -881,29 +881,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -913,7 +913,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -927,18 +927,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -948,16 +948,16 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 13750 Data size: 264875 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 6519500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D) (type: boolean) - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1024,25 +1024,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1052,10 +1052,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 4412500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D) (type: boolean) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1071,20 +1071,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1094,13 +1094,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 329 Data size: 173712 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1167,29 +1167,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1199,7 +1199,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1213,18 +1213,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1234,16 +1234,16 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 13750 Data size: 264875 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 975 Data size: 514800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D) (type: boolean) - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 325 Data size: 171600 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1300,25 +1300,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1328,10 +1328,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12500 Data size: 240800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12500 Data size: 4412500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D) (type: boolean) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1347,20 +1347,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1370,13 +1370,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4191 Data size: 174240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1443,29 +1443,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1475,7 +1475,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1489,18 +1489,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1510,16 +1510,16 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 13750 Data size: 264875 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13125 Data size: 6758795 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D) (type: boolean) - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4375 Data size: 2253167 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1590,29 +1590,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan alias: t2 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) Reduce Operator Tree: Join Operator @@ -1622,7 +1622,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 22 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 72836 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1635,41 +1635,41 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t3 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan alias: t5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan alias: t4 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 22 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 72836 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) Reduce Operator Tree: Join Operator @@ -1683,20 +1683,20 @@ STAGE PLANS: 2 3 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 176000 Data size: 9396800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 800000 Data size: 1463999090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col0 = _col24) or ((_col1 = _col25) and (_col26 = _col20))) and ((_col12 = _col24) or ((_col27 = _col15) and (_col13 = _col25))) and ((_col6 = _col24) or ((_col28 = _col16) and (_col8 = 42)))) (type: boolean) - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450000 Data size: 823500000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: string), _col19 (type: string), _col20 (type: int), _col21 (type: float), _col22 (type: boolean), _col23 (type: string), _col24 (type: string), _col25 (type: string), _col26 (type: int), _col27 (type: float), _col28 (type: boolean), _col29 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: float), _col16 (type: boolean), _col17 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450000 Data size: 823500000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join46.q.out b/ql/src/test/results/clientpositive/join46.q.out index c192194329..368c44500c 100644 --- a/ql/src/test/results/clientpositive/join46.q.out +++ b/ql/src/test/results/clientpositive/join46.q.out @@ -60,29 +60,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -92,10 +92,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -153,33 +153,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 filterExpr: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -192,10 +192,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -254,29 +254,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 filterExpr: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -289,10 +289,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1142 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1142 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -347,29 +347,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -379,10 +379,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -435,25 +435,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -466,10 +466,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -533,25 +533,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -562,10 +562,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -632,25 +632,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -661,10 +661,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -729,25 +729,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -758,10 +758,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -822,29 +822,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -855,10 +855,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -918,25 +918,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -947,14 +947,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or (_col0 = _col3))} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1016,25 +1016,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1045,10 +1045,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1115,25 +1115,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1144,10 +1144,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1209,25 +1209,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1238,10 +1238,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1304,29 +1304,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1337,10 +1337,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1400,25 +1400,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1429,10 +1429,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1499,25 +1499,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1528,10 +1528,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1596,25 +1596,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1625,10 +1625,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1691,29 +1691,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1724,10 +1724,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1819,29 +1819,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1852,7 +1852,7 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1866,12 +1866,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) Reduce Operator Tree: Join Operator @@ -1882,10 +1882,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 residual filter predicates: {(_col1 is null or (_col10 is null and (_col7 <> _col4)))} - Statistics: Num rows: 36 Data size: 768 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 768 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1896,29 +1896,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n0 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1929,7 +1929,7 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join47.q.out b/ql/src/test/results/clientpositive/join47.q.out index 6f529d603f..dc3c765713 100644 --- a/ql/src/test/results/clientpositive/join47.q.out +++ b/ql/src/test/results/clientpositive/join47.q.out @@ -25,36 +25,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -64,13 +64,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,36 +125,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -164,13 +164,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -236,32 +236,32 @@ STAGE PLANS: TableScan alias: src1 filterExpr: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src filterExpr: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -271,13 +271,13 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 110 Data size: 2103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 38830 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -337,25 +337,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -366,13 +366,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0D AND 102.0D or UDFToDouble(_col3) BETWEEN 100.0D AND 102.0D)} - Statistics: Num rows: 9026 Data size: 173876 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9026 Data size: 3186178 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -440,25 +440,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -469,13 +469,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D)} {((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D)} - Statistics: Num rows: 1388 Data size: 26738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1388 Data size: 489964 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -537,25 +537,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -566,13 +566,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D) or ((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D))} - Statistics: Num rows: 8332 Data size: 160507 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8332 Data size: 2941196 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -636,25 +636,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -665,13 +665,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(struct(_col0,_col2)) IN (const struct(100,100), const struct(101,101), const struct(102,102))} - Statistics: Num rows: 9375 Data size: 180600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 625 Data size: 220625 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -726,29 +726,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -758,7 +758,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -772,18 +772,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -794,17 +794,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) >= 100.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -871,29 +871,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -903,7 +903,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -917,18 +917,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -939,13 +939,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1012,25 +1012,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1041,7 +1041,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1057,20 +1057,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1080,13 +1080,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 329 Data size: 173712 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1153,29 +1153,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1185,7 +1185,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1199,18 +1199,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1221,13 +1221,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 325 Data size: 171600 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1284,25 +1284,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1313,7 +1313,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1329,20 +1329,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1352,13 +1352,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4191 Data size: 174240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1425,29 +1425,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1457,7 +1457,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1471,18 +1471,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1493,13 +1493,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4375 Data size: 2253167 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1570,29 +1570,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan alias: t2 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) Reduce Operator Tree: Join Operator @@ -1602,7 +1602,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 22 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 72836 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1615,41 +1615,41 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t3 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan alias: t5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan alias: t4 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 22 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 72836 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) Reduce Operator Tree: Join Operator @@ -1664,17 +1664,17 @@ STAGE PLANS: 3 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 residual filter predicates: {((_col6 = _col24) or ((_col28 = _col16) and (_col8 = 42)))} {((_col12 = _col24) or ((_col27 = _col15) and (_col13 = _col25)))} {((_col0 = _col24) or ((_col1 = _col25) and (_col26 = _col20)))} - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450000 Data size: 823500000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: string), _col19 (type: string), _col20 (type: int), _col21 (type: float), _col22 (type: boolean), _col23 (type: string), _col24 (type: string), _col25 (type: string), _col26 (type: int), _col27 (type: float), _col28 (type: boolean), _col29 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: float), _col16 (type: boolean), _col17 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450000 Data size: 823500000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join5.q.out b/ql/src/test/results/clientpositive/join5.q.out index 49dd968dd3..ad8daeb5df 100644 --- a/ql/src/test/results/clientpositive/join5.q.out +++ b/ql/src/test/results/clientpositive/join5.q.out @@ -49,36 +49,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -88,14 +88,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,12 +104,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -141,7 +141,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -149,10 +149,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join6.q.out b/ql/src/test/results/clientpositive/join6.q.out index 055eee2c26..9462658ef3 100644 --- a/ql/src/test/results/clientpositive/join6.q.out +++ b/ql/src/test/results/clientpositive/join6.q.out @@ -49,36 +49,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -88,14 +88,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 19936 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 11072 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 11072 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,12 +104,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 11072 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -141,7 +141,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -149,10 +149,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join7.q.out b/ql/src/test/results/clientpositive/join7.q.out index 0339c90fad..ddd61d641d 100644 --- a/ql/src/test/results/clientpositive/join7.q.out +++ b/ql/src/test/results/clientpositive/join7.q.out @@ -59,53 +59,53 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src3 filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -117,14 +117,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 29370 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string), UDFToInteger(_col4) (type: int), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 15675 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 15675 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -133,12 +133,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: int), _col5 (type: string) outputColumnNames: c1, c2, c3, c4, c5, c6 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 15675 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -170,7 +170,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -178,10 +178,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join8.q.out b/ql/src/test/results/clientpositive/join8.q.out index c9c8833ee2..99552863c7 100644 --- a/ql/src/test/results/clientpositive/join8.q.out +++ b/ql/src/test/results/clientpositive/join8.q.out @@ -49,36 +49,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) > 10.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -88,17 +88,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is null (type: boolean) - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -107,12 +107,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -144,7 +144,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -152,10 +152,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join9.q.out b/ql/src/test/results/clientpositive/join9.q.out index e02572693e..af08918e7f 100644 --- a/ql/src/test/results/clientpositive/join9.q.out +++ b/ql/src/test/results/clientpositive/join9.q.out @@ -34,43 +34,43 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((ds = '2008-04-08') and (hr = '12') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 133500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 133500 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -186,17 +186,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -227,12 +227,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -299,7 +299,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -337,13 +337,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/join_alt_syntax.q.out b/ql/src/test/results/clientpositive/join_alt_syntax.q.out index 57a9109bf7..85f99da489 100644 --- a/ql/src/test/results/clientpositive/join_alt_syntax.q.out +++ b/ql/src/test/results/clientpositive/join_alt_syntax.q.out @@ -15,25 +15,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: p2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -43,10 +43,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 676 Data size: 163592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 676 Data size: 163592 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -77,51 +77,51 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -132,10 +132,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 10164 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 10164 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -166,51 +166,51 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: part filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -221,10 +221,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 10164 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 10164 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -257,36 +257,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -295,7 +295,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -309,18 +309,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -330,17 +330,17 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 702 Data size: 260442 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 + _col3) = _col3) (type: boolean) - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 130221 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 127413 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 127413 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -375,36 +375,36 @@ STAGE PLANS: TableScan alias: p1 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: p4 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -414,7 +414,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -430,14 +430,14 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Reduce Operator Tree: Join Operator @@ -447,14 +447,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col1, _col3, _col5, _col6 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 14036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: string), _col6 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 14036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 14036 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -466,36 +466,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -504,7 +504,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -541,36 +541,36 @@ STAGE PLANS: TableScan alias: p1 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: p4 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -580,7 +580,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -596,14 +596,14 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Reduce Operator Tree: Join Operator @@ -613,14 +613,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col1, _col3, _col5, _col6 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 14036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: string), _col6 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 14036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 14036 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -632,36 +632,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -670,7 +670,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 6642 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out index dc2de9f01f..0160bdd9f2 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out @@ -15,53 +15,53 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -73,10 +73,10 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -105,53 +105,53 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -163,10 +163,10 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -197,36 +197,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -236,7 +236,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -250,18 +250,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -271,17 +271,17 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 702 Data size: 1303614 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 + _col18) = _col18) (type: boolean) - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 651807 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 651807 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 651807 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -312,36 +312,36 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: ((p_partkey = 1) and p_name is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_partkey = 1) and p_name is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -351,7 +351,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1234 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -365,18 +365,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1234 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -386,14 +386,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 48178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 48282 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 48282 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out index 741b11f371..5341795df2 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_2.q.out @@ -16,36 +16,36 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p4 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -55,7 +55,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -69,43 +69,43 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reduce Operator Tree: Join Operator @@ -117,14 +117,14 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -157,36 +157,36 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -196,7 +196,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -212,14 +212,14 @@ STAGE PLANS: key expressions: _col9 (type: int), _col10 (type: string) sort order: ++ Map-reduce partition columns: _col9 (type: int), _col10 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reduce Operator Tree: Join Operator @@ -229,14 +229,14 @@ STAGE PLANS: 0 _col9 (type: int), _col10 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -248,36 +248,36 @@ STAGE PLANS: TableScan alias: p1 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p4 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -287,7 +287,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out index c157212b91..2ca850ff69 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out @@ -17,53 +17,53 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -75,10 +75,10 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -109,53 +109,53 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -167,10 +167,10 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 51996 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -203,36 +203,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -242,7 +242,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -256,18 +256,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -277,17 +277,17 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 702 Data size: 1303614 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 + _col18) = _col18) (type: boolean) - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 651807 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 651807 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 364 Data size: 89415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 351 Data size: 651807 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -320,36 +320,36 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: ((p_partkey = 1) and p_name is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_partkey = 1) and p_name is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -359,7 +359,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1234 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -373,18 +373,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1234 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -394,14 +394,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 48178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 48282 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 728 Data size: 178830 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 48282 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out index f35d397f2a..3275cf6566 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out @@ -18,36 +18,36 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p4 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -57,7 +57,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -71,43 +71,43 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reduce Operator Tree: Join Operator @@ -119,14 +119,14 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 61 Data size: 7614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -161,36 +161,36 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -200,7 +200,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -216,14 +216,14 @@ STAGE PLANS: key expressions: _col9 (type: int), _col10 (type: string) sort order: ++ Map-reduce partition columns: _col9 (type: int), _col10 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) Reduce Operator Tree: Join Operator @@ -233,14 +233,14 @@ STAGE PLANS: 0 _col9 (type: int), _col10 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 71804 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -252,36 +252,36 @@ STAGE PLANS: TableScan alias: p1 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p4 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -291,7 +291,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 33426 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out index 5c2dee3197..db00208abb 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual1.q.out @@ -71,53 +71,53 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -129,14 +129,14 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -165,53 +165,53 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -223,14 +223,14 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -261,36 +261,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -300,7 +300,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -314,18 +314,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -335,17 +335,17 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 + _col18) = _col18) (type: boolean) - Statistics: Num rows: 13 Data size: 1586 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 24076 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 13 Data size: 1586 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 24076 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 1586 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 24076 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -376,36 +376,36 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: ((p2_partkey = 1) and p2_name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((p2_partkey = 1) and p2_name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -415,7 +415,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -429,18 +429,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -450,14 +450,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out index 3d6af2d769..1d5cfde0e7 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual2.q.out @@ -71,70 +71,70 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p4 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -148,14 +148,14 @@ STAGE PLANS: 2 _col1 (type: string) 3 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 85 Data size: 10385 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 85 Data size: 53110 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 85 Data size: 10385 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 85 Data size: 53110 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 85 Data size: 10385 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 85 Data size: 53110 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -188,36 +188,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: (p2_name is not null and p2_partkey is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (p2_name is not null and p2_partkey is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -227,7 +227,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -243,24 +243,24 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -270,7 +270,7 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3461 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -286,24 +286,24 @@ STAGE PLANS: key expressions: _col18 (type: int) sort order: + Map-reduce partition columns: _col18 (type: int) - Statistics: Num rows: 28 Data size: 3461 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) TableScan alias: p4 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -313,14 +313,14 @@ STAGE PLANS: 0 _col18 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3807 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out index 0ce23ae335..ac20d5ee6d 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual3.q.out @@ -73,53 +73,53 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -131,14 +131,14 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -169,53 +169,53 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -227,14 +227,14 @@ STAGE PLANS: 1 _col1 (type: string) 2 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -267,36 +267,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -306,7 +306,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -320,18 +320,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -341,17 +341,17 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col0 + _col18) = _col18) (type: boolean) - Statistics: Num rows: 13 Data size: 1586 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 24076 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 13 Data size: 1586 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 24076 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 1586 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 24076 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -384,36 +384,36 @@ STAGE PLANS: TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p2 filterExpr: ((p2_partkey = 1) and p2_name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((p2_partkey = 1) and p2_name is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -423,7 +423,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -437,18 +437,18 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -458,14 +458,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 3173 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 26 Data size: 48152 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out index a7dfc2c422..b69064b3da 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual4.q.out @@ -73,70 +73,70 @@ STAGE PLANS: TableScan alias: p2 filterExpr: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p2_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p4 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -150,14 +150,14 @@ STAGE PLANS: 2 _col1 (type: string) 3 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 85 Data size: 10385 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 85 Data size: 53110 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 85 Data size: 10385 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 85 Data size: 53110 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 85 Data size: 10385 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 85 Data size: 53110 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -192,36 +192,36 @@ STAGE PLANS: TableScan alias: p2 filterExpr: (p2_name is not null and p2_partkey is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (p2_name is not null and p2_partkey is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p2_partkey (type: int), p2_name (type: string), p2_mfgr (type: string), p2_brand (type: string), p2_type (type: string), p2_size (type: int), p2_container (type: string), p2_retailprice (type: double), p2_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) TableScan alias: p3 filterExpr: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: p3_name is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p3_partkey (type: int), p3_name (type: string), p3_mfgr (type: string), p3_brand (type: string), p3_type (type: string), p3_size (type: int), p3_container (type: string), p3_retailprice (type: double), p3_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1120 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -231,7 +231,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -247,24 +247,24 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string) TableScan alias: p1 filterExpr: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_name is not null and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -274,7 +274,7 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26 - Statistics: Num rows: 28 Data size: 3461 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -290,24 +290,24 @@ STAGE PLANS: key expressions: _col18 (type: int) sort order: + Map-reduce partition columns: _col18 (type: int) - Statistics: Num rows: 28 Data size: 3461 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string) TableScan alias: p4 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reduce Operator Tree: Join Operator @@ -317,14 +317,14 @@ STAGE PLANS: 0 _col18 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35 - Statistics: Num rows: 30 Data size: 3807 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 3807 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 30 Data size: 19473 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual5.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual5.q.out index d80bbf17ee..10f5768122 100644 --- a/ql/src/test/results/clientpositive/join_cond_pushdown_unqual5.q.out +++ b/ql/src/test/results/clientpositive/join_cond_pushdown_unqual5.q.out @@ -51,29 +51,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: l - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: index (type: int), la (type: int), lk1 (type: string), lk2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string), _col3 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int) TableScan alias: r - Statistics: Num rows: 2 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ra (type: int), rk1 (type: string), rk2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 2 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -83,13 +83,13 @@ STAGE PLANS: 0 _col2 (type: string), _col3 (type: string) 1 _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (COALESCE(_col1,'EMPTY') = COALESCE(_col4,'EMPTY')) (type: boolean) - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -132,11 +132,11 @@ STAGE PLANS: $hdt$_1:r TableScan alias: r - Statistics: Num rows: 2 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ra (type: int), rk1 (type: string), rk2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 47 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col2 (type: string), _col3 (type: string) @@ -147,11 +147,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: l - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: index (type: int), la (type: int), lk1 (type: string), lk2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -159,13 +159,13 @@ STAGE PLANS: 0 _col2 (type: string), _col3 (type: string) 1 _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2 Data size: 57 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 772 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (COALESCE(_col1,'EMPTY') = COALESCE(_col4,'EMPTY')) (type: boolean) - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_emit_interval.q.out b/ql/src/test/results/clientpositive/join_emit_interval.q.out index 6b8178db27..384c5e8ff4 100644 --- a/ql/src/test/results/clientpositive/join_emit_interval.q.out +++ b/ql/src/test/results/clientpositive/join_emit_interval.q.out @@ -60,29 +60,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n7 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n4 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -95,10 +95,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -152,25 +152,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n7 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n4 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -183,10 +183,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_filters_overlap.q.out b/ql/src/test/results/clientpositive/join_filters_overlap.q.out index 6557cac9f4..bd96c29308 100644 --- a/ql/src/test/results/clientpositive/join_filters_overlap.q.out +++ b/ql/src/test/results/clientpositive/join_filters_overlap.q.out @@ -33,62 +33,62 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n4 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: b filterExpr: (value = 50) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 50) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 50 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: c filterExpr: (value = 60) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 60) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 60 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 2 value expressions: _col1 (type: int) auto parallelism: false @@ -162,13 +162,13 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -238,61 +238,61 @@ STAGE PLANS: TableScan alias: a_n4 filterExpr: (value = 50) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 50) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 50 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: b - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: c filterExpr: (value = 60) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 60) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 60 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 2 value expressions: _col1 (type: int) auto parallelism: false @@ -366,13 +366,13 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -442,61 +442,61 @@ STAGE PLANS: TableScan alias: a_n4 filterExpr: (value = 50) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 50) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 50 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: b - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: c filterExpr: (value = 60) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 60) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 60 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 2 value expressions: _col1 (type: int) auto parallelism: false @@ -570,13 +570,13 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -647,79 +647,79 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n4 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: b - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: c filterExpr: (value = 60) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 60) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 60 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 2 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: d filterExpr: (value = 40) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 40 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 3 value expressions: _col1 (type: int) auto parallelism: false @@ -797,13 +797,13 @@ STAGE PLANS: 2 _col0 (type: int) 3 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9 Data size: 59 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 9 Data size: 59 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -866,84 +866,84 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a_n4 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: int), value (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: b filterExpr: (value = 50) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 50) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 50 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: c filterExpr: (value = 60) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 60) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 60 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 2 value expressions: _col1 (type: int) auto parallelism: false TableScan alias: d filterExpr: (value = 40) (type: boolean) - Statistics: Num rows: 3 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), 40 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE tag: 3 value expressions: _col1 (type: int) auto parallelism: false @@ -1020,13 +1020,13 @@ STAGE PLANS: 2 _col0 (type: int) 3 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9 Data size: 59 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 9 Data size: 59 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/join_grp_diff_keys.q.out b/ql/src/test/results/clientpositive/join_grp_diff_keys.q.out index 063392357a..fe0e573580 100644 --- a/ql/src/test/results/clientpositive/join_grp_diff_keys.q.out +++ b/ql/src/test/results/clientpositive/join_grp_diff_keys.q.out @@ -58,67 +58,67 @@ STAGE PLANS: TableScan alias: foo filterExpr: ((orders <> 'blah') and id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((orders <> 'blah') and id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int), line_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE TableScan alias: bar filterExpr: (id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int), line_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TableScan alias: split filterExpr: (id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int), line_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TableScan alias: forecast filterExpr: (id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id is not null and line_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int), line_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -131,13 +131,13 @@ STAGE PLANS: 2 _col0 (type: int), _col1 (type: int) 3 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 633 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 633 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -153,7 +153,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 633 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -162,10 +162,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_hive_626.q.out b/ql/src/test/results/clientpositive/join_hive_626.q.out index 81e48bca14..14692064a3 100644 --- a/ql/src/test/results/clientpositive/join_hive_626.q.out +++ b/ql/src/test/results/clientpositive/join_hive_626.q.out @@ -76,36 +76,36 @@ STAGE PLANS: TableScan alias: hive_bar filterExpr: (foo_id is not null and bar_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 230 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (bar_id is not null and foo_id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 230 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bar_id (type: int), foo_id (type: int), bar_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 230 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 230 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: hive_foo filterExpr: foo_id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: foo_id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo_id (type: int), foo_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -115,7 +115,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 1 Data size: 253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -131,24 +131,24 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 211 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col4 (type: string) TableScan alias: hive_count filterExpr: bar_id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: bar_id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bar_id (type: int), n (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -158,14 +158,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col4, _col6 - Statistics: Num rows: 1 Data size: 278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col4 (type: string), _col2 (type: string), _col6 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_map_ppr.q.out b/ql/src/test/results/clientpositive/join_map_ppr.q.out index 585f6c3425..9d285b1f43 100644 --- a/ql/src/test/results/clientpositive/join_map_ppr.q.out +++ b/ql/src/test/results/clientpositive/join_map_ppr.q.out @@ -46,12 +46,12 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -62,12 +62,12 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -81,12 +81,12 @@ STAGE PLANS: TableScan alias: z filterExpr: (key is not null and (ds = '2008-04-08') and (hr = 11)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -97,17 +97,17 @@ STAGE PLANS: 2 key (type: string) outputColumnNames: _col0, _col6, _col11 Position of Big Table: 2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 195800 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 195800 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 195800 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -138,7 +138,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 195800 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash @@ -687,12 +687,12 @@ STAGE PLANS: TableScan alias: x filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 UDFToDouble(key) (type: double) @@ -703,12 +703,12 @@ STAGE PLANS: TableScan alias: y filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 UDFToDouble(key) (type: double) @@ -722,12 +722,12 @@ STAGE PLANS: TableScan alias: z filterExpr: (UDFToDouble(key) is not null and (ds = '2008-04-08') and (hr = 11)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -738,17 +738,17 @@ STAGE PLANS: 2 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col6, _col11 Position of Big Table: 2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 104500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 104500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 104500 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -779,7 +779,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 104500 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out b/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out index 75cf433d73..e739182ec6 100644 --- a/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out +++ b/ql/src/test/results/clientpositive/join_merge_multi_expressions.q.out @@ -16,51 +16,51 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), hr (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL TableScan alias: b filterExpr: (key is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), hr (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL TableScan alias: c filterExpr: (hr is not null and key is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), hr (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 542000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Operator Tree: Join Operator condition map: @@ -70,12 +70,12 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) 2 _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80115 Data size: 640920 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -89,7 +89,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -97,10 +97,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_merging.q.out b/ql/src/test/results/clientpositive/join_merging.q.out index 0e46d6c809..5cb20f1c0f 100644 --- a/ql/src/test/results/clientpositive/join_merging.q.out +++ b/ql/src/test/results/clientpositive/join_merging.q.out @@ -19,45 +19,45 @@ STAGE PLANS: TableScan alias: p1 filterExpr: (p_size > 10) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (p_size > 10) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_size (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: p2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_size (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: p3 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -68,14 +68,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col1, _col3 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -108,49 +108,49 @@ STAGE PLANS: TableScan alias: p1 filterExpr: ((p_size > 10) and p_partkey is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_size > 10) and p_partkey is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_size (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: p2 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int), p_size (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: p3 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -162,14 +162,14 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col1, _col3 residual filter predicates: {(_col1 > (_col3 + 10))} - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_on_varchar.q.out b/ql/src/test/results/clientpositive/join_on_varchar.q.out index becd16afe7..2bfc46e17a 100644 --- a/ql/src/test/results/clientpositive/join_on_varchar.q.out +++ b/ql/src/test/results/clientpositive/join_on_varchar.q.out @@ -75,14 +75,14 @@ STAGE PLANS: TableScan alias: tbl2_n2 filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c2 (type: varchar(30)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: varchar(30)) @@ -94,14 +94,14 @@ STAGE PLANS: TableScan alias: tbl1_n3 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: varchar(10)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -109,11 +109,11 @@ STAGE PLANS: 0 _col0 (type: varchar(30)) 1 _col0 (type: varchar(30)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: varchar(10)), _col1 (type: varchar(30)) sort order: ++ - Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -121,10 +121,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: varchar(10)), KEY.reducesinkkey1 (type: varchar(30)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_parse.q.out b/ql/src/test/results/clientpositive/join_parse.q.out index 77ae41d57b..fb99452ee4 100644 --- a/ql/src/test/results/clientpositive/join_parse.q.out +++ b/ql/src/test/results/clientpositive/join_parse.q.out @@ -20,36 +20,36 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -58,7 +58,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -74,24 +74,24 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string) TableScan alias: src1 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -100,14 +100,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -141,36 +141,36 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -179,7 +179,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -195,24 +195,24 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string) TableScan alias: src1 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -221,14 +221,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -262,36 +262,36 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -300,7 +300,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -316,24 +316,24 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string) TableScan alias: src1 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -342,14 +342,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5153 Data size: 917234 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -386,36 +386,36 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -424,7 +424,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -440,14 +440,14 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 563192 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 71981 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -456,14 +456,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col4 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8152 Data size: 1451056 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8152 Data size: 1451056 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8152 Data size: 1451056 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -475,36 +475,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -513,7 +513,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 71981 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/join_rc.q.out b/ql/src/test/results/clientpositive/join_rc.q.out index 84644dffe4..cb3cd06bee 100644 --- a/ql/src/test/results/clientpositive/join_rc.q.out +++ b/ql/src/test/results/clientpositive/join_rc.q.out @@ -53,35 +53,35 @@ STAGE PLANS: TableScan alias: join_rc1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: join_rc2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -91,14 +91,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_reorder.q.out b/ql/src/test/results/clientpositive/join_reorder.q.out index 95cbe87025..21d7846e12 100644 --- a/ql/src/test/results/clientpositive/join_reorder.q.out +++ b/ql/src/test/results/clientpositive/join_reorder.q.out @@ -63,28 +63,28 @@ STAGE PLANS: TableScan alias: a filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(key) (type: double) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string), val (type: string) TableScan alias: c filterExpr: (key + 1) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key + 1) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (key + 1) (type: double) sort order: + Map-reduce partition columns: (key + 1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -94,14 +94,14 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double) 1 (key + 1) (type: double) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -130,28 +130,28 @@ STAGE PLANS: TableScan alias: a filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(key) (type: double) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string), val (type: string) TableScan alias: c filterExpr: (key + 1) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key + 1) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (key + 1) (type: double) sort order: + Map-reduce partition columns: (key + 1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -161,14 +161,14 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double) 1 (key + 1) (type: double) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -233,21 +233,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -256,7 +256,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -272,16 +272,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col5 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: val (type: string) sort order: + Map-reduce partition columns: val (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -290,14 +290,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 val (type: string) outputColumnNames: _col0, _col1, _col5, _col11 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col1 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -330,21 +330,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -353,7 +353,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -369,16 +369,16 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col5 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: val (type: string) sort order: + Map-reduce partition columns: val (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -387,14 +387,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 val (type: string) outputColumnNames: _col0, _col1, _col5, _col11 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col1 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -472,28 +472,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), val (type: string) sort order: ++ Map-reduce partition columns: key (type: string), val (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), val (type: string) sort order: ++ Map-reduce partition columns: key (type: string), val (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), val (type: string) sort order: ++ Map-reduce partition columns: key (type: string), val (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -505,14 +505,14 @@ STAGE PLANS: 1 key (type: string), val (type: string) 2 key (type: string), val (type: string) outputColumnNames: _col0, _col5, _col10 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col10 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -546,28 +546,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), val (type: string) sort order: ++ Map-reduce partition columns: key (type: string), val (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), val (type: string) sort order: ++ Map-reduce partition columns: key (type: string), val (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string), val (type: string) sort order: ++ Map-reduce partition columns: key (type: string), val (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -579,14 +579,14 @@ STAGE PLANS: 1 key (type: string), val (type: string) 2 key (type: string), val (type: string) outputColumnNames: _col0, _col5, _col10 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col10 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_reorder2.q.out b/ql/src/test/results/clientpositive/join_reorder2.q.out index 34b5f55b4f..94cffad791 100644 --- a/ql/src/test/results/clientpositive/join_reorder2.q.out +++ b/ql/src/test/results/clientpositive/join_reorder2.q.out @@ -85,54 +85,54 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: d filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -146,14 +146,14 @@ STAGE PLANS: 2 key (type: string) 3 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -211,28 +211,28 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null and (key + 1) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key + 1) is not null and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b filterExpr: (key is not null and (key + 1) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key + 1) is not null and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -242,7 +242,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -258,20 +258,20 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) TableScan alias: c filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: val (type: string) sort order: + Map-reduce partition columns: val (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -281,7 +281,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 val (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -297,20 +297,20 @@ STAGE PLANS: key expressions: (_col0 + 1) (type: double) sort order: + Map-reduce partition columns: (_col0 + 1) (type: double) - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) TableScan alias: d filterExpr: (key + 1) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key + 1) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: (key + 1) (type: double) sort order: + Map-reduce partition columns: (key + 1) (type: double) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string), val (type: string) Reduce Operator Tree: Join Operator @@ -320,14 +320,14 @@ STAGE PLANS: 0 (_col0 + 1) (type: double) 1 (key + 1) (type: double) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16 - Statistics: Num rows: 1 Data size: 399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_reorder3.q.out b/ql/src/test/results/clientpositive/join_reorder3.q.out index e1c1068f9b..31ebc7e217 100644 --- a/ql/src/test/results/clientpositive/join_reorder3.q.out +++ b/ql/src/test/results/clientpositive/join_reorder3.q.out @@ -85,54 +85,54 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: d filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -146,14 +146,14 @@ STAGE PLANS: 2 key (type: string) 3 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -211,28 +211,28 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null and (key + 1) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key + 1) is not null and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b filterExpr: (key is not null and (key + 1) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key + 1) is not null and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -242,7 +242,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -258,20 +258,20 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string) TableScan alias: c filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: val (type: string) sort order: + Map-reduce partition columns: val (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -281,7 +281,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 val (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -297,20 +297,20 @@ STAGE PLANS: key expressions: (_col0 + 1) (type: double) sort order: + Map-reduce partition columns: (_col0 + 1) (type: double) - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) TableScan alias: d filterExpr: (key + 1) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key + 1) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: (key + 1) (type: double) sort order: + Map-reduce partition columns: (key + 1) (type: double) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string), val (type: string) Reduce Operator Tree: Join Operator @@ -320,14 +320,14 @@ STAGE PLANS: 0 (_col0 + 1) (type: double) 1 (key + 1) (type: double) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16 - Statistics: Num rows: 1 Data size: 399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 399 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_reorder4.q.out b/ql/src/test/results/clientpositive/join_reorder4.q.out index 963f4f0423..2c0f4e8705 100644 --- a/ql/src/test/results/clientpositive/join_reorder4.q.out +++ b/ql/src/test/results/clientpositive/join_reorder4.q.out @@ -61,41 +61,41 @@ STAGE PLANS: TableScan alias: a filterExpr: key1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key1 (type: string) sort order: + Map-reduce partition columns: key1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val1 (type: string) TableScan alias: b filterExpr: key2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key2 (type: string) sort order: + Map-reduce partition columns: key2 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val2 (type: string) TableScan alias: c filterExpr: key3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key3 (type: string) sort order: + Map-reduce partition columns: key3 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val3 (type: string) Reduce Operator Tree: Join Operator @@ -107,14 +107,14 @@ STAGE PLANS: 1 key2 (type: string) 2 key3 (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -154,41 +154,41 @@ STAGE PLANS: TableScan alias: a filterExpr: key1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key1 (type: string) sort order: + Map-reduce partition columns: key1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val1 (type: string) TableScan alias: b filterExpr: key2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key2 (type: string) sort order: + Map-reduce partition columns: key2 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val2 (type: string) TableScan alias: c filterExpr: key3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key3 (type: string) sort order: + Map-reduce partition columns: key3 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val3 (type: string) Reduce Operator Tree: Join Operator @@ -200,14 +200,14 @@ STAGE PLANS: 1 key2 (type: string) 2 key3 (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -247,41 +247,41 @@ STAGE PLANS: TableScan alias: a filterExpr: key1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key1 (type: string) sort order: + Map-reduce partition columns: key1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val1 (type: string) TableScan alias: b filterExpr: key2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key2 (type: string) sort order: + Map-reduce partition columns: key2 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val2 (type: string) TableScan alias: c filterExpr: key3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key3 (type: string) sort order: + Map-reduce partition columns: key3 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val3 (type: string) Reduce Operator Tree: Join Operator @@ -293,14 +293,14 @@ STAGE PLANS: 1 key2 (type: string) 2 key3 (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_star.q.out b/ql/src/test/results/clientpositive/join_star.q.out index df97d43cae..80e9314414 100644 --- a/ql/src/test/results/clientpositive/join_star.q.out +++ b/ql/src/test/results/clientpositive/join_star.q.out @@ -147,14 +147,14 @@ STAGE PLANS: TableScan alias: dim1 filterExpr: f1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: f1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f1 (type: int), f2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col2 (type: int) @@ -166,14 +166,14 @@ STAGE PLANS: TableScan alias: fact filterExpr: d1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: d1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: m1 (type: int), m2 (type: int), d1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -181,14 +181,14 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 1 Data size: 1078 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col4 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1078 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1078 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -247,14 +247,14 @@ STAGE PLANS: TableScan alias: dim1 filterExpr: f1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: f1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f1 (type: int), f2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col2 (type: int) @@ -263,14 +263,14 @@ STAGE PLANS: TableScan alias: dim2 filterExpr: f3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: f3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f3 (type: int), f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col3 (type: int) @@ -282,14 +282,14 @@ STAGE PLANS: TableScan alias: fact filterExpr: (d1 is not null and d2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (d1 is not null and d2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: m1 (type: int), m2 (type: int), d1 (type: int), d2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -297,7 +297,7 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col5 - Statistics: Num rows: 1 Data size: 1078 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -305,14 +305,14 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col5, _col7 - Statistics: Num rows: 1 Data size: 1185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -373,14 +373,14 @@ STAGE PLANS: TableScan alias: dim1 filterExpr: (f1 is not null and f2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (f1 is not null and f2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f1 (type: int), f2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -389,14 +389,14 @@ STAGE PLANS: TableScan alias: fact filterExpr: d1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: d1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: m1 (type: int), m2 (type: int), d1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -408,14 +408,14 @@ STAGE PLANS: TableScan alias: dim2 filterExpr: f3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: f3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f3 (type: int), f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -423,7 +423,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -431,14 +431,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col2 (type: int) outputColumnNames: _col1, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col4 (type: int), _col5 (type: int), _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -498,11 +498,11 @@ STAGE PLANS: $hdt$_1:dim1 TableScan alias: dim1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f1 (type: int), f2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col2 (type: int) @@ -510,11 +510,11 @@ STAGE PLANS: $hdt$_2:dim2 TableScan alias: dim2 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f3 (type: int), f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col4 (type: int) @@ -525,11 +525,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: fact - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: m1 (type: int), m2 (type: int), d1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -537,7 +537,7 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 1 Data size: 1078 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -545,14 +545,14 @@ STAGE PLANS: 0 _col4 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col4, _col6 - Statistics: Num rows: 1 Data size: 1185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col4 (type: int), _col6 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -643,11 +643,11 @@ STAGE PLANS: $hdt$_1:dim1 TableScan alias: dim1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f1 (type: int), f2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col2 (type: int) @@ -655,11 +655,11 @@ STAGE PLANS: $hdt$_2:dim2 TableScan alias: dim2 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f3 (type: int), f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col5 (type: int) @@ -667,11 +667,11 @@ STAGE PLANS: $hdt$_3:dim3 TableScan alias: dim3 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f5 (type: int), f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col3 (type: int) @@ -679,11 +679,11 @@ STAGE PLANS: $hdt$_4:dim4 TableScan alias: dim4 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f7 (type: int), f8 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col9 (type: int) @@ -691,11 +691,11 @@ STAGE PLANS: $hdt$_5:dim5 TableScan alias: dim5 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f9 (type: int), f10 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col11 (type: int) @@ -703,11 +703,11 @@ STAGE PLANS: $hdt$_6:dim6 TableScan alias: dim6 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f11 (type: int), f12 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col9 (type: int) @@ -715,11 +715,11 @@ STAGE PLANS: $hdt$_7:dim7 TableScan alias: dim7 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f13 (type: int), f14 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col15 (type: int) @@ -730,11 +730,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: fact - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: m1 (type: int), m2 (type: int), d1 (type: int), d2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -742,7 +742,7 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col5 - Statistics: Num rows: 1 Data size: 1078 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -750,7 +750,7 @@ STAGE PLANS: 0 _col5 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col5, _col7 - Statistics: Num rows: 1 Data size: 1185 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -758,7 +758,7 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col5, _col7, _col9 - Statistics: Num rows: 1 Data size: 1303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -766,7 +766,7 @@ STAGE PLANS: 0 _col9 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11 - Statistics: Num rows: 1 Data size: 1433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -774,7 +774,7 @@ STAGE PLANS: 0 _col11 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13 - Statistics: Num rows: 1 Data size: 1576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 22 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -782,7 +782,7 @@ STAGE PLANS: 0 _col9 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15 - Statistics: Num rows: 1 Data size: 1733 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -790,14 +790,14 @@ STAGE PLANS: 0 _col15 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col5, _col7, _col9, _col11, _col13, _col15, _col17 - Statistics: Num rows: 1 Data size: 1906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col7 (type: int), _col9 (type: int), _col11 (type: int), _col13 (type: int), _col15 (type: int), _col17 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 26 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_thrift.q.out b/ql/src/test/results/clientpositive/join_thrift.q.out index 578aaff3a7..da687eb609 100644 --- a/ql/src/test/results/clientpositive/join_thrift.q.out +++ b/ql/src/test/results/clientpositive/join_thrift.q.out @@ -37,27 +37,27 @@ STAGE PLANS: TableScan alias: s1 filterExpr: aint is not null (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: aint is not null (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: aint (type: int) sort order: + Map-reduce partition columns: aint (type: int) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE TableScan alias: s2 filterExpr: aint is not null (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 28204 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: aint is not null (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 28204 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: aint (type: int) sort order: + Map-reduce partition columns: aint (type: int) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 28204 Basic stats: COMPLETE Column stats: NONE value expressions: lintstring (type: array>) Reduce Operator Tree: Join Operator @@ -67,14 +67,14 @@ STAGE PLANS: 0 aint (type: int) 1 aint (type: int) outputColumnNames: _col0, _col17 - Statistics: Num rows: 12 Data size: 33770 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col17 (type: array>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 33770 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 33770 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_vc.q.out b/ql/src/test/results/clientpositive/join_vc.q.out index 7ae3801d01..22e34c304b 100644 --- a/ql/src/test/results/clientpositive/join_vc.q.out +++ b/ql/src/test/results/clientpositive/join_vc.q.out @@ -15,35 +15,35 @@ STAGE PLANS: TableScan alias: t1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2 filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -53,7 +53,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 71981 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -69,23 +69,23 @@ STAGE PLANS: key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 71981 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t3 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -95,11 +95,11 @@ STAGE PLANS: 0 _col2 (type: string) 1 _col1 (type: string) outputColumnNames: _col3, _col4, _col5 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 239568 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: bigint), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 239568 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -114,20 +114,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 239568 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1288 Data size: 239568 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -170,35 +170,35 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2 filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -208,11 +208,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -227,16 +227,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1328 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/join_view.q.out b/ql/src/test/results/clientpositive/join_view.q.out index 5fc5c6fd64..ed4e09d40e 100644 --- a/ql/src/test/results/clientpositive/join_view.q.out +++ b/ql/src/test/results/clientpositive/join_view.q.out @@ -55,34 +55,34 @@ STAGE PLANS: filterExpr: (ds = '2011-09-01') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (ds = '2011-09-01') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: bar (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 278 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 278 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string) TableScan alias: invites2 filterExpr: (ds = '2011-09-01') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (ds = '2011-09-01') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -92,14 +92,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col2 (type: int), '2011-09-01' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/keyword_1.q.out b/ql/src/test/results/clientpositive/keyword_1.q.out index 621a73918b..cf9dc0d3ea 100644 --- a/ql/src/test/results/clientpositive/keyword_1.q.out +++ b/ql/src/test/results/clientpositive/keyword_1.q.out @@ -26,11 +26,11 @@ STAGE PLANS: Processor Tree: TableScan alias: test_user - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: user (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: show grant user hive_test on table test_user @@ -74,11 +74,11 @@ STAGE PLANS: Processor Tree: TableScan alias: test_user - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: role (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: show grant user hive_test on table test_user diff --git a/ql/src/test/results/clientpositive/lateral_view_cp.q.out b/ql/src/test/results/clientpositive/lateral_view_cp.q.out index fec8c81a7d..a63c81f8bd 100644 --- a/ql/src/test/results/clientpositive/lateral_view_cp.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_cp.q.out @@ -36,27 +36,27 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1001504 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 951428 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 951428 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: array) Reduce Operator Tree: Join Operator @@ -66,18 +66,18 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col6 (type: array) outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 95700 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col2) mode: hash @@ -92,13 +92,13 @@ STAGE PLANS: Select Operator expressions: _col1 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 95700 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col2) mode: hash diff --git a/ql/src/test/results/clientpositive/lateral_view_onview.q.out b/ql/src/test/results/clientpositive/lateral_view_onview.q.out index 1ba94daaba..5d7c0231c4 100644 --- a/ql/src/test/results/clientpositive/lateral_view_onview.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_onview.q.out @@ -47,50 +47,50 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lv_table_n0 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: string), c2 (type: array), c3 (type: int), c4 (type: char(1)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col4 (type: int) sort order: ++ - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col4 (type: int) sort order: ++ - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), VALUE._col1 (type: int), VALUE._col2 (type: char(1)), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 374 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,7 +105,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col4 (type: int) sort order: ++ - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 374 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) Execution mode: vectorized @@ -113,13 +113,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), VALUE._col1 (type: int), VALUE._col2 (type: char(1)), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 374 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 374 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 374 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -538,30 +538,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lv_table_n0 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: string), c2 (type: array), c3 (type: int), c4 (type: char(1)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array), _col2 (type: int), _col3 (type: char(1)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: size(_col1) (type: int), _col2 (type: int), trim(_col0) (type: string), _col3 (type: char(1)), _col4 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1122 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1122 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -569,23 +569,23 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 500 Data size: 8500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 187068 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: size(_col1) (type: int), _col2 (type: int), trim(_col0) (type: string), _col3 (type: char(1)), _col4 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 17000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 374136 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1122 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 51 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1122 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -673,28 +673,28 @@ STAGE PLANS: TableScan alias: lv_table1_n0 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 485000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 485000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: c1 (type: string) sort order: + Map-reduce partition columns: c1 (type: string) - Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 485000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: c3 (type: int), c4 (type: char(1)), c5 (type: string), c6 (type: string), c7 (type: string), c8 (type: string), c9 (type: string), c10 (type: string), c11 (type: string), c12 (type: string), c13 (type: string) TableScan alias: lv_table2 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 144704 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 137468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: c1 (type: string) sort order: + Map-reduce partition columns: c1 (type: string) - Statistics: Num rows: 500 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 137468 Basic stats: COMPLETE Column stats: NONE value expressions: c2 (type: array) Reduce Operator Tree: Join Operator @@ -704,20 +704,20 @@ STAGE PLANS: 0 c1 (type: string) 1 c1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col16 - Statistics: Num rows: 550 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 533500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: char(1)), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col16 (type: array) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 550 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 533500 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 550 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 533500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: char(1)), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: array) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 550 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 533500 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1100 Data size: 61600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 1067000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -727,13 +727,13 @@ STAGE PLANS: Select Operator expressions: _col12 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 533500 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 550 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 533500 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1100 Data size: 61600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 1067000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -748,7 +748,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col13 (type: int) sort order: ++ - Statistics: Num rows: 1100 Data size: 61600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 1067000 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: char(1)), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: array) Execution mode: vectorized @@ -756,10 +756,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: char(1)), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), VALUE._col10 (type: string), VALUE._col11 (type: array), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1100 Data size: 61600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 1067000 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 970 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -774,7 +774,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col13 (type: int) sort order: ++ - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 970 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: char(1)), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: array) Execution mode: vectorized @@ -782,13 +782,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: char(1)), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), VALUE._col10 (type: string), VALUE._col11 (type: array), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 970 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 970 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 970 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/lateral_view_outer.q.out b/ql/src/test/results/clientpositive/lateral_view_outer.q.out index 342ed4bc95..6a95c8bf7c 100644 --- a/ql/src/test/results/clientpositive/lateral_view_outer.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_outer.q.out @@ -14,26 +14,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 261000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -41,24 +41,24 @@ STAGE PLANS: Select Operator expressions: array() (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 20000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 20000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode outer lateral view: true Lateral View Join Operator outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -104,26 +104,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 261000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 285000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 285000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -131,24 +131,24 @@ STAGE PLANS: Select Operator expressions: array(4,5) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode outer lateral view: true Lateral View Join Operator outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 285000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 285000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -206,26 +206,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: array_valued - Statistics: Num rows: 500 Data size: 5610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1001504 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 500 Data size: 5610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1001504 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: array) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1001504 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1000 Data size: 11220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 2003008 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 11220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 2003008 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20030 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20030 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -233,24 +233,24 @@ STAGE PLANS: Select Operator expressions: value (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1001504 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 500 Data size: 5610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1001504 Basic stats: COMPLETE Column stats: NONE function name: explode outer lateral view: true Lateral View Join Operator outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 1000 Data size: 11220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 2003008 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 11220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 2003008 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20030 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20030 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/lateral_view_ppd.q.out b/ql/src/test/results/clientpositive/lateral_view_ppd.q.out index 25c94e23db..f989b2f39e 100644 --- a/ql/src/test/results/clientpositive/lateral_view_ppd.q.out +++ b/ql/src/test/results/clientpositive/lateral_view_ppd.q.out @@ -13,26 +13,26 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '0') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '0') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -40,20 +40,20 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -97,26 +97,26 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '0') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '0') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -124,23 +124,23 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Filter Operator predicate: (col = 1) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,26 +178,26 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '12')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 307500 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col7 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 335500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col7 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 91000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 12 - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -205,23 +205,23 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col1, _col7 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 335500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col7 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 91000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 12 - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -270,35 +270,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '0') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '0') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col1, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1776 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5, _col6 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -306,20 +306,20 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col1, _col5, _col6 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -327,29 +327,29 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1152 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col1, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1776 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5, _col6 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -357,20 +357,20 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col1, _col5, _col6 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -432,26 +432,26 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '0') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '0') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -459,23 +459,23 @@ STAGE PLANS: Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Filter Operator predicate: (col > 1) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col1, _col5 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/leftsemijoin.q.out b/ql/src/test/results/clientpositive/leftsemijoin.q.out index f8ae36b02b..203f12c865 100644 --- a/ql/src/test/results/clientpositive/leftsemijoin.q.out +++ b/ql/src/test/results/clientpositive/leftsemijoin.q.out @@ -125,17 +125,17 @@ STAGE PLANS: TableScan alias: p1 filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: p2 @@ -153,12 +153,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 676 Data size: 85202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 676 Data size: 81796 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 676 Data size: 85202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 3025 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -172,26 +172,26 @@ STAGE PLANS: TableScan alias: part filterExpr: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_name is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string), p_type (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 676 Data size: 85202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 3025 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -200,14 +200,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 743 Data size: 93722 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 743 Data size: 93722 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 743 Data size: 93722 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -268,11 +268,11 @@ STAGE PLANS: Processor Tree: TableScan alias: part - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_type (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select part.p_type from part left join (select p1.p_name from part p1, part p2 group by p1.p_name) pp ON pp.p_name = part.p_name diff --git a/ql/src/test/results/clientpositive/limit_pushdown2.q.out b/ql/src/test/results/clientpositive/limit_pushdown2.q.out index 87be772d40..2e042a1349 100644 --- a/ql/src/test/results/clientpositive/limit_pushdown2.q.out +++ b/ql/src/test/results/clientpositive/limit_pushdown2.q.out @@ -18,22 +18,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized @@ -43,17 +43,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -117,22 +117,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: +- Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized @@ -142,17 +142,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -216,22 +216,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: -+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized @@ -241,17 +241,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -315,22 +315,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col1 (type: string), _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized @@ -340,17 +340,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -414,22 +414,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col1 (type: string), _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: -+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized @@ -439,17 +439,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -513,22 +513,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col1 (type: string), _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: -+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized @@ -538,17 +538,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -613,22 +613,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: bigint) Execution mode: vectorized @@ -638,7 +638,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -653,20 +653,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -731,22 +731,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col2) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: -+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: bigint) Execution mode: vectorized @@ -756,7 +756,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -771,20 +771,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: -++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -849,22 +849,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -873,11 +873,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (_col1 / _col2) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -892,20 +892,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col1 (type: double), _col0 (type: string) sort order: +- - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -970,22 +970,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -994,12 +994,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col1 (type: string), _col0 (type: string), (_col3 / _col4) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1014,7 +1014,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double) Execution mode: vectorized @@ -1022,13 +1022,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1061,22 +1061,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1085,12 +1085,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col1 (type: string), _col0 (type: string), (_col3 / _col4) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1105,7 +1105,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: double) Execution mode: vectorized @@ -1113,13 +1113,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out index 20bcd4b126..2fce77f94b 100644 --- a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out +++ b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out @@ -13,36 +13,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -52,13 +52,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -84,22 +84,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(key) keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Reduce Operator Tree: Group By Operator @@ -107,16 +107,16 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 100.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -142,30 +142,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 134500 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 1094500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 2004000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20040 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20040 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -173,23 +173,23 @@ STAGE PLANS: Select Operator expressions: array(_col1,_col1) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 960000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 960000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 1094500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 2004000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20040 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 20040 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -241,34 +241,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -277,12 +277,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 29165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -294,10 +294,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -329,7 +329,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -337,10 +337,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -360,24 +360,24 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -386,12 +386,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, c1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(c1, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -415,7 +415,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -423,10 +423,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/lineage1.q.out b/ql/src/test/results/clientpositive/lineage1.q.out index beee1294d5..dd249ec3be 100644 --- a/ql/src/test/results/clientpositive/lineage1.q.out +++ b/ql/src/test/results/clientpositive/lineage1.q.out @@ -50,29 +50,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: t1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -81,11 +81,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -98,14 +98,14 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 13806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 7410 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 7410 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -114,26 +114,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 7410 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan Union - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 13806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 7410 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 7410 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -142,25 +142,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 7410 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -228,29 +228,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: t2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -259,11 +259,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out index 226e778a6d..3c368630bc 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out @@ -33,19 +33,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -73,19 +73,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -200,17 +200,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -419,22 +419,22 @@ STAGE PLANS: TableScan alias: list_bucketing_dynamic_part_n0 filterExpr: ((ds = '2008-04-08') and (hr = '11') and (key = '484')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '484') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out index 11f7dc1a0d..d6e1bd34c0 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out @@ -35,19 +35,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -75,19 +75,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -151,17 +151,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -300,22 +300,22 @@ STAGE PLANS: TableScan alias: list_bucketing_static_part_n3 filterExpr: ((ds = '2008-04-08') and (hr = '11') and (value = 'val_466')) (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 'val_466') (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), 'val_466' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out index f1c20e5307..dc338e6741 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out @@ -35,19 +35,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: '1' (type: string), key (type: string), '1' (type: string), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 216500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 216500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -75,19 +75,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: col1, col2, col3, col4, col5, ds, hr - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 306500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll'), compute_stats(col4, 'hll'), compute_stats(col5, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2380 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct) auto parallelism: false @@ -151,17 +151,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2380 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2380 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -308,22 +308,22 @@ STAGE PLANS: TableScan alias: list_bucketing_mul_col_n0 filterExpr: ((col2 = '466') and (col4 = 'val_466')) (type: boolean) - Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 216500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean) - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 433 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 613 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 613 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -439,22 +439,22 @@ STAGE PLANS: TableScan alias: list_bucketing_mul_col_n0 filterExpr: ((col2 = '382') and (col4 = 'val_382')) (type: boolean) - Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 216500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((col2 = '382') and (col4 = 'val_382')) (type: boolean) - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 433 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col1 (type: string), '382' (type: string), col3 (type: string), 'val_382' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 613 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 613 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out index b9f658aea9..990900a4b1 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out @@ -35,19 +35,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: '1' (type: string), key (type: string), '1' (type: string), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 216500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 216500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -75,19 +75,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string) outputColumnNames: col1, col2, col3, col4, col5, ds, hr - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 315000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll'), compute_stats(col4, 'hll'), compute_stats(col5, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2397 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2397 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct) auto parallelism: false @@ -151,17 +151,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2397 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2397 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2397 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -308,22 +308,22 @@ STAGE PLANS: TableScan alias: list_bucketing_mul_col filterExpr: ((col2 = '466') and (col4 = 'val_466')) (type: boolean) - Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 216500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean) - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 433 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 630 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 630 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out index 7420e42d76..b810374040 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out @@ -29,18 +29,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -71,16 +71,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -143,13 +143,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -303,22 +303,22 @@ STAGE PLANS: TableScan alias: list_bucketing filterExpr: (key = '484') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '484') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out index bd8e215c22..e330855c28 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out @@ -37,19 +37,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -77,19 +77,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 358000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -204,17 +204,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -375,22 +375,22 @@ STAGE PLANS: TableScan alias: list_bucketing_static_part_n4 filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out index 5ba8948a19..8f38a0a83a 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out @@ -27,19 +27,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -67,19 +67,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 358000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -194,17 +194,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -367,22 +367,22 @@ STAGE PLANS: TableScan alias: list_bucketing_static_part_n1 filterExpr: ((ds = '2008-04-08') and (hr = '11') and (key = '484')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '484') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out index 520d48e3d9..f2a858a75d 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out @@ -37,19 +37,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -77,19 +77,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 358000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -204,17 +204,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -365,19 +365,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -404,19 +404,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 358000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -531,17 +531,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -818,22 +818,22 @@ STAGE PLANS: TableScan alias: list_bucketing_static_part_n2 filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out index 47c9e249c8..a5f3594a3f 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out @@ -33,19 +33,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -73,19 +73,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -200,17 +200,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -424,22 +424,22 @@ STAGE PLANS: TableScan alias: list_bucketing_dynamic_part_n1 filterExpr: ((key = '103') and (value = 'val_103')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '103') and (value = 'val_103')) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out index aad1458cc2..c112357ae2 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out @@ -37,19 +37,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -77,19 +77,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -204,17 +204,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -410,19 +410,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -450,19 +450,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -577,17 +577,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -914,22 +914,22 @@ STAGE PLANS: TableScan alias: list_bucketing_dynamic_part_n3 filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out index 7232e79fc8..638cf1b038 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out @@ -37,19 +37,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -77,19 +77,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -204,17 +204,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -410,19 +410,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -450,19 +450,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -577,17 +577,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -914,22 +914,22 @@ STAGE PLANS: TableScan alias: list_bucketing_dynamic_part filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out index 337f9dc7bf..2cedc0d6a0 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out @@ -37,19 +37,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -77,19 +77,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -204,17 +204,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -474,22 +474,22 @@ STAGE PLANS: TableScan alias: list_bucketing_dynamic_part_n2 filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out index fbd4fde1bd..dbb173c307 100644 --- a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out @@ -37,19 +37,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -77,19 +77,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 358000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -204,17 +204,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -365,19 +365,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-04-08/hr=11/ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat @@ -404,19 +404,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 358000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -531,17 +531,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -818,22 +818,22 @@ STAGE PLANS: TableScan alias: list_bucketing_static_part_n0 filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out index e324cab738..6d8a922e18 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out @@ -94,22 +94,22 @@ STAGE PLANS: TableScan alias: fact_daily filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -217,22 +217,22 @@ STAGE PLANS: TableScan alias: fact_daily filterExpr: ((key = '238') and (value = 'val_238')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '238') and (value = 'val_238')) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '238' (type: string), 'val_238' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -341,22 +341,22 @@ STAGE PLANS: TableScan alias: fact_daily filterExpr: ((ds = '1') and (hr = '4') and (value = '3')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = '3') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -463,22 +463,22 @@ STAGE PLANS: TableScan alias: fact_daily filterExpr: ((ds = '1') and (hr = '4') and (key = '495')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '495') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '495' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out index ec1e54060c..fe02f51391 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out @@ -94,22 +94,22 @@ STAGE PLANS: TableScan alias: fact_daily_n2 filterExpr: ((ds = '1') and (hr = '4') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (value = 'val_484') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), 'val_484' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -267,22 +267,22 @@ STAGE PLANS: TableScan alias: fact_daily_n2 filterExpr: ((ds = '1') and (hr = '4') and (key = '406')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '406') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '406' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -390,22 +390,22 @@ STAGE PLANS: TableScan alias: fact_daily_n2 filterExpr: ((struct(key,value)) IN (const struct('484','val_484'), const struct('238','val_238')) and (ds = '1') and (hr = '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(key,value)) IN (const struct('484','val_484'), const struct('238','val_238')) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out index 889f23c6da..c3e7e94a88 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out @@ -204,22 +204,22 @@ STAGE PLANS: TableScan alias: fact_daily_n3 filterExpr: ((ds = '1') and (hr = '1') and (key = '145')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '145') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '145' (type: string), value (type: string), '1' (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -357,22 +357,22 @@ STAGE PLANS: TableScan alias: fact_daily_n3 filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), 'val_484' (type: string), '1' (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -482,22 +482,22 @@ STAGE PLANS: TableScan alias: fact_daily_n3 filterExpr: ((key = '327') and (value = 'val_327')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = '327') and (value = 'val_327')) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '327' (type: string), 'val_327' (type: string), '1' (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out index dcff8a5037..ff55d718f4 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out @@ -145,22 +145,22 @@ STAGE PLANS: TableScan alias: fact_daily_n4 filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 484 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -265,22 +265,22 @@ STAGE PLANS: TableScan alias: fact_daily_n4 filterExpr: ((ds = '1') and (x = 495)) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x = 495) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 495 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -385,22 +385,22 @@ STAGE PLANS: TableScan alias: fact_daily_n4 filterExpr: ((ds = '1') and (x = 1)) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out index 3251dc4ef3..2c2233b2f3 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out @@ -148,22 +148,22 @@ STAGE PLANS: TableScan alias: fact_daily_n5 filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 484 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -268,22 +268,22 @@ STAGE PLANS: TableScan alias: fact_daily_n5 filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 484 (type: int), y (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -389,28 +389,28 @@ STAGE PLANS: TableScan alias: fact_daily_n5 filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: y (type: string) outputColumnNames: y - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() keys: y (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -473,13 +473,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 428 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -533,26 +533,26 @@ STAGE PLANS: TableScan alias: fact_daily_n5 filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() keys: 484 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -615,17 +615,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 484 (type: int), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 244 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out index a61d9d86b4..0febcd68a4 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out @@ -168,22 +168,22 @@ STAGE PLANS: TableScan alias: fact_daily_n0 filterExpr: ((ds = '1') and (x <> 86)) (type: boolean) - Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1178 Basic stats: PARTIAL Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (x <> 86) (type: boolean) - Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1178 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: x (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1178 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 1178 Basic stats: PARTIAL Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part1.q.out b/ql/src/test/results/clientpositive/load_dyn_part1.q.out index eae65bb216..9768c1812a 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part1.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part1.q.out @@ -70,17 +70,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -89,29 +89,29 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Filter Operator predicate: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -120,13 +120,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: '2008-12-31' (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -139,14 +139,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -241,7 +241,7 @@ STAGE PLANS: key expressions: '2008-12-31' (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -250,14 +250,14 @@ STAGE PLANS: keys: '2008-12-31' (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), '2008-12-31' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part10.q.out b/ql/src/test/results/clientpositive/load_dyn_part10.q.out index 5320999191..177469214f 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part10.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part10.q.out @@ -53,14 +53,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -69,18 +69,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-12-31' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -88,14 +88,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part13.q.out b/ql/src/test/results/clientpositive/load_dyn_part13.q.out index 75e1de41f4..205f8e0f87 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part13.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part13.q.out @@ -67,19 +67,19 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '22' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 43824 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 58344 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 58344 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -88,35 +88,35 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2010-03-03' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 79118 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) TableScan alias: src filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(key) < 40.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 40.0D) and (UDFToDouble(key) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '33' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14520 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 58344 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 58344 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -125,18 +125,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2010-03-03' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 79118 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -144,14 +144,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part2.q.out b/ql/src/test/results/clientpositive/load_dyn_part2.q.out index 9fb551ae7e..01a1dd278f 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part2.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part2.q.out @@ -46,25 +46,25 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -73,13 +73,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2010-03-23' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 912000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -116,7 +116,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -125,14 +125,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part3.q.out b/ql/src/test/results/clientpositive/load_dyn_part3.q.out index 41fa54c35f..ba7b8ae716 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part3.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part3.q.out @@ -51,14 +51,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -67,18 +67,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -86,14 +86,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part4.q.out b/ql/src/test/results/clientpositive/load_dyn_part4.q.out index 4cdba68976..4a0cc5e46e 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part4.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part4.q.out @@ -61,14 +61,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds is not null and hr is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -77,18 +77,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -96,14 +96,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 4992 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part8.q.out b/ql/src/test/results/clientpositive/load_dyn_part8.q.out index 0bf2145afd..05ad470645 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part8.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part8.q.out @@ -57,22 +57,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -99,37 +99,37 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false Filter Operator isSamplingPred: false predicate: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2008-12-31/ - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -156,13 +156,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: '2008-12-31' (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -392,17 +392,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -501,7 +501,7 @@ STAGE PLANS: null sort order: aa sort order: ++ Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -540,17 +540,17 @@ STAGE PLANS: keys: '2008-12-31' (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), '2008-12-31' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/load_dyn_part9.q.out b/ql/src/test/results/clientpositive/load_dyn_part9.q.out index 48f1516d2a..1606b52016 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part9.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part9.q.out @@ -53,14 +53,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -69,18 +69,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -88,14 +88,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/louter_join_ppr.q.out index b77c91a6c6..491760faad 100644 --- a/ql/src/test/results/clientpositive/louter_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/louter_join_ppr.q.out @@ -34,44 +34,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -237,13 +237,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -341,44 +341,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -544,17 +544,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -652,44 +652,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -855,13 +855,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -959,44 +959,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -1162,17 +1162,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin1.q.out b/ql/src/test/results/clientpositive/mapjoin1.q.out index b521f62caf..8be9d1e24d 100644 --- a/ql/src/test/results/clientpositive/mapjoin1.q.out +++ b/ql/src/test/results/clientpositive/mapjoin1.q.out @@ -43,11 +43,11 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -58,11 +58,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -70,13 +70,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -130,11 +130,11 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -148,11 +148,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -163,13 +163,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -225,11 +225,11 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -243,11 +243,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), named_struct('key',key,'value',value) (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 251500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -258,13 +258,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 538671 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6810 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6810 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -320,11 +320,11 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -335,11 +335,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -347,13 +347,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -407,11 +407,11 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -425,11 +425,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -440,13 +440,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -502,11 +502,11 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -520,11 +520,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), named_struct('key',key,'value',value) (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 251500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -535,13 +535,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 538671 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6810 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6810 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin3.q.out b/ql/src/test/results/clientpositive/mapjoin3.q.out index cf48fa2c60..aa817618b8 100644 --- a/ql/src/test/results/clientpositive/mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/mapjoin3.q.out @@ -109,11 +109,11 @@ STAGE PLANS: $hdt$_1:test_1 TableScan alias: test_1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: member (type: bigint), age (type: varchar(100)), age (type: varchar(100)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: bigint) @@ -124,11 +124,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 3 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: member (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -136,14 +136,14 @@ STAGE PLANS: 0 _col0 (type: bigint) 1 _col0 (type: bigint) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 3 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col2 (type: varchar(100)), _col3 (type: varchar(100)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin46.q.out b/ql/src/test/results/clientpositive/mapjoin46.q.out index a4f067f101..f66108447b 100644 --- a/ql/src/test/results/clientpositive/mapjoin46.q.out +++ b/ql/src/test/results/clientpositive/mapjoin46.q.out @@ -66,11 +66,11 @@ STAGE PLANS: $hdt$_1:test2_n2 TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -81,11 +81,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -93,10 +93,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -163,14 +163,14 @@ STAGE PLANS: TableScan alias: test2_n2 filterExpr: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {_col0 BETWEEN 100 AND 102} @@ -184,11 +184,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -199,10 +199,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 857 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -270,14 +270,14 @@ STAGE PLANS: TableScan alias: test2_n2 filterExpr: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {_col0 BETWEEN 100 AND 102} @@ -291,11 +291,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -306,10 +306,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1142 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1142 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -372,11 +372,11 @@ STAGE PLANS: $hdt$_0:test1_n4 TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -387,11 +387,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -399,10 +399,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -463,11 +463,11 @@ STAGE PLANS: $hdt$_1:test2_n2 TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {_col0 BETWEEN 100 AND 102} @@ -481,11 +481,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -496,10 +496,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -571,11 +571,11 @@ STAGE PLANS: $hdt$_1:test2_n2 TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -586,11 +586,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -599,10 +599,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -677,11 +677,11 @@ STAGE PLANS: $hdt$_1:test2_n2 TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -692,11 +692,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -705,10 +705,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -781,11 +781,11 @@ STAGE PLANS: $hdt$_1:test2_n2 TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -796,11 +796,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -809,10 +809,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -881,11 +881,11 @@ STAGE PLANS: $hdt$_1:test2_n2 TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -896,11 +896,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -909,10 +909,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -982,11 +982,11 @@ STAGE PLANS: $hdt$_0:test1_n4 TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -997,11 +997,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1010,10 +1010,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1088,11 +1088,11 @@ STAGE PLANS: $hdt$_0:test1_n4 TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1103,11 +1103,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1116,10 +1116,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1189,11 +1189,11 @@ STAGE PLANS: $hdt$_0:test1_n4 TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1204,11 +1204,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1217,10 +1217,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1291,11 +1291,11 @@ STAGE PLANS: $hdt$_0:test1_n4 TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -1306,11 +1306,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1319,10 +1319,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1384,25 +1384,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1413,10 +1413,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1483,25 +1483,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1512,10 +1512,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1580,25 +1580,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1609,10 +1609,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1675,29 +1675,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1708,10 +1708,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1810,11 +1810,11 @@ STAGE PLANS: $hdt$_0:test1_n4 TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -1822,11 +1822,11 @@ STAGE PLANS: $hdt$_2:$hdt$_3:test2_n2 TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -1837,11 +1837,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1850,18 +1850,18 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) TableScan alias: test1_n4 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -1870,10 +1870,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1524 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) Local Work: Map Reduce Local Work @@ -1886,10 +1886,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 residual filter predicates: {(_col1 is null or (_col10 is null and (_col7 <> _col4)))} - Statistics: Num rows: 36 Data size: 768 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 768 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 64 Data size: 24440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin47.q.out b/ql/src/test/results/clientpositive/mapjoin47.q.out index 172d160772..4f731be2f6 100644 --- a/ql/src/test/results/clientpositive/mapjoin47.q.out +++ b/ql/src/test/results/clientpositive/mapjoin47.q.out @@ -31,14 +31,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -50,14 +50,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(value) BETWEEN 100.0D AND 102.0D and key is not null) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -65,13 +65,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -135,14 +135,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -154,14 +154,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -169,13 +169,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -250,14 +250,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -269,14 +269,14 @@ STAGE PLANS: TableScan alias: src filterExpr: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(value) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -284,13 +284,13 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 110 Data size: 2103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 38830 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -359,11 +359,11 @@ STAGE PLANS: $hdt$_0:src1 TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -374,11 +374,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -387,13 +387,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((_col0 = _col2) or UDFToDouble(_col1) BETWEEN 100.0D AND 102.0D or UDFToDouble(_col3) BETWEEN 100.0D AND 102.0D)} - Statistics: Num rows: 9026 Data size: 173876 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9026 Data size: 3186178 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -469,11 +469,11 @@ STAGE PLANS: $hdt$_0:src1 TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -484,11 +484,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -497,13 +497,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D)} {((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D)} - Statistics: Num rows: 1388 Data size: 26738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1388 Data size: 489964 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -573,11 +573,11 @@ STAGE PLANS: $hdt$_0:src1 TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -588,11 +588,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -601,13 +601,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(((UDFToDouble(_col0) + UDFToDouble(_col2)) >= 100.0D) or ((UDFToDouble(_col0) + UDFToDouble(_col2)) <= 102.0D))} - Statistics: Num rows: 8332 Data size: 160507 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8332 Data size: 2941196 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -679,11 +679,11 @@ STAGE PLANS: $hdt$_0:src1 TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -694,11 +694,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -707,13 +707,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(struct(_col0,_col2)) IN (const struct(100,100), const struct(101,101), const struct(102,102))} - Statistics: Num rows: 9375 Data size: 180600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 625 Data size: 220625 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -778,11 +778,11 @@ STAGE PLANS: $hdt$_1:b TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -790,11 +790,11 @@ STAGE PLANS: $hdt$_2:a TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -805,11 +805,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -817,7 +817,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -826,17 +826,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) >= 100.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -913,11 +913,11 @@ STAGE PLANS: $hdt$_1:a TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -925,11 +925,11 @@ STAGE PLANS: $hdt$_2:b TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -940,11 +940,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -952,7 +952,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 96000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -961,13 +961,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 2172873 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1045,11 +1045,11 @@ STAGE PLANS: $hdt$_1:a TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1060,11 +1060,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1073,7 +1073,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1105,11 +1105,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1117,13 +1117,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 329 Data size: 173712 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1140,20 +1140,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1163,13 +1163,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 329 Data size: 173712 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1244,11 +1244,11 @@ STAGE PLANS: $hdt$_0:src TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -1256,11 +1256,11 @@ STAGE PLANS: $hdt$_2:b TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1271,11 +1271,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1283,7 +1283,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1292,13 +1292,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 325 Data size: 171600 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1362,11 +1362,11 @@ STAGE PLANS: $hdt$_1:a TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1377,24 +1377,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1403,12 +1403,12 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {((UDFToDouble(_col2) + UDFToDouble(_col0)) >= 100.0D)} - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4166 Data size: 80253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4166 Data size: 1470598 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Local Work: Map Reduce Local Work @@ -1420,13 +1420,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4582 Data size: 88278 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4191 Data size: 174240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1494,29 +1494,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: a - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1526,7 +1526,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1544,11 +1544,11 @@ STAGE PLANS: $hdt$_2:b TableScan alias: b - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1566,13 +1566,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((UDFToDouble(_col4) + UDFToDouble(_col0)) <= 102.0D)} - Statistics: Num rows: 4583 Data size: 88285 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4375 Data size: 2253167 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5280 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1659,11 +1659,11 @@ STAGE PLANS: $hdt$_0:t3 TableScan alias: t3 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1673,11 +1673,11 @@ STAGE PLANS: $hdt$_1:t5 TableScan alias: t5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1687,11 +1687,11 @@ STAGE PLANS: $hdt$_2:t4 TableScan alias: t4 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1701,11 +1701,11 @@ STAGE PLANS: $hdt$_3:$hdt$_3:t1 TableScan alias: t1 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -1716,11 +1716,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), c_int (type: int), c_float (type: float), c_boolean (type: boolean), dt (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7138 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1728,7 +1728,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 22 Data size: 288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 72836 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1741,17 +1741,17 @@ STAGE PLANS: 3 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 residual filter predicates: {((_col6 = _col24) or ((_col28 = _col16) and (_col8 = 42)))} {((_col12 = _col24) or ((_col27 = _col15) and (_col13 = _col25)))} {((_col0 = _col24) or ((_col1 = _col25) and (_col26 = _col20)))} - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450000 Data size: 823500000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: string), _col19 (type: string), _col20 (type: int), _col21 (type: float), _col22 (type: boolean), _col23 (type: string), _col24 (type: string), _col25 (type: string), _col26 (type: int), _col27 (type: float), _col28 (type: boolean), _col29 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: float), _col4 (type: boolean), _col5 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: float), _col16 (type: boolean), _col17 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: float), _col10 (type: boolean), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 74250 Data size: 3964275 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450000 Data size: 823500000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 18300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin_distinct.q.out b/ql/src/test/results/clientpositive/mapjoin_distinct.q.out index 19ab4e5137..8f28092a5b 100644 --- a/ql/src/test/results/clientpositive/mapjoin_distinct.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_distinct.q.out @@ -28,14 +28,14 @@ STAGE PLANS: TableScan alias: c filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -47,14 +47,14 @@ STAGE PLANS: TableScan alias: d filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -62,17 +62,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -81,7 +81,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,17 +97,17 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -176,14 +176,14 @@ STAGE PLANS: TableScan alias: c filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -195,14 +195,14 @@ STAGE PLANS: TableScan alias: d filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -210,17 +210,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -229,10 +229,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -302,14 +302,14 @@ STAGE PLANS: TableScan alias: c filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -321,14 +321,14 @@ STAGE PLANS: TableScan alias: d filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -336,12 +336,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -350,7 +350,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -366,17 +366,17 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -445,14 +445,14 @@ STAGE PLANS: TableScan alias: c filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -464,14 +464,14 @@ STAGE PLANS: TableScan alias: d filterExpr: ((ds = '2008-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -479,12 +479,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 287924 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -493,10 +493,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 307 Data size: 27937 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin_filter_on_outerjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_filter_on_outerjoin.q.out index 9472b85f2b..1f63caa5c6 100644 --- a/ql/src/test/results/clientpositive/mapjoin_filter_on_outerjoin.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_filter_on_outerjoin.q.out @@ -68,10 +68,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key < 300) and (key < 10)) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 300)) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -85,10 +85,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key < 300) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 300) (type: boolean) - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -105,10 +105,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: (key < 300) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 300) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -122,15 +122,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 65005 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 65005 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string), _col4 (type: string) sort order: +++ - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 65005 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string) Execution mode: vectorized Local Work: @@ -139,10 +139,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 65005 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 65005 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -224,10 +224,10 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((key < 300) and (key < 10)) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and (key < 300)) (type: boolean) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 350 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -241,10 +241,10 @@ STAGE PLANS: TableScan alias: src2 filterExpr: (key < 300) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 300) (type: boolean) - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 @@ -261,10 +261,10 @@ STAGE PLANS: TableScan alias: src3 filterExpr: (key < 300) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 300) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -278,15 +278,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string), _col4 (type: string) sort order: +++ - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string) Execution mode: vectorized Local Work: @@ -295,10 +295,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 2112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out b/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out index a8055665fe..89de065a79 100644 --- a/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out @@ -41,14 +41,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -75,10 +75,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 5568 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 5568 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin_subquery.q.out b/ql/src/test/results/clientpositive/mapjoin_subquery.q.out index 7f754a662d..cde9646e0c 100644 --- a/ql/src/test/results/clientpositive/mapjoin_subquery.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_subquery.q.out @@ -32,14 +32,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -49,14 +49,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -69,14 +69,14 @@ STAGE PLANS: TableScan alias: z filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -86,14 +86,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -271,14 +271,14 @@ STAGE PLANS: TableScan alias: y filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -288,14 +288,14 @@ STAGE PLANS: TableScan alias: x filterExpr: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -308,14 +308,14 @@ STAGE PLANS: TableScan alias: z filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -325,14 +325,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out b/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out index 89aac8f58a..d45554cb41 100644 --- a/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_subquery2.q.out @@ -98,14 +98,14 @@ STAGE PLANS: TableScan alias: y filterExpr: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int), name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -115,14 +115,14 @@ STAGE PLANS: TableScan alias: z filterExpr: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: int), name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -135,14 +135,14 @@ STAGE PLANS: TableScan alias: x filterExpr: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 1 Data size: 130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: name (type: string), id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -152,14 +152,14 @@ STAGE PLANS: 1 _col1 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 413 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col3 (type: int), _col2 (type: string), _col0 (type: int), _col1 (type: string), _col4 (type: int), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 413 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 132 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 413 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapjoin_test_outer.q.out b/ql/src/test/results/clientpositive/mapjoin_test_outer.q.out index dfa9387c15..6f52b058d2 100644 --- a/ql/src/test/results/clientpositive/mapjoin_test_outer.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_test_outer.q.out @@ -258,7 +258,7 @@ STAGE PLANS: src1 TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -267,7 +267,7 @@ STAGE PLANS: src2 TableScan alias: src2 - Statistics: Num rows: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1620 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -279,7 +279,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1539 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -289,15 +289,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9625 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9625 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9625 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -305,10 +305,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9625 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9625 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1080,7 +1080,7 @@ STAGE PLANS: src1 TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -1089,7 +1089,7 @@ STAGE PLANS: src2 TableScan alias: src2 - Statistics: Num rows: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1620 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -1101,7 +1101,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src3 - Statistics: Num rows: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1539 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1111,15 +1111,15 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 11046 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 11046 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 11046 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -1127,10 +1127,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 11046 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 11046 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce1.q.out b/ql/src/test/results/clientpositive/mapreduce1.q.out index 090a370daf..1c2b229691 100644 --- a/ql/src/test/results/clientpositive/mapreduce1.q.out +++ b/ql/src/test/results/clientpositive/mapreduce1.q.out @@ -34,32 +34,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: _col3 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -68,12 +68,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) outputColumnNames: key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -105,7 +105,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -113,10 +113,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce2.q.out b/ql/src/test/results/clientpositive/mapreduce2.q.out index 41abfebf5b..f966cf4788 100644 --- a/ql/src/test/results/clientpositive/mapreduce2.q.out +++ b/ql/src/test/results/clientpositive/mapreduce2.q.out @@ -32,31 +32,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col3 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -65,12 +65,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) outputColumnNames: key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -102,7 +102,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -110,10 +110,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce3.q.out b/ql/src/test/results/clientpositive/mapreduce3.q.out index 17721e59ec..0c64080762 100644 --- a/ql/src/test/results/clientpositive/mapreduce3.q.out +++ b/ql/src/test/results/clientpositive/mapreduce3.q.out @@ -32,31 +32,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col0 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -65,12 +65,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) outputColumnNames: key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -102,7 +102,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -110,10 +110,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce4.q.out b/ql/src/test/results/clientpositive/mapreduce4.q.out index be7b33c43d..27616997ef 100644 --- a/ql/src/test/results/clientpositive/mapreduce4.q.out +++ b/ql/src/test/results/clientpositive/mapreduce4.q.out @@ -34,32 +34,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string) sort order: -+ Map-reduce partition columns: _col3 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), UDFToInteger(VALUE._col1) (type: int), UDFToInteger(VALUE._col2) (type: int), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -68,12 +68,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) outputColumnNames: key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -105,7 +105,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -113,10 +113,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce5.q.out b/ql/src/test/results/clientpositive/mapreduce5.q.out index 156ee55f74..547e6fdcb2 100644 --- a/ql/src/test/results/clientpositive/mapreduce5.q.out +++ b/ql/src/test/results/clientpositive/mapreduce5.q.out @@ -32,26 +32,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int) sort order: -+ Map-reduce partition columns: _col3 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col3 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -60,12 +60,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) outputColumnNames: key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,7 +97,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -105,10 +105,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce6.q.out b/ql/src/test/results/clientpositive/mapreduce6.q.out index b0dde1a692..fb157abdc6 100644 --- a/ql/src/test/results/clientpositive/mapreduce6.q.out +++ b/ql/src/test/results/clientpositive/mapreduce6.q.out @@ -32,26 +32,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int) sort order: -+ Map-reduce partition columns: _col3 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col3 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -60,12 +60,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) outputColumnNames: key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,7 +97,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -105,10 +105,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce7.q.out b/ql/src/test/results/clientpositive/mapreduce7.q.out index 82cad214bb..669cdb629c 100644 --- a/ql/src/test/results/clientpositive/mapreduce7.q.out +++ b/ql/src/test/results/clientpositive/mapreduce7.q.out @@ -32,31 +32,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: string), _col2 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), UDFToInteger(VALUE._col2) (type: int), UDFToInteger(VALUE._col3) (type: int), UDFToInteger(VALUE._col4) (type: int), VALUE._col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -65,12 +65,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: string) outputColumnNames: k, v, key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k, 'hll'), compute_stats(v, 'hll'), compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -102,7 +102,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -110,10 +110,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mapreduce8.q.out b/ql/src/test/results/clientpositive/mapreduce8.q.out index 93f1bea0a2..c86286223e 100644 --- a/ql/src/test/results/clientpositive/mapreduce8.q.out +++ b/ql/src/test/results/clientpositive/mapreduce8.q.out @@ -34,32 +34,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), key (type: string), UDFToInteger((key / 10)) (type: int), UDFToInteger((key % 10)) (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: string), _col2 (type: string) sort order: ++ Map-reduce partition columns: rand(3) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), UDFToInteger(VALUE._col2) (type: int), UDFToInteger(VALUE._col3) (type: int), UDFToInteger(VALUE._col4) (type: int), VALUE._col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -68,12 +68,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: string) outputColumnNames: k, v, key, ten, one, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 140500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k, 'hll'), compute_stats(v, 'hll'), compute_stats(key, 'hll'), compute_stats(ten, 'hll'), compute_stats(one, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -105,7 +105,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2592 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -113,10 +113,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2640 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_1.q.out b/ql/src/test/results/clientpositive/masking_1.q.out index b5e67e281e..9f98bb6f09 100644 --- a/ql/src/test/results/clientpositive/masking_1.q.out +++ b/ql/src/test/results/clientpositive/masking_1.q.out @@ -25,17 +25,17 @@ STAGE PLANS: TableScan alias: masking_test_n8 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -77,17 +77,17 @@ STAGE PLANS: TableScan alias: masking_test_n8 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -126,17 +126,17 @@ STAGE PLANS: TableScan alias: masking_test_n8 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -175,17 +175,17 @@ STAGE PLANS: TableScan alias: masking_test_n8 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -224,36 +224,36 @@ STAGE PLANS: TableScan alias: masking_test_n8 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: srcpart filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator @@ -263,10 +263,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -359,17 +359,17 @@ STAGE PLANS: TableScan alias: masking_test_n8 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -408,17 +408,17 @@ STAGE PLANS: TableScan alias: masking_test_n8 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -457,17 +457,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToDouble(key) > 0.0D) and (UDFToDouble(key) < 10.0D) and ((UDFToDouble(key) % 2.0D) = 0.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(key) % 2.0D) = 0.0D) and (UDFToDouble(key) < 10.0D) and (UDFToDouble(key) > 0.0D)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_10.q.out b/ql/src/test/results/clientpositive/masking_10.q.out index 5d5e1fe8a4..d8b91aa8d9 100644 --- a/ql/src/test/results/clientpositive/masking_10.q.out +++ b/ql/src/test/results/clientpositive/masking_10.q.out @@ -27,38 +27,38 @@ STAGE PLANS: TableScan alias: masking_test filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 2017 (type: int), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22372 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22372 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -119,31 +119,31 @@ STAGE PLANS: TableScan alias: masking_test filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: masking_test - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 2017 (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 175 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -153,7 +153,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 83 Data size: 1794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -169,24 +169,24 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 83 Data size: 1794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88744 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) TableScan alias: masking_test filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -196,10 +196,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 91 Data size: 1973 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 97618 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 91 Data size: 1973 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 97618 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_12.q.out b/ql/src/test/results/clientpositive/masking_12.q.out index 15ff0efaeb..15777e23c4 100644 --- a/ql/src/test/results/clientpositive/masking_12.q.out +++ b/ql/src/test/results/clientpositive/masking_12.q.out @@ -41,17 +41,17 @@ STAGE PLANS: filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,27 +127,27 @@ STAGE PLANS: filterExpr: key is not null (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -161,26 +161,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -190,12 +190,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -211,26 +211,26 @@ STAGE PLANS: filterExpr: key is not null (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -239,13 +239,13 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -323,17 +323,17 @@ STAGE PLANS: filterExpr: (((key % 2) = 0) and (key < 10) and (key > 6)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 6)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger((UDFToDouble(key) / 2.0D)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -378,38 +378,38 @@ STAGE PLANS: filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: masking_test_n5 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 6) and ((UDFToInteger((UDFToDouble(key) / 2.0D)) % 2) = 0) and (UDFToInteger((UDFToDouble(key) / 2.0D)) < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((UDFToInteger((UDFToDouble(key) / 2.0D)) % 2) = 0) and ((key % 2) = 0) and (UDFToInteger((UDFToDouble(key) / 2.0D)) < 10) and (key < 10) and (key > 6)) (type: boolean) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger((UDFToDouble(key) / 2.0D)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -418,14 +418,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 49218 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 49218 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275 Data size: 49218 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_1_newdb.q.out b/ql/src/test/results/clientpositive/masking_1_newdb.q.out index 10d3a0fc2f..315a719451 100644 --- a/ql/src/test/results/clientpositive/masking_1_newdb.q.out +++ b/ql/src/test/results/clientpositive/masking_1_newdb.q.out @@ -43,17 +43,17 @@ STAGE PLANS: TableScan alias: masking_test_n12 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -95,17 +95,17 @@ STAGE PLANS: TableScan alias: masking_test_n12 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_2.q.out b/ql/src/test/results/clientpositive/masking_2.q.out index bfa36c509b..d87c0d5151 100644 --- a/ql/src/test/results/clientpositive/masking_2.q.out +++ b/ql/src/test/results/clientpositive/masking_2.q.out @@ -27,17 +27,17 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -83,17 +83,17 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -134,38 +134,38 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0) and reverse(value) is not null) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0) and reverse(value) is not null) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -175,10 +175,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -207,38 +207,38 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0) and reverse(value) is not null) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0) and reverse(value) is not null) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col1) (type: double) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -248,10 +248,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -280,60 +280,60 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 20680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 20680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_3.q.out b/ql/src/test/results/clientpositive/masking_3.q.out index 0dbc39411e..163697cdfe 100644 --- a/ql/src/test/results/clientpositive/masking_3.q.out +++ b/ql/src/test/results/clientpositive/masking_3.q.out @@ -27,27 +27,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -61,26 +61,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -90,12 +90,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -109,26 +109,26 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -137,10 +137,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -679,27 +679,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -713,26 +713,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -742,12 +742,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -761,26 +761,26 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -789,10 +789,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1328,27 +1328,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1362,26 +1362,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -1391,12 +1391,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1410,25 +1410,25 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -1437,10 +1437,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1976,27 +1976,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2010,26 +2010,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -2039,12 +2039,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2058,26 +2058,26 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -2086,14 +2086,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2630,27 +2630,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2664,26 +2664,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -2693,12 +2693,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2712,26 +2712,26 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -2740,7 +2740,7 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2756,24 +2756,24 @@ STAGE PLANS: key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: srcpart filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator @@ -2783,10 +2783,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6947,27 +6947,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -6981,26 +6981,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -7010,12 +7010,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -7029,26 +7029,26 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -7057,10 +7057,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7596,27 +7596,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -7630,26 +7630,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -7659,12 +7659,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -7678,26 +7678,26 @@ STAGE PLANS: TableScan alias: masking_test_subq_n3 filterExpr: (key > 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key > 0) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -7706,10 +7706,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -8243,17 +8243,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToDouble(key) > 0.0D) and (UDFToDouble(key) < 10.0D) and ((UDFToDouble(key) % 2.0D) = 0.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(key) % 2.0D) = 0.0D) and (UDFToDouble(key) < 10.0D) and (UDFToDouble(key) > 0.0D)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_4.q.out b/ql/src/test/results/clientpositive/masking_4.q.out index 8ece717d54..ce1f1e5864 100644 --- a/ql/src/test/results/clientpositive/masking_4.q.out +++ b/ql/src/test/results/clientpositive/masking_4.q.out @@ -43,17 +43,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -85,17 +85,17 @@ STAGE PLANS: TableScan alias: masking_test_n11 filterExpr: (((key % 2) = 0) and (key = 5)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key = 5)) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,17 +127,17 @@ STAGE PLANS: TableScan alias: masking_test_n11 filterExpr: (((key % 2) = 0) and (key = 5)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key = 5)) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -171,27 +171,27 @@ STAGE PLANS: TableScan alias: masking_test_subq_n2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -205,26 +205,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 237 Data size: 902 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -234,12 +234,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -253,26 +253,26 @@ STAGE PLANS: TableScan alias: masking_test_subq_n2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col0 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), _col1 (type: int) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), _col1 (type: int) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -281,10 +281,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double), _col0 (type: int) 1 UDFToDouble(_col0) (type: double), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_5.q.out b/ql/src/test/results/clientpositive/masking_5.q.out index 594abeea3f..2d18eef92d 100644 --- a/ql/src/test/results/clientpositive/masking_5.q.out +++ b/ql/src/test/results/clientpositive/masking_5.q.out @@ -26,17 +26,17 @@ STAGE PLANS: alias: masking_test_n6 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) Row Limit Per Split: 10 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -74,17 +74,17 @@ STAGE PLANS: TableScan alias: masking_test_n6 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -156,17 +156,17 @@ STAGE PLANS: TableScan alias: masking_test_n6 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((hash(key) & 2147483647) % 2) = 0) and ((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 7708 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 7708 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_7.q.out b/ql/src/test/results/clientpositive/masking_7.q.out index bbdf3f9f41..8097aaca81 100644 --- a/ql/src/test/results/clientpositive/masking_7.q.out +++ b/ql/src/test/results/clientpositive/masking_7.q.out @@ -33,17 +33,17 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string), '12' (type: string), ROW__ID (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 29050 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 29050 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -89,17 +89,17 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string), '12' (type: string), ROW__ID (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 9450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 9450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -177,17 +177,17 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), '12' (type: string), ROW__ID (type: struct), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 85158 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 85158 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -233,17 +233,17 @@ STAGE PLANS: filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2349 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), '12' (type: string), ROW__ID (type: struct), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 27702 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 27702 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_8.q.out b/ql/src/test/results/clientpositive/masking_8.q.out index 115a8d3327..4153abe5d8 100644 --- a/ql/src/test/results/clientpositive/masking_8.q.out +++ b/ql/src/test/results/clientpositive/masking_8.q.out @@ -30,17 +30,17 @@ STAGE PLANS: TableScan alias: masking_test_n2 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 6812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177072 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string), _c2 (type: string), ROW__ID (type: struct) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -82,17 +82,17 @@ STAGE PLANS: TableScan alias: masking_test_n2 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 6812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177072 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string), _c2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -134,17 +134,17 @@ STAGE PLANS: TableScan alias: masking_test_n2 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 6812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177072 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: INPUT__FILE__NAME (type: string), key (type: int), reverse(value) (type: string), _c2 (type: string), ROW__ID (type: struct) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 1130 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 88536 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -212,17 +212,17 @@ STAGE PLANS: TableScan alias: masking_test_n2 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 17406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 877744 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 438872 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID (type: struct), key (type: int), _c1 (type: string), _c2 (type: string), _c3 (type: string), _c4 (type: string), _c5 (type: string), _c6 (type: string), _c7 (type: string), _c8 (type: string), _c9 (type: string), _c10 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 83 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 438872 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 2889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 438872 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_9.q.out b/ql/src/test/results/clientpositive/masking_9.q.out index c9c0ad70c6..3d1bd94524 100644 --- a/ql/src/test/results/clientpositive/masking_9.q.out +++ b/ql/src/test/results/clientpositive/masking_9.q.out @@ -27,17 +27,17 @@ STAGE PLANS: TableScan alias: masking_test filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out b/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out index cf7fd0049d..16b8bac874 100644 --- a/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out +++ b/ql/src/test/results/clientpositive/masking_disablecbo_1.q.out @@ -25,17 +25,17 @@ STAGE PLANS: TableScan alias: masking_test_n10 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -77,17 +77,17 @@ STAGE PLANS: TableScan alias: masking_test_n10 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -126,17 +126,17 @@ STAGE PLANS: TableScan alias: masking_test_n10 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -175,17 +175,17 @@ STAGE PLANS: TableScan alias: masking_test_n10 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -224,32 +224,32 @@ STAGE PLANS: TableScan alias: masking_test_n10 filterExpr: (((key % 2) = 0) and (key < 10) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 225 Data size: 40269 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 225 Data size: 40269 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 225 Data size: 40269 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: srcpart filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(key) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(key) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) Reduce Operator Tree: Join Operator @@ -259,14 +259,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -359,17 +359,17 @@ STAGE PLANS: TableScan alias: masking_test_n10 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -408,17 +408,17 @@ STAGE PLANS: TableScan alias: masking_test_n10 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -457,17 +457,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key > 0) and (key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_disablecbo_2.q.out b/ql/src/test/results/clientpositive/masking_disablecbo_2.q.out index 5a70e005e2..c5f4f6c315 100644 --- a/ql/src/test/results/clientpositive/masking_disablecbo_2.q.out +++ b/ql/src/test/results/clientpositive/masking_disablecbo_2.q.out @@ -25,17 +25,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -79,17 +79,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -130,32 +130,32 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and reverse(value) is not null and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0) and reverse(value) is not null) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -165,14 +165,14 @@ STAGE PLANS: 0 key (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -199,36 +199,36 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and UDFToDouble(UDFToInteger(key)) is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and UDFToDouble(UDFToInteger(key)) is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and UDFToDouble(reverse(value)) is not null and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0) and UDFToDouble(reverse(value)) is not null) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col1) (type: double) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -238,10 +238,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 8064 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 42 Data size: 8064 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -268,58 +268,58 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 20680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and (UDFToInteger(key) > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5076 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 20680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 110 Data size: 1167 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_disablecbo_3.q.out b/ql/src/test/results/clientpositive/masking_disablecbo_3.q.out index df96b3da17..67cdfe8e4f 100644 --- a/ql/src/test/results/clientpositive/masking_disablecbo_3.q.out +++ b/ql/src/test/results/clientpositive/masking_disablecbo_3.q.out @@ -25,37 +25,37 @@ STAGE PLANS: TableScan alias: masking_test_subq filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), value (type: string) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -64,10 +64,10 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -604,37 +604,37 @@ STAGE PLANS: TableScan alias: masking_test_subq filterExpr: (UDFToDouble(key) is not null and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > 0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), value (type: string) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -643,10 +643,10 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1180,37 +1180,37 @@ STAGE PLANS: TableScan alias: masking_test_subq filterExpr: (UDFToDouble(key) is not null and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > 0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1219,10 +1219,10 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1756,37 +1756,37 @@ STAGE PLANS: TableScan alias: masking_test_subq filterExpr: (UDFToDouble(key) is not null and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > 0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1795,14 +1795,14 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2337,37 +2337,37 @@ STAGE PLANS: TableScan alias: masking_test_subq filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), value (type: string) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -2376,7 +2376,7 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2392,20 +2392,20 @@ STAGE PLANS: key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: srcpart filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(key) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(key) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) Reduce Operator Tree: Join Operator @@ -2415,14 +2415,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col1, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 1201200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6581,37 +6581,37 @@ STAGE PLANS: TableScan alias: masking_test_subq filterExpr: (UDFToDouble(key) is not null and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > 0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), value (type: string) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -6620,10 +6620,10 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7157,37 +7157,37 @@ STAGE PLANS: TableScan alias: masking_test_subq filterExpr: (UDFToDouble(key) is not null and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key > 0) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), value (type: string) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -7196,10 +7196,10 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -7733,17 +7733,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key > 0) and (key < 10) and ((key % 2) = 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 7317 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/masking_disablecbo_4.q.out b/ql/src/test/results/clientpositive/masking_disablecbo_4.q.out index 62a10464d2..f56ca433e4 100644 --- a/ql/src/test/results/clientpositive/masking_disablecbo_4.q.out +++ b/ql/src/test/results/clientpositive/masking_disablecbo_4.q.out @@ -43,17 +43,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '5') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '5') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '5' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -85,17 +85,17 @@ STAGE PLANS: TableScan alias: masking_test_n3 filterExpr: (((key % 2) = 0) and (key < 10) and (key = 5)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key = 5)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,17 +127,17 @@ STAGE PLANS: TableScan alias: masking_test_n3 filterExpr: (((key % 2) = 0) and (key < 10) and (key = 5)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key = 5)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 536 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -169,37 +169,37 @@ STAGE PLANS: TableScan alias: masking_test_subq_n0 filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: int), value (type: string) TableScan alias: src filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) sort order: ++ Map-reduce partition columns: UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -208,10 +208,10 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double), UDFToDouble(key) (type: double) 1 UDFToDouble(_col0) (type: double), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge1.q.out b/ql/src/test/results/clientpositive/merge1.q.out index a5c0502082..5d46fc9673 100644 --- a/ql/src/test/results/clientpositive/merge1.q.out +++ b/ql/src/test/results/clientpositive/merge1.q.out @@ -31,22 +31,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -55,14 +55,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -71,12 +71,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, val - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -147,7 +147,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -155,10 +155,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -559,14 +559,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_src_n2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -575,25 +575,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: key - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -691,14 +691,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_src_n2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -707,25 +707,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: key - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge2.q.out b/ql/src/test/results/clientpositive/merge2.q.out index 1c11c6e516..395ce2dc04 100644 --- a/ql/src/test/results/clientpositive/merge2.q.out +++ b/ql/src/test/results/clientpositive/merge2.q.out @@ -31,22 +31,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -55,14 +55,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -71,12 +71,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: key, val - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -147,7 +147,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -155,10 +155,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -559,14 +559,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_src_n0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -575,25 +575,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: key - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -691,14 +691,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_src_n0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -707,25 +707,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: key - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge3.q.out b/ql/src/test/results/clientpositive/merge3.q.out index dd400c5651..8626545933 100644 --- a/ql/src/test/results/clientpositive/merge3.q.out +++ b/ql/src/test/results/clientpositive/merge3.q.out @@ -76,18 +76,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: merge_src - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 699568 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 699568 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 699568 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2396,18 +2396,18 @@ STAGE PLANS: TableScan alias: merge_src_part filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2434,19 +2434,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -2559,17 +2559,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4879,18 +4879,18 @@ STAGE PLANS: TableScan alias: merge_src_part filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) auto parallelism: false @@ -5002,13 +5002,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -5035,23 +5035,23 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2128 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/merge4.q.out b/ql/src/test/results/clientpositive/merge4.q.out index 1bbfd86cd2..9e3d4f00e7 100644 --- a/ql/src/test/results/clientpositive/merge4.q.out +++ b/ql/src/test/results/clientpositive/merge4.q.out @@ -29,14 +29,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -45,18 +45,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2010-08-15' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -64,14 +64,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1189,14 +1189,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1205,18 +1205,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2010-08-15' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 358000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -1224,14 +1224,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2855,19 +2855,19 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 140124 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1500 Data size: 491500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: src @@ -2877,25 +2877,25 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 129500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 140124 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1500 Data size: 491500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2904,13 +2904,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2010-08-15' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1 Data size: 353 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1063 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 1158 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2986,7 +2986,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 1063 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 1158 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2995,14 +2995,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1063 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 1158 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1063 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 1158 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1063 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 1158 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out index 6cd424717e..1f229efcbb 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out @@ -65,14 +65,14 @@ STAGE PLANS: TableScan alias: srcpart_merge_dp_n1 filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -81,18 +81,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 140664 Basic stats: PARTIAL Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 140664 Basic stats: PARTIAL Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -100,14 +100,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 69064 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 69064 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 69064 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -696,14 +696,14 @@ STAGE PLANS: TableScan alias: srcpart_merge_dp_n1 filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -712,18 +712,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -731,14 +731,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 46252 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 46252 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 46252 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1366,14 +1366,14 @@ STAGE PLANS: TableScan alias: srcpart_merge_dp_n1 filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D)) (type: boolean) - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1382,18 +1382,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 111664 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 140664 Basic stats: PARTIAL Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 99 Data size: 140664 Basic stats: PARTIAL Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -1401,14 +1401,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 69064 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 69064 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 49 Data size: 69064 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out index 3f8dccc3ad..d5b713fd87 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out @@ -87,14 +87,14 @@ STAGE PLANS: TableScan alias: srcpart_merge_dp_n0 filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 333310 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 333310 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 333310 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -103,18 +103,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 333310 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 420520 Basic stats: PARTIAL Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 420520 Basic stats: PARTIAL Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -122,14 +122,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 148 Data size: 207152 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 148 Data size: 207152 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 148 Data size: 207152 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out index b25a80aa37..1e11ef1f20 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out @@ -147,14 +147,14 @@ STAGE PLANS: TableScan alias: srcpart_merge_dp_n2 filterExpr: (ds >= '2008-04-08') (type: boolean) - Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 594 Data size: 775180 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 594 Data size: 775180 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 594 Data size: 775180 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -163,18 +163,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 594 Data size: 775180 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 594 Data size: 949600 Basic stats: PARTIAL Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 594 Data size: 949600 Basic stats: PARTIAL Column stats: PARTIAL value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -182,14 +182,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 469648 Basic stats: PARTIAL Column stats: PARTIAL Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 469648 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 297 Data size: 469648 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out index f5740cf95c..c9a4aa355c 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out @@ -148,14 +148,14 @@ STAGE PLANS: TableScan alias: srcpart_merge_dp_rc_n1 filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 2.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -164,18 +164,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 456000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -183,14 +183,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 365928 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out index c3319b8bfe..e5c3e4b2b8 100644 --- a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out +++ b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out @@ -124,14 +124,14 @@ STAGE PLANS: TableScan alias: srcpart_merge_dp_rc filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 618 Data size: 110004 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 618 Data size: 223716 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 618 Data size: 223716 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -140,18 +140,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 618 Data size: 281808 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 357822 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 357822 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -159,14 +159,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 357822 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 357822 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 357822 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/merge_join_1.q.out b/ql/src/test/results/clientpositive/merge_join_1.q.out index ccbae94553..d5cdbf66cc 100644 --- a/ql/src/test/results/clientpositive/merge_join_1.q.out +++ b/ql/src/test/results/clientpositive/merge_join_1.q.out @@ -78,36 +78,36 @@ STAGE PLANS: TableScan alias: test_join_1 filterExpr: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: test_join_2 filterExpr: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -116,7 +116,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -132,24 +132,24 @@ STAGE PLANS: key expressions: _col0 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: test_join_1 filterExpr: (a is not null and b is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (a is not null and b is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -158,14 +158,14 @@ STAGE PLANS: 0 _col0 (type: string), _col0 (type: string) 1 _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mergejoin.q.out b/ql/src/test/results/clientpositive/mergejoin.q.out index 7cbcbbe9a8..fb67b73217 100644 --- a/ql/src/test/results/clientpositive/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/mergejoin.q.out @@ -19,36 +19,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Map Vectorization: enabled: false @@ -65,10 +65,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -261,35 +261,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -304,12 +304,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -331,7 +331,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -358,10 +358,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1384,28 +1384,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -1420,12 +1420,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1447,7 +1447,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1474,10 +1474,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1529,28 +1529,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -1565,12 +1565,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1592,7 +1592,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1619,10 +1619,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1674,28 +1674,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -1710,12 +1710,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1737,7 +1737,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1764,10 +1764,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1819,36 +1819,36 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -1864,7 +1864,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1880,23 +1880,23 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -1911,12 +1911,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1938,7 +1938,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1965,10 +1965,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2019,35 +2019,35 @@ STAGE PLANS: TableScan alias: a filterExpr: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2062,12 +2062,12 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2089,7 +2089,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -2116,10 +2116,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2175,35 +2175,35 @@ STAGE PLANS: TableScan alias: s1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2219,7 +2219,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2232,46 +2232,46 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2286,12 +2286,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2313,7 +2313,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -2340,10 +2340,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2377,35 +2377,35 @@ STAGE PLANS: TableScan alias: a filterExpr: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2420,12 +2420,12 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2447,7 +2447,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -2474,10 +2474,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2527,36 +2527,36 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: c filterExpr: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2572,7 +2572,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2588,23 +2588,23 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2619,12 +2619,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2646,7 +2646,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -2673,10 +2673,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2734,35 +2734,35 @@ STAGE PLANS: TableScan alias: s1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2778,7 +2778,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2791,46 +2791,46 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -2845,12 +2845,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2872,7 +2872,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -2899,10 +2899,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2950,7 +2950,7 @@ STAGE PLANS: TableScan alias: t1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct] @@ -2960,7 +2960,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 @@ -2968,7 +2968,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ @@ -2977,7 +2977,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -3003,7 +3003,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3019,13 +3019,13 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -3040,12 +3040,12 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3067,7 +3067,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -3094,10 +3094,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3109,7 +3109,7 @@ STAGE PLANS: TableScan alias: t2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct] @@ -3119,7 +3119,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 @@ -3127,7 +3127,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ @@ -3136,7 +3136,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -3162,7 +3162,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/mergejoins.q.out b/ql/src/test/results/clientpositive/mergejoins.q.out index 58d1c1d2d8..6c832d1bf0 100644 --- a/ql/src/test/results/clientpositive/mergejoins.q.out +++ b/ql/src/test/results/clientpositive/mergejoins.q.out @@ -54,70 +54,70 @@ STAGE PLANS: TableScan alias: a_n0 filterExpr: (val1 is not null and val2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (val1 is not null and val2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val1 (type: int), val2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) TableScan alias: b_n0 filterExpr: val1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val1 (type: int), val2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) TableScan alias: c_n0 filterExpr: val1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val1 (type: int), val2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) TableScan alias: d_n0 filterExpr: val1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val1 (type: int), val2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -131,7 +131,7 @@ STAGE PLANS: 2 _col0 (type: int) 3 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -147,24 +147,24 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int) TableScan alias: e_n0 filterExpr: val2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val2 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val1 (type: int), val2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -174,10 +174,10 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 28 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -204,53 +204,53 @@ STAGE PLANS: TableScan alias: a_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: c_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -266,10 +266,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 668034 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1251 Data size: 668034 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mergejoins_mixed.q.out b/ql/src/test/results/clientpositive/mergejoins_mixed.q.out index 9ac6d59fc7..63c06893d3 100644 --- a/ql/src/test/results/clientpositive/mergejoins_mixed.q.out +++ b/ql/src/test/results/clientpositive/mergejoins_mixed.q.out @@ -23,70 +23,70 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: d filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -100,10 +100,10 @@ STAGE PLANS: 2 _col0 (type: string) 3 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -132,66 +132,66 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -205,10 +205,10 @@ STAGE PLANS: 2 _col0 (type: string) 3 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -237,62 +237,62 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -306,10 +306,10 @@ STAGE PLANS: 2 _col0 (type: string) 3 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -338,62 +338,62 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -407,10 +407,10 @@ STAGE PLANS: 2 _col0 (type: string) 3 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,36 +441,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -480,7 +480,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -496,20 +496,20 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -519,7 +519,7 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -535,24 +535,24 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: d filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -562,10 +562,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -596,36 +596,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -635,7 +635,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -651,20 +651,20 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -674,7 +674,7 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -690,20 +690,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -713,10 +713,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -747,36 +747,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -786,7 +786,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -802,20 +802,20 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -825,7 +825,7 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -841,20 +841,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -864,10 +864,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -898,36 +898,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -937,7 +937,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -953,20 +953,20 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -976,7 +976,7 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -992,20 +992,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1015,10 +1015,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1049,36 +1049,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1088,7 +1088,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1104,20 +1104,20 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1127,7 +1127,7 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1143,20 +1143,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1166,10 +1166,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1200,36 +1200,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1239,7 +1239,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1255,20 +1255,20 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1278,7 +1278,7 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1294,20 +1294,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1317,10 +1317,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1351,36 +1351,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1390,7 +1390,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1406,20 +1406,20 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1429,7 +1429,7 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1445,20 +1445,20 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1468,10 +1468,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1501,36 +1501,36 @@ STAGE PLANS: TableScan alias: a_n5 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1540,7 +1540,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1556,33 +1556,33 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: d - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1594,10 +1594,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/metadata_only_queries.q.out index b8abe8f7b9..105619e1e1 100644 --- a/ql/src/test/results/clientpositive/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/metadata_only_queries.q.out @@ -192,19 +192,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 3306348 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 3306348 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -212,14 +212,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -247,19 +247,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl_part - Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 4116353 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 4116353 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -267,14 +267,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -302,19 +302,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 3306348 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9999 Data size: 3306348 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -322,14 +322,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -357,19 +357,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl_part - Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 4116353 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), bo (type: boolean), bin (type: binary), si (type: smallint), i (type: int), b (type: bigint) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 4116353 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -377,14 +377,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -612,19 +612,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: stats_tbl_part - Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 1339425 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) outputColumnNames: ts - Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9489 Data size: 1339425 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(ts) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -632,10 +632,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/mm_all.q.out b/ql/src/test/results/clientpositive/mm_all.q.out index e5428bbe07..5ba8e9bd1a 100644 --- a/ql/src/test/results/clientpositive/mm_all.q.out +++ b/ql/src/test/results/clientpositive/mm_all.q.out @@ -69,14 +69,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: intermediate_n0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -86,18 +86,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), UDFToInteger('455') (type: int) outputColumnNames: key, key_mm - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') keys: key_mm (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1284 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator @@ -105,14 +105,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1332 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1332 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1332 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_distinct.q.out b/ql/src/test/results/clientpositive/multi_insert_distinct.q.out index e86711ad6c..3e0d843d61 100644 --- a/ql/src/test/results/clientpositive/multi_insert_distinct.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_distinct.q.out @@ -77,32 +77,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tmp1 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), v2 (type: string), v3 (type: string) outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT v2), count(DISTINCT v3) keys: v1 (type: string), v2 (type: string), v3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), v2 (type: string), v3 (type: string) outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT v3) keys: v1 (type: string), v2 (type: string), v3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -115,14 +115,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -147,7 +147,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -155,14 +155,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -242,32 +242,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tmp1 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), v2 (type: string), v3 (type: string) outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT v2), count(DISTINCT v3) keys: v1 (type: string), v2 (type: string), v3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), v2 (type: string), v3 (type: string) outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(v3) keys: v1 (type: string), v2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -280,14 +280,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -312,7 +312,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -321,14 +321,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -402,31 +402,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tmp1 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), v2 (type: string), v3 (type: string) outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT v2), count(DISTINCT v3) keys: v1 (type: string), v2 (type: string), v3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), v2 (type: string), v3 (type: string) outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: v1 (type: string), v2 (type: string), v3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -439,14 +439,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -471,17 +471,17 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_gby.q.out b/ql/src/test/results/clientpositive/multi_insert_gby.q.out index 9c7b61eb3f..5350c67f2d 100644 --- a/ql/src/test/results/clientpositive/multi_insert_gby.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_gby.q.out @@ -42,35 +42,35 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key > 500) or (key > 450)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > 450) or (key > 500)) (type: boolean) - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 > 450) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 9570 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -79,12 +79,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -93,20 +93,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 > 500) (type: boolean) - Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 9570 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -115,12 +115,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -152,7 +152,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -160,10 +160,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -193,7 +193,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -201,10 +201,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -312,33 +312,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -347,12 +347,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -361,20 +361,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 > 450) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -383,12 +383,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -420,7 +420,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -428,10 +428,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -461,7 +461,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -469,10 +469,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_gby2.q.out b/ql/src/test/results/clientpositive/multi_insert_gby2.q.out index 0b392fe968..e89bb555a9 100644 --- a/ql/src/test/results/clientpositive/multi_insert_gby2.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_gby2.q.out @@ -41,31 +41,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -74,19 +74,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: count - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(count, 'hll') mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -95,10 +95,10 @@ STAGE PLANS: aggregations: percentile_approx(VALUE._col0, 0.5) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -107,19 +107,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: double) outputColumnNames: percentile - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(percentile, 'hll') mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_gby3.q.out b/ql/src/test/results/clientpositive/multi_insert_gby3.q.out index 677d9d479f..53c4097211 100644 --- a/ql/src/test/results/clientpositive/multi_insert_gby3.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_gby3.q.out @@ -52,32 +52,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col2) keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -90,14 +90,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -106,12 +106,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -143,7 +143,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -151,10 +151,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -176,7 +176,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -185,14 +185,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -201,12 +201,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) outputColumnNames: key, keyd, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -230,7 +230,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -238,10 +238,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -277,33 +277,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double) Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col2) keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -316,14 +316,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -332,12 +332,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) outputColumnNames: key, keyd, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -369,7 +369,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -377,10 +377,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -402,7 +402,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -410,14 +410,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -426,12 +426,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -455,7 +455,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -463,10 +463,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1816,32 +1816,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT key) keys: value (type: string), key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1854,14 +1854,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1870,12 +1870,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1907,7 +1907,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1915,10 +1915,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1940,7 +1940,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -1948,14 +1948,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1964,12 +1964,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1993,7 +1993,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2001,10 +2001,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2048,32 +2048,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT _col2) keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2085,7 +2085,7 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: double), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2098,14 +2098,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2114,12 +2114,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2151,7 +2151,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2159,10 +2159,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2192,7 +2192,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -2201,14 +2201,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2217,12 +2217,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) outputColumnNames: key, keyd, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2246,7 +2246,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2254,10 +2254,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2271,7 +2271,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -2279,14 +2279,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToDouble(_col3) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2295,12 +2295,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2324,7 +2324,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2332,10 +2332,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_gby4.q.out b/ql/src/test/results/clientpositive/multi_insert_gby4.q.out index eed39eedf8..8bc668e1f9 100644 --- a/ql/src/test/results/clientpositive/multi_insert_gby4.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_gby4.q.out @@ -58,39 +58,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col0 > 500) or (_col0 > 450)) or (_col0 > 490)) (type: boolean) - Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 > 450) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -99,12 +99,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -113,20 +113,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 > 500) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -135,12 +135,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -149,20 +149,20 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (KEY._col0 > 490) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -171,12 +171,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, count - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -208,7 +208,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -216,10 +216,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -257,7 +257,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -265,10 +265,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -290,7 +290,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -298,10 +298,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_mixed.q.out b/ql/src/test/results/clientpositive/multi_insert_mixed.q.out index 478a379c35..f097d6b6c3 100644 --- a/ql/src/test/results/clientpositive/multi_insert_mixed.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_mixed.q.out @@ -53,33 +53,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -88,14 +88,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,12 +104,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -122,7 +122,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -137,17 +137,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), CAST( VALUE._col0 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -156,19 +156,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -200,7 +200,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -209,7 +209,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -224,17 +224,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), CAST( VALUE._col0 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -243,19 +243,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -303,7 +303,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -311,10 +311,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out b/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out index 7e720b6021..a6a00b11c9 100644 --- a/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out @@ -39,17 +39,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -58,26 +58,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -86,12 +86,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -103,10 +103,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -157,7 +157,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -165,10 +165,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -257,17 +257,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -276,26 +276,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -304,12 +304,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -321,10 +321,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -414,7 +414,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -422,10 +422,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -514,17 +514,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -533,26 +533,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -561,12 +561,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -578,10 +578,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -671,7 +671,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -679,10 +679,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -776,17 +776,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -795,26 +795,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -823,12 +823,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -840,10 +840,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -972,7 +972,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -980,10 +980,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1069,30 +1069,30 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1101,12 +1101,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1115,15 +1115,15 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1132,12 +1132,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1190,7 +1190,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1198,10 +1198,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1213,7 +1213,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1221,10 +1221,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1313,30 +1313,30 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1345,12 +1345,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1359,15 +1359,15 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1376,12 +1376,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1473,7 +1473,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1481,10 +1481,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1535,7 +1535,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1543,10 +1543,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1625,30 +1625,30 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1657,12 +1657,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1671,15 +1671,15 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1688,12 +1688,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1746,7 +1746,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1754,10 +1754,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1769,7 +1769,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1777,10 +1777,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1869,30 +1869,30 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1901,12 +1901,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1915,15 +1915,15 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1932,12 +1932,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2029,7 +2029,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2037,10 +2037,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2091,7 +2091,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2099,10 +2099,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2179,19 +2179,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2200,22 +2200,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2224,12 +2224,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2238,19 +2238,19 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2259,22 +2259,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2283,12 +2283,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2300,10 +2300,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2354,7 +2354,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2362,10 +2362,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2473,19 +2473,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2494,22 +2494,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2518,12 +2518,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2532,19 +2532,19 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2553,22 +2553,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2577,12 +2577,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2594,10 +2594,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2687,7 +2687,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -2695,10 +2695,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2806,19 +2806,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2827,22 +2827,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2851,12 +2851,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2865,19 +2865,19 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2886,22 +2886,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2910,12 +2910,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -2927,10 +2927,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3020,7 +3020,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -3028,10 +3028,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3144,19 +3144,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3165,22 +3165,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3189,12 +3189,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3203,19 +3203,19 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3224,22 +3224,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((_col0 < 20) and (_col0 > 10)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3248,12 +3248,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3265,10 +3265,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3397,7 +3397,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -3405,10 +3405,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3508,45 +3508,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 2) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 4) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3607,45 +3607,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 2) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 4) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3706,45 +3706,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 2) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 4) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3805,45 +3805,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 2) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (key = 4) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -3905,42 +3905,42 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -3965,17 +3965,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4021,42 +4021,42 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4081,17 +4081,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4137,42 +4137,42 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4197,17 +4197,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4253,42 +4253,42 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4313,17 +4313,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4378,17 +4378,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4397,26 +4397,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4425,12 +4425,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4439,7 +4439,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4451,10 +4451,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4505,7 +4505,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -4513,10 +4513,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4530,34 +4530,34 @@ STAGE PLANS: key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4579,17 +4579,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4696,17 +4696,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4715,26 +4715,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -4743,12 +4743,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4757,7 +4757,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4769,10 +4769,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4862,7 +4862,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -4870,10 +4870,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4887,34 +4887,34 @@ STAGE PLANS: key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -4936,17 +4936,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -5053,17 +5053,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -5072,26 +5072,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -5100,12 +5100,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -5114,7 +5114,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -5126,10 +5126,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5219,7 +5219,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -5227,10 +5227,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5244,34 +5244,34 @@ STAGE PLANS: key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -5293,17 +5293,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -5415,17 +5415,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -5434,26 +5434,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Filter Operator predicate: ((key < 20) and (key > 10)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -5462,12 +5462,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -5476,7 +5476,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -5488,10 +5488,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5620,7 +5620,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -5628,10 +5628,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5645,34 +5645,34 @@ STAGE PLANS: key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 221 Data size: 2347 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 775 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: ((KEY._col0 < 20) and (KEY._col0 > 10)) (type: boolean) - Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -5694,17 +5694,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_union_src.q.out b/ql/src/test/results/clientpositive/multi_insert_union_src.q.out index a35c1e48a9..b7236c0518 100644 --- a/ql/src/test/results/clientpositive/multi_insert_union_src.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_union_src.q.out @@ -63,27 +63,27 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 174 Data size: 1824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 59555 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (_col0 < 150) (type: boolean) - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 28918 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 28918 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) Filter Operator predicate: (_col0 > 400) (type: boolean) - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 28918 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -93,27 +93,27 @@ STAGE PLANS: TableScan alias: src2_n4 filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58155 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58155 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 174 Data size: 1824 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174 Data size: 59555 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (_col0 < 150) (type: boolean) - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 28918 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 28918 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string) Filter Operator predicate: (_col0 > 400) (type: boolean) - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 28918 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -124,10 +124,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 10150 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 10150 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -136,19 +136,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 10150 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -179,17 +179,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col1 (type: string) sort order: + - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 28918 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 10150 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 10150 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -198,19 +198,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 58 Data size: 608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58 Data size: 10150 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out b/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out index 0e7538403b..48915010ae 100644 --- a/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out @@ -80,30 +80,30 @@ STAGE PLANS: TableScan alias: a filterExpr: (id = 'Id_1') (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (id = 'Id_1') (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -112,14 +112,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'Id_1' (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -128,12 +128,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -165,7 +165,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -173,10 +173,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -208,30 +208,30 @@ STAGE PLANS: TableScan alias: a filterExpr: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: string) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((val = 'val_104') and (id = 'Id_2')) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((id = 'Id_2') and (val = 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -240,14 +240,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'Id_2' (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -256,12 +256,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -293,7 +293,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -301,10 +301,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -343,21 +343,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) TableScan alias: b - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -367,17 +367,17 @@ STAGE PLANS: 0 id (type: string) 1 id (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 <> _col6) and (_col5 = 'Id_2') and (_col6 = 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -386,12 +386,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -400,14 +400,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -416,12 +416,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -453,7 +453,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -461,10 +461,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -494,7 +494,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -502,10 +502,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -544,21 +544,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) TableScan alias: b - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -568,17 +568,17 @@ STAGE PLANS: 0 id (type: string) 1 id (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -587,12 +587,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -601,14 +601,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col5 = 'Id_2') and (_col6 = 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -617,12 +617,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -654,7 +654,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -662,10 +662,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -695,7 +695,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -703,10 +703,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -746,28 +746,28 @@ STAGE PLANS: TableScan alias: a filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) TableScan alias: b filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -777,17 +777,17 @@ STAGE PLANS: 0 id (type: string) 1 id (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -796,12 +796,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -810,14 +810,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col5 = 'Id_2') and (_col6 = 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -826,12 +826,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -863,7 +863,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -871,10 +871,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -904,7 +904,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -912,10 +912,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -955,28 +955,28 @@ STAGE PLANS: TableScan alias: a filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) TableScan alias: b filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: id (type: string) sort order: + Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -986,17 +986,17 @@ STAGE PLANS: 0 id (type: string) 1 id (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1005,12 +1005,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1019,14 +1019,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col5 = 'Id_2') and (_col6 = 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1035,12 +1035,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1072,7 +1072,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1080,10 +1080,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1113,7 +1113,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1121,10 +1121,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1164,36 +1164,36 @@ STAGE PLANS: TableScan alias: a filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1203,21 +1203,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 'val_103') and (_col3 = 'Id_1')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1226,12 +1226,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1240,14 +1240,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1256,12 +1256,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1293,7 +1293,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1301,10 +1301,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1334,7 +1334,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1342,10 +1342,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1385,36 +1385,36 @@ STAGE PLANS: TableScan alias: a filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1424,21 +1424,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 'val_103') and (_col3 = 'Id_1')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col3 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1447,12 +1447,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1461,14 +1461,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1477,12 +1477,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1514,7 +1514,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1522,10 +1522,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1555,7 +1555,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1563,10 +1563,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multi_join_union.q.out b/ql/src/test/results/clientpositive/multi_join_union.q.out index 991ffd5f34..8cdde0a9c0 100644 --- a/ql/src/test/results/clientpositive/multi_join_union.q.out +++ b/ql/src/test/results/clientpositive/multi_join_union.q.out @@ -79,14 +79,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -95,16 +95,16 @@ STAGE PLANS: TableScan alias: src13 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 950 Data size: 332818 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col3 (type: string) @@ -113,16 +113,16 @@ STAGE PLANS: TableScan alias: src14 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 950 Data size: 332818 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col3 (type: string) @@ -134,14 +134,14 @@ STAGE PLANS: TableScan alias: b filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450 Data size: 157651 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450 Data size: 157651 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -149,7 +149,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 522 Data size: 183049 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -157,10 +157,10 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1045 Data size: 366099 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1045 Data size: 366099 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/multigroupby_singlemr.q.out b/ql/src/test/results/clientpositive/multigroupby_singlemr.q.out index 1cc0684778..f0b7a2191c 100644 --- a/ql/src/test/results/clientpositive/multigroupby_singlemr.q.out +++ b/ql/src/test/results/clientpositive/multigroupby_singlemr.q.out @@ -64,33 +64,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: int) outputColumnNames: c1, c2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c2) keys: c1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Select Operator expressions: c1 (type: int), c2 (type: int), c3 (type: int) outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c3) keys: c1 (type: int), c2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -104,14 +104,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -120,12 +120,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: d1, d2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -157,7 +157,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -165,10 +165,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -190,7 +190,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -199,14 +199,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -215,12 +215,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -244,7 +244,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -252,10 +252,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -287,33 +287,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: int) outputColumnNames: c1, c2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c2) keys: c1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Select Operator expressions: c1 (type: int), c2 (type: int), c3 (type: int) outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c3) keys: c2 (type: int), c1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -327,14 +327,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -343,12 +343,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: d1, d2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -380,7 +380,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -388,10 +388,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -413,7 +413,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -422,14 +422,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: int), _col0 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -438,12 +438,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -467,7 +467,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -475,10 +475,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -510,33 +510,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c4) keys: c1 (type: int), c2 (type: int), c3 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Select Operator expressions: c1 (type: int), c2 (type: int), c3 (type: int) outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c3) keys: c1 (type: int), c2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -550,14 +550,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -566,12 +566,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -603,7 +603,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -611,10 +611,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -636,7 +636,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -645,14 +645,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -661,12 +661,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -690,7 +690,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -698,10 +698,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -732,34 +732,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: c1 (type: int), c2 (type: int), c3 (type: int) sort order: +++ Map-reduce partition columns: c1 (type: int), c2 (type: int), c3 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: c4 (type: int) Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -768,12 +768,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -785,14 +785,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col2 (type: int), KEY._col1 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -801,12 +801,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -838,7 +838,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -846,10 +846,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -879,7 +879,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -887,10 +887,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -928,33 +928,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c4) keys: c1 (type: int), c2 (type: int), c3 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint) Select Operator expressions: c1 (type: int), c2 (type: int), c3 (type: int) outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c3) keys: c1 (type: int), c2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -964,13 +964,13 @@ STAGE PLANS: Select Operator expressions: c1 (type: int), c2 (type: int) outputColumnNames: c1, c2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(c2) keys: c1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -984,14 +984,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1000,12 +1000,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1037,7 +1037,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1696 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1045,10 +1045,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1078,7 +1078,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1087,14 +1087,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1103,12 +1103,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1132,7 +1132,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1272 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1140,10 +1140,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1157,7 +1157,7 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1166,14 +1166,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1182,12 +1182,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: d1, d2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1211,7 +1211,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1219,10 +1219,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 896 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 896 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/named_column_join.q.out b/ql/src/test/results/clientpositive/named_column_join.q.out index 8b59410e11..0022d0bd8a 100644 --- a/ql/src/test/results/clientpositive/named_column_join.q.out +++ b/ql/src/test/results/clientpositive/named_column_join.q.out @@ -31,36 +31,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: a is not null (type: boolean) - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: a is not null (type: boolean) - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: t2 filterExpr: a is not null (type: boolean) - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: a is not null (type: boolean) - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -70,14 +70,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 8 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 132 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 132 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 132 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nested_column_pruning.q.out b/ql/src/test/results/clientpositive/nested_column_pruning.q.out index 02a271641b..0b1f6df90a 100644 --- a/ql/src/test/results/clientpositive/nested_column_pruning.q.out +++ b/ql/src/test/results/clientpositive/nested_column_pruning.q.out @@ -135,14 +135,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: nested_tbl_1_n1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,14 +178,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f1 (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -221,14 +221,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f1, s1.f2 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f1 (type: boolean), s1.f2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -264,14 +264,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -307,14 +307,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f3.f5 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -350,14 +350,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f3.f4, s2.f8.f9 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f4 (type: int), s2.f8.f9 (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -394,17 +394,17 @@ STAGE PLANS: alias: nested_tbl_1_n1 filterExpr: (s1.f1 = false) (type: boolean) Pruned Column Paths: s1.f2, s1.f1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f1 = false) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,17 +441,17 @@ STAGE PLANS: alias: nested_tbl_1_n1 filterExpr: (s1.f3.f4 = 4) (type: boolean) Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f3.f4 = 4) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -488,17 +488,17 @@ STAGE PLANS: alias: nested_tbl_1_n1 filterExpr: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) Pruned Column Paths: s1.f2, s2.f8 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s2.f8 (type: struct,f11:map>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -538,32 +538,32 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s2.f8.f10 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s3 (type: struct>>) outputColumnNames: s3 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int) outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -571,20 +571,20 @@ STAGE PLANS: Select Operator expressions: _col3.f12 (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -592,29 +592,29 @@ STAGE PLANS: Select Operator expressions: s2.f8.f10 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int) outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -622,20 +622,20 @@ STAGE PLANS: Select Operator expressions: _col3.f12 (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -678,14 +678,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s2.f8.f10, s1.f3.f4 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (s2.f8.f10[1] pmod s1.f3.f4) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -721,22 +721,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -744,10 +744,10 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -783,22 +783,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: struct) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -806,10 +806,10 @@ STAGE PLANS: keys: KEY._col0 (type: struct) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -846,22 +846,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: struct) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -869,7 +869,7 @@ STAGE PLANS: keys: KEY._col0 (type: struct) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -884,16 +884,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: struct) sort order: + - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -935,36 +935,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f3.f4 (type: int) sort order: + Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: ((s2.f8.f9 = false) and s1.f6 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((s2.f8.f9 = false) and s1.f6 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f6 (type: int) sort order: + Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -974,14 +974,14 @@ STAGE PLANS: 0 _col0.f3.f4 (type: int) 1 _col0.f6 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1031,36 +1031,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f3.f4 (type: int) sort order: + Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: (s2.f8.f9 and s1.f6 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f6 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f6 (type: int) sort order: + Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -1070,14 +1070,14 @@ STAGE PLANS: 0 _col0.f3.f4 (type: int) 1 _col0.f6 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1123,42 +1123,42 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int), true (type: boolean) sort order: ++ Map-reduce partition columns: _col1 (type: int), true (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: (s2.f8.f9 and s1.f6 is not null and s2.f8.f9 is not null) (type: boolean) Pruned Column Paths: s1.f6, s2.f8.f9 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f6 is not null and s2.f8.f9 and s2.f8.f9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f6 (type: int), (s2.f8.f9 = true) (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: boolean) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: boolean) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -1167,14 +1167,14 @@ STAGE PLANS: 0 _col1 (type: int), true (type: boolean) 1 _col0 (type: int), _col1 (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1218,25 +1218,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s2 (type: struct,f11:map>>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -1247,14 +1247,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 residual filter predicates: {(_col0.f1 <> _col1.f8.f9)} - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1299,37 +1299,37 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: s1.f6 is not null (type: boolean) Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f6 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s2 (type: struct,f11:map>>), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -1340,14 +1340,14 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col2 residual filter predicates: {(_col0.f1 <> _col2.f8.f9)} - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1430,22 +1430,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s3.f12, s1.f6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s3.f12[0].f14 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1453,14 +1453,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1506,22 +1506,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s4['key1'].f15 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1529,14 +1529,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1582,22 +1582,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s5.f16, s1.f6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s5.f16[0].f18.f19 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1605,14 +1605,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1658,22 +1658,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f6, s5.f16 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s5 (type: struct>>>) outputColumnNames: s1, s5 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(s1.f6) keys: s5.f16.f18.f19 (type: array) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: array) sort order: + Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1681,14 +1681,14 @@ STAGE PLANS: keys: KEY._col0 (type: array) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1734,22 +1734,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s6['key1'].f20[0].f21.f22 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1757,14 +1757,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1810,22 +1810,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n1 Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s6 (type: map>>>>) outputColumnNames: s1, s6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(s1.f6) keys: s6['key1'].f20.f21.f22 (type: array) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: array) sort order: + Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1833,14 +1833,14 @@ STAGE PLANS: keys: KEY._col0 (type: array) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/no_hooks.q.out b/ql/src/test/results/clientpositive/no_hooks.q.out index 3826fd3ad6..55aaff3870 100644 --- a/ql/src/test/results/clientpositive/no_hooks.q.out +++ b/ql/src/test/results/clientpositive/no_hooks.q.out @@ -14,24 +14,24 @@ STAGE PLANS: TableScan alias: src1 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) TableScan alias: src2 filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) Reduce Operator Tree: Join Operator @@ -41,11 +41,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -60,16 +60,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/noalias_subq1.q.out b/ql/src/test/results/clientpositive/noalias_subq1.q.out index d93e7a00c5..e0904a4220 100644 --- a/ql/src/test/results/clientpositive/noalias_subq1.q.out +++ b/ql/src/test/results/clientpositive/noalias_subq1.q.out @@ -15,17 +15,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out index 0365705ed9..24ce5fe858 100644 --- a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out +++ b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out @@ -12,14 +12,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(key) + 1.0D) (type: double), ((UDFToDouble(key) + 1.0D) + 1.0D) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -95,14 +95,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan Reduce Output Operator @@ -117,10 +117,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -249,11 +249,11 @@ STAGE PLANS: $hdt$_0:src1 TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -270,10 +270,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nonmr_fetch.q.out b/ql/src/test/results/clientpositive/nonmr_fetch.q.out index 366dc1eb34..ff42929a41 100644 --- a/ql/src/test/results/clientpositive/nonmr_fetch.q.out +++ b/ql/src/test/results/clientpositive/nonmr_fetch.q.out @@ -12,14 +12,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from src limit 10 @@ -55,14 +55,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from srcpart where ds='2008-04-08' AND hr='11' limit 10 @@ -99,14 +99,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key from src limit 10 @@ -142,20 +142,20 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (UDFToDouble(key) > 100.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4560 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4560 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -205,20 +205,20 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5460 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 5460 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -271,17 +271,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -326,14 +326,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from src limit 10 @@ -369,14 +369,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from srcpart where ds='2008-04-08' AND hr='11' limit 10 @@ -413,14 +413,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select cast(key as int) * 10, upper(value) from src limit 10 @@ -456,17 +456,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key from src where key < 100 limit 10 @@ -502,14 +502,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key from srcpart where ds='2008-04-08' AND hr='11' limit 10 @@ -547,17 +547,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select *, BLOCK__OFFSET__INSIDE__FILE from src where key < 100 limit 10 @@ -593,17 +593,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 368964 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 30 - Statistics: Num rows: 30 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16620 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select *, BLOCK__OFFSET__INSIDE__FILE from srcpart where key < 10 limit 30 @@ -666,14 +666,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hash(key) & 2147483647) % 40) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select *, BLOCK__OFFSET__INSIDE__FILE from src TABLESAMPLE (BUCKET 1 OUT OF 40 ON key) @@ -712,14 +712,14 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (((hash(key) & 2147483647) % 40) = 0) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 554000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select *, BLOCK__OFFSET__INSIDE__FILE from srcpart TABLESAMPLE (BUCKET 1 OUT OF 40 ON key) @@ -808,11 +808,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from src TABLESAMPLE (0.25 PERCENT) @@ -839,11 +839,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1108000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select *, BLOCK__OFFSET__INSIDE__FILE from srcpart TABLESAMPLE (0.25 PERCENT) @@ -887,17 +887,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 250.0D) and (UDFToDouble(key) > 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key, value from (select value key,key value from src where key > 200) a where value < 250 limit 20 @@ -945,41 +945,41 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 351000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col7 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 1311000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE ListSink Select Operator expressions: array(key,value) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 960000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 960000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col7 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 1311000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key,X from srcpart lateral view explode(array(key,value)) L as x where (ds='2008-04-08' AND hr='11') limit 20 @@ -1026,14 +1026,14 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (rand() > 1.0D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 61938 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select key, value, BLOCK__OFFSET__INSIDE__FILE from srcpart where ds="2008-04-09" AND rand() > 1 @@ -1062,22 +1062,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1086,10 +1086,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1115,31 +1115,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1167,31 +1167,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1252,36 +1252,36 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1291,10 +1291,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out b/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out index e5d6e6b1d3..5236e8fcc1 100644 --- a/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out +++ b/ql/src/test/results/clientpositive/nonmr_fetch_threshold.q.out @@ -13,14 +13,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select cast(key as int) * 10, upper(value) from src limit 10 @@ -37,14 +37,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from srcpart where ds='2008-04-08' AND hr='11' limit 10 @@ -62,14 +62,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select cast(key as int) * 10, upper(value) from src limit 10 @@ -86,14 +86,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select concat(key, value) from src @@ -110,11 +110,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: concat(key, value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from srcpart where ds='2008-04-08' AND hr='11' limit 10 @@ -132,14 +132,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 179000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select cast(key as int) * 10, upper(value) from src limit 10 @@ -156,14 +156,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(key) * 10) (type: int), upper(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select concat(key, value) from src @@ -180,14 +180,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: concat(key, value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -214,11 +214,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select key from src @@ -235,11 +235,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from src @@ -256,11 +256,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select key,1 from src @@ -277,11 +277,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select cast(key as char(20)),1 from src @@ -298,10 +298,10 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( key AS CHAR(20)) (type: char(20)), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 54000 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out b/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out index 37f86456ac..d6ae7ffcac 100644 --- a/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out +++ b/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out @@ -26,34 +26,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -62,12 +62,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, as - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(as, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -99,7 +99,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -107,10 +107,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -155,34 +155,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -191,12 +191,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, as - Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 9500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(as, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -228,7 +228,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -236,10 +236,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -293,34 +293,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -329,12 +329,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, as - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(as, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -366,7 +366,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -374,10 +374,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/notable_alias1.q.out b/ql/src/test/results/clientpositive/notable_alias1.q.out index 082a9c82b3..e39fa9a867 100644 --- a/ql/src/test/results/clientpositive/notable_alias1.q.out +++ b/ql/src/test/results/clientpositive/notable_alias1.q.out @@ -27,21 +27,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -50,14 +50,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -66,12 +66,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) outputColumnNames: dummy, key, value - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(dummy, 'hll'), compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -103,7 +103,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -111,10 +111,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/notable_alias2.q.out b/ql/src/test/results/clientpositive/notable_alias2.q.out index 2deeefdf18..2d70ec72fe 100644 --- a/ql/src/test/results/clientpositive/notable_alias2.q.out +++ b/ql/src/test/results/clientpositive/notable_alias2.q.out @@ -27,21 +27,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -50,14 +50,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -66,12 +66,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) outputColumnNames: dummy, key, value - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(dummy, 'hll'), compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -103,7 +103,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -111,10 +111,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullformatCTAS.q.out b/ql/src/test/results/clientpositive/nullformatCTAS.q.out index b6b51d5e54..23f78288ef 100644 --- a/ql/src/test/results/clientpositive/nullformatCTAS.q.out +++ b/ql/src/test/results/clientpositive/nullformatCTAS.q.out @@ -57,14 +57,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: base_tab_n2 - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/nullgroup.q.out b/ql/src/test/results/clientpositive/nullgroup.q.out index 04b1ad967a..9a8ecec57a 100644 --- a/ql/src/test/results/clientpositive/nullgroup.q.out +++ b/ql/src/test/results/clientpositive/nullgroup.q.out @@ -15,30 +15,30 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -76,30 +76,30 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -138,22 +138,22 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count() mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -167,17 +167,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -215,24 +215,24 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count() mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullgroup2.q.out b/ql/src/test/results/clientpositive/nullgroup2.q.out index 60b6aefe49..04da5d543f 100644 --- a/ql/src/test/results/clientpositive/nullgroup2.q.out +++ b/ql/src/test/results/clientpositive/nullgroup2.q.out @@ -16,21 +16,21 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -39,7 +39,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -55,7 +55,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -64,10 +64,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -104,21 +104,21 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -127,10 +127,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -168,15 +168,15 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -184,7 +184,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -200,7 +200,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -209,10 +209,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -249,15 +249,15 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -265,10 +265,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullgroup3.q.out b/ql/src/test/results/clientpositive/nullgroup3.q.out index c17d0cc71d..5450b5bcb2 100644 --- a/ql/src/test/results/clientpositive/nullgroup3.q.out +++ b/ql/src/test/results/clientpositive/nullgroup3.q.out @@ -40,17 +40,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tstparttbl_n0 - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -58,10 +58,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -128,17 +128,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tstparttbl2_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -146,10 +146,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -224,17 +224,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tstparttbl_n0 - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -242,10 +242,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -320,17 +320,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tstparttbl2_n0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -338,10 +338,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullgroup4.q.out b/ql/src/test/results/clientpositive/nullgroup4.q.out index 6f36b03ee0..408d665429 100644 --- a/ql/src/test/results/clientpositive/nullgroup4.q.out +++ b/ql/src/test/results/clientpositive/nullgroup4.q.out @@ -16,32 +16,32 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(DISTINCT value) keys: value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 13375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 13375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -55,7 +55,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -63,10 +63,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -105,25 +105,25 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -132,12 +132,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), count(_col0) mode: partial2 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -151,7 +151,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -159,10 +159,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -201,26 +201,26 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(), count(DISTINCT KEY._col0:0._col0) mode: partial1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -234,7 +234,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -242,10 +242,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -283,28 +283,28 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: value (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(), count(DISTINCT KEY._col0:0._col0) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out b/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out index 8af20937de..fc8b539859 100644 --- a/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out +++ b/ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out @@ -15,34 +15,34 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(DISTINCT _col0), count(DISTINCT _col1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 37375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 37375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -80,28 +80,28 @@ STAGE PLANS: TableScan alias: x filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullgroup5.q.out b/ql/src/test/results/clientpositive/nullgroup5.q.out index cffd076ee4..0710fdcd95 100644 --- a/ql/src/test/results/clientpositive/nullgroup5.q.out +++ b/ql/src/test/results/clientpositive/nullgroup5.q.out @@ -59,19 +59,19 @@ STAGE PLANS: TableScan alias: x filterExpr: (ds = '2009-04-05') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (ds = '2009-04-05') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 121 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 121 Data size: 100808 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 121 Data size: 100808 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -79,16 +79,16 @@ STAGE PLANS: TableScan alias: y filterExpr: (ds = '2009-04-09') (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 100440 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 120 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 120 Data size: 100440 Basic stats: PARTIAL Column stats: NONE Union - Statistics: Num rows: 121 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 121 Data size: 100808 Basic stats: PARTIAL Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 58120 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 121 Data size: 100808 Basic stats: PARTIAL Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/nullscript.q.out b/ql/src/test/results/clientpositive/nullscript.q.out index e05bd1cee3..b8b76bbaa4 100644 --- a/ql/src/test/results/clientpositive/nullscript.q.out +++ b/ql/src/test/results/clientpositive/nullscript.q.out @@ -38,21 +38,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: nullscript - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out b/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out index f7475f5984..ba5755d2d3 100644 --- a/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out +++ b/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out @@ -19,17 +19,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 410 TopN Hash Memory Usage: 0.1 @@ -244,17 +244,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 Offset of rows: 400 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -325,17 +325,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 500 TopN Hash Memory Usage: 0.1 @@ -550,17 +550,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 Offset of rows: 490 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -631,17 +631,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 510 TopN Hash Memory Usage: 0.1 @@ -856,17 +856,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 20 Offset of rows: 490 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 12780 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 12780 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -947,17 +947,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 1090 TopN Hash Memory Usage: 0.1 @@ -1172,17 +1172,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 600 Offset of rows: 490 - Statistics: Num rows: 600 Data size: 6000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 383400 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 600 Data size: 6000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 383400 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1838,17 +1838,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 410 TopN Hash Memory Usage: 0.1 @@ -2063,17 +2063,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 Offset of rows: 400 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2139,17 +2139,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 500 TopN Hash Memory Usage: 0.1 @@ -2364,17 +2364,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 Offset of rows: 490 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 6390 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2440,17 +2440,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 510 TopN Hash Memory Usage: 0.1 @@ -2665,17 +2665,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 20 Offset of rows: 490 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 12780 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 12780 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2751,17 +2751,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 TopN: 1090 TopN Hash Memory Usage: 0.1 @@ -2976,17 +2976,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1278000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 600 Offset of rows: 490 - Statistics: Num rows: 600 Data size: 6000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 383400 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 600 Data size: 6000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 383400 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/optional_outer.q.out b/ql/src/test/results/clientpositive/optional_outer.q.out index 9ec1af7cba..8c8109607f 100644 --- a/ql/src/test/results/clientpositive/optional_outer.q.out +++ b/ql/src/test/results/clientpositive/optional_outer.q.out @@ -12,29 +12,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -44,10 +44,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -73,29 +73,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -105,10 +105,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -134,29 +134,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -166,10 +166,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -195,29 +195,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -227,10 +227,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -256,29 +256,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -288,10 +288,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -317,29 +317,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -349,10 +349,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 281952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_createas1.q.out b/ql/src/test/results/clientpositive/orc_createas1.q.out index ecfad35286..f6a8ea39ad 100644 --- a/ql/src/test/results/clientpositive/orc_createas1.q.out +++ b/ql/src/test/results/clientpositive/orc_createas1.q.out @@ -69,14 +69,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -161,28 +161,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_createas1b - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1750 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1750 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -236,14 +236,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_createas1a - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), (hash(key) pmod 50) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out index 73d55e7de0..380dba5e78 100644 --- a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out +++ b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out @@ -186,14 +186,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypes_orc_n0 - Statistics: Num rows: 2 Data size: 1908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ti (type: tinyint), si (type: bigint), i (type: bigint), bi (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 1908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 1908 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge1.q.out b/ql/src/test/results/clientpositive/orc_merge1.q.out index ec6dbddbcb..7c163a3bd2 100644 --- a/ql/src/test/results/clientpositive/orc_merge1.q.out +++ b/ql/src/test/results/clientpositive/orc_merge1.q.out @@ -61,14 +61,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -77,18 +77,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -96,14 +96,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -175,14 +175,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -191,18 +191,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -210,14 +210,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -328,14 +328,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -344,18 +344,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -363,14 +363,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge10.q.out b/ql/src/test/results/clientpositive/orc_merge10.q.out index f04e4a3101..cff55e0292 100644 --- a/ql/src/test/results/clientpositive/orc_merge10.q.out +++ b/ql/src/test/results/clientpositive/orc_merge10.q.out @@ -61,14 +61,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -77,18 +77,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -96,14 +96,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -175,14 +175,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -191,18 +191,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -210,14 +210,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -328,14 +328,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -344,18 +344,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -363,14 +363,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge2.q.out b/ql/src/test/results/clientpositive/orc_merge2.q.out index f1a7ba7f58..0b7298125c 100644 --- a/ql/src/test/results/clientpositive/orc_merge2.q.out +++ b/ql/src/test/results/clientpositive/orc_merge2.q.out @@ -40,14 +40,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 10) (type: int), (hash(value) pmod 10) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -56,18 +56,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string), CAST( _col3 AS STRING) (type: string) outputColumnNames: key, value, one, two, three - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 274000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: one (type: string), two (type: string), three (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 329250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 329250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: struct), _col4 (type: struct), _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 333250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge3.q.out b/ql/src/test/results/clientpositive/orc_merge3.q.out index 2ac7c3104b..3351a128b1 100644 --- a/ql/src/test/results/clientpositive/orc_merge3.q.out +++ b/ql/src/test/results/clientpositive/orc_merge3.q.out @@ -70,14 +70,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orcfile_merge3a_n0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -86,25 +86,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge4.q.out b/ql/src/test/results/clientpositive/orc_merge4.q.out index 49147b5dc6..3f38a8b805 100644 --- a/ql/src/test/results/clientpositive/orc_merge4.q.out +++ b/ql/src/test/results/clientpositive/orc_merge4.q.out @@ -88,14 +88,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orcfile_merge3a - Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,25 +104,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge5.q.out b/ql/src/test/results/clientpositive/orc_merge5.q.out index 5aa64c127a..27e41a34d7 100644 --- a/ql/src/test/results/clientpositive/orc_merge5.q.out +++ b/ql/src/test/results/clientpositive/orc_merge5.q.out @@ -38,17 +38,17 @@ STAGE PLANS: TableScan alias: orc_merge5_n5 filterExpr: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -57,25 +57,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp) outputColumnNames: userid, string1, subtype, decimal1, ts - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -154,17 +154,17 @@ STAGE PLANS: TableScan alias: orc_merge5_n5 filterExpr: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -173,25 +173,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp) outputColumnNames: userid, string1, subtype, decimal1, ts - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge6.q.out b/ql/src/test/results/clientpositive/orc_merge6.q.out index 7f3d3d305b..cde1eb022c 100644 --- a/ql/src/test/results/clientpositive/orc_merge6.q.out +++ b/ql/src/test/results/clientpositive/orc_merge6.q.out @@ -38,17 +38,17 @@ STAGE PLANS: TableScan alias: orc_merge5_n4 filterExpr: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -57,18 +57,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp), '2000' (type: string), UDFToInteger('24') (type: int) outputColumnNames: userid, string1, subtype, decimal1, ts, year, hour - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') keys: year (type: string), hour (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct) Reduce Operator Tree: Group By Operator @@ -76,14 +76,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -207,17 +207,17 @@ STAGE PLANS: TableScan alias: orc_merge5_n4 filterExpr: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -226,18 +226,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp), '2000' (type: string), UDFToInteger('24') (type: int) outputColumnNames: userid, string1, subtype, decimal1, ts, year, hour - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') keys: year (type: string), hour (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct) Reduce Operator Tree: Group By Operator @@ -245,14 +245,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out b/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out index 129b19e11f..10347aee50 100644 --- a/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out +++ b/ql/src/test/results/clientpositive/orc_merge_diff_fs.q.out @@ -61,14 +61,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -77,18 +77,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -96,14 +96,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -175,14 +175,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -191,18 +191,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -210,14 +210,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -328,14 +328,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -344,18 +344,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: key, value, ds, part - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), part (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Reduce Operator Tree: Group By Operator @@ -363,14 +363,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out b/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out index f0d5026563..5e21a386a9 100644 --- a/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out +++ b/ql/src/test/results/clientpositive/orc_merge_incompat1.q.out @@ -38,17 +38,17 @@ STAGE PLANS: TableScan alias: orc_merge5_n3 filterExpr: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (userid <= 13L) (type: boolean) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -57,25 +57,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp) outputColumnNames: userid, string1, subtype, decimal1, ts - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_merge_incompat2.q.out b/ql/src/test/results/clientpositive/orc_merge_incompat2.q.out index ef7552048c..5f86f60b53 100644 --- a/ql/src/test/results/clientpositive/orc_merge_incompat2.q.out +++ b/ql/src/test/results/clientpositive/orc_merge_incompat2.q.out @@ -37,14 +37,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_merge5 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp), subtype (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -53,18 +53,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp), _col5 (type: double) outputColumnNames: userid, string1, subtype, decimal1, ts, st - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') keys: st (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct) Reduce Operator Tree: Group By Operator @@ -72,14 +72,14 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 22980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_nested_column_pruning.q.out b/ql/src/test/results/clientpositive/orc_nested_column_pruning.q.out index 83e7da2943..803aae1feb 100644 --- a/ql/src/test/results/clientpositive/orc_nested_column_pruning.q.out +++ b/ql/src/test/results/clientpositive/orc_nested_column_pruning.q.out @@ -135,14 +135,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: nested_tbl_1_n0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,14 +178,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f1 (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -221,14 +221,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f1, s1.f2 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f1 (type: boolean), s1.f2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -264,14 +264,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -307,14 +307,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f3.f5 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -350,14 +350,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f3.f4, s2.f8.f9 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f4 (type: int), s2.f8.f9 (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -394,17 +394,17 @@ STAGE PLANS: alias: nested_tbl_1_n0 filterExpr: (s1.f1 = false) (type: boolean) Pruned Column Paths: s1.f2, s1.f1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f1 = false) (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,17 +441,17 @@ STAGE PLANS: alias: nested_tbl_1_n0 filterExpr: (s1.f3.f4 = 4) (type: boolean) Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f3.f4 = 4) (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -488,17 +488,17 @@ STAGE PLANS: alias: nested_tbl_1_n0 filterExpr: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) Pruned Column Paths: s1.f2, s2.f8 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s2.f8 (type: struct,f11:map>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -538,32 +538,32 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s2.f8.f10 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s3 (type: struct>>) outputColumnNames: s3 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int) outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -571,20 +571,20 @@ STAGE PLANS: Select Operator expressions: _col3.f12 (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -592,29 +592,29 @@ STAGE PLANS: Select Operator expressions: s2.f8.f10 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int) outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -622,20 +622,20 @@ STAGE PLANS: Select Operator expressions: _col3.f12 (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 2 Data size: 2250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: int), _col11 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 4500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -678,14 +678,14 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s2.f8.f10, s1.f3.f4 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (s2.f8.f10[1] pmod s1.f3.f4) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -721,22 +721,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3.f5 (type: double), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -744,10 +744,10 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -783,22 +783,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: struct) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -806,10 +806,10 @@ STAGE PLANS: keys: KEY._col0 (type: struct) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -846,22 +846,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: struct) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -869,7 +869,7 @@ STAGE PLANS: keys: KEY._col0 (type: struct) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -884,16 +884,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: struct) sort order: + - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -935,36 +935,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f3.f4 (type: int) sort order: + Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: ((s2.f8.f9 = false) and s1.f6 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 1126 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((s2.f8.f9 = false) and s1.f6 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 1126 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1126 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f6 (type: int) sort order: + Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 1126 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -974,14 +974,14 @@ STAGE PLANS: 0 _col0.f3.f4 (type: int) 1 _col0.f6 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1031,36 +1031,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f3.f4 (type: int) sort order: + Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: (s2.f8.f9 and s1.f6 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f6 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0.f6 (type: int) sort order: + Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -1070,14 +1070,14 @@ STAGE PLANS: 0 _col0.f3.f4 (type: int) 1 _col0.f6 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1123,42 +1123,42 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int), true (type: boolean) sort order: ++ Map-reduce partition columns: _col1 (type: int), true (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: (s2.f8.f9 and s1.f6 is not null and s2.f8.f9 is not null) (type: boolean) Pruned Column Paths: s1.f6, s2.f8.f9 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (s1.f6 is not null and s2.f8.f9 and s2.f8.f9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1.f6 (type: int), (s2.f8.f9 = true) (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int), _col1 (type: boolean) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: boolean) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -1167,14 +1167,14 @@ STAGE PLANS: 0 _col1 (type: int), true (type: boolean) 1 _col0 (type: int), _col1 (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1218,25 +1218,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s2 (type: struct,f11:map>>) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -1247,14 +1247,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 residual filter predicates: {(_col0.f1 <> _col1.f8.f9)} - Statistics: Num rows: 1 Data size: 2251 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2251 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2251 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1299,37 +1299,37 @@ STAGE PLANS: TableScan alias: t1 filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f6:int>) TableScan alias: t2 filterExpr: s1.f6 is not null (type: boolean) Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: s1.f6 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s2 (type: struct,f11:map>>), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct,f11:map>>) Reduce Operator Tree: Join Operator @@ -1340,14 +1340,14 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col2 residual filter predicates: {(_col0.f1 <> _col2.f8.f9)} - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0.f3.f5 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1237 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1430,22 +1430,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s3.f12, s1.f6 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s3.f12[0].f14 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1453,14 +1453,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1506,22 +1506,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s4['key1'].f15 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1529,14 +1529,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1582,22 +1582,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s5.f16, s1.f6 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s5.f16[0].f18.f19 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1605,14 +1605,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1658,22 +1658,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f6, s5.f16 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s5 (type: struct>>>) outputColumnNames: s1, s5 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(s1.f6) keys: s5.f16.f18.f19 (type: array) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: array) sort order: + Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1681,14 +1681,14 @@ STAGE PLANS: keys: KEY._col0 (type: array) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1734,22 +1734,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s6['key1'].f20[0].f21.f22 (type: int), s1.f6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1757,14 +1757,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1810,22 +1810,22 @@ STAGE PLANS: TableScan alias: nested_tbl_1_n0 Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s1 (type: struct,f6:int>), s6 (type: map>>>>) outputColumnNames: s1, s6 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(s1.f6) keys: s6['key1'].f20.f21.f22 (type: array) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: array) sort order: + Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -1833,14 +1833,14 @@ STAGE PLANS: keys: KEY._col0 (type: array) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_ppd_str_conversion.q.out b/ql/src/test/results/clientpositive/orc_ppd_str_conversion.q.out index a057a27bf8..5d2a2d6e1d 100644 --- a/ql/src/test/results/clientpositive/orc_ppd_str_conversion.q.out +++ b/ql/src/test/results/clientpositive/orc_ppd_str_conversion.q.out @@ -49,17 +49,17 @@ STAGE PLANS: TableScan alias: text_test filterExpr: (col2 = '1 ') (type: boolean) - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (col2 = '1 ') (type: boolean) - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col1 (type: varchar(15)), '1 ' (type: char(10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/orc_struct_type_vectorization.q.out b/ql/src/test/results/clientpositive/orc_struct_type_vectorization.q.out index 7691b5f6c3..c47e90a9f0 100644 --- a/ql/src/test/results/clientpositive/orc_struct_type_vectorization.q.out +++ b/ql/src/test/results/clientpositive/orc_struct_type_vectorization.q.out @@ -90,7 +90,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_struct_type - Statistics: Num rows: 1023 Data size: 196416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 459256 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -101,19 +101,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 4, 5, 2, 6, 7] selectExpressions: VectorUDFStructField(col 1:struct, col 0:int) -> 4:int, VectorUDFStructField(col 1:struct, col 1:int) -> 5:string, VectorUDFStructField(col 2:struct, col 0:int) -> 6:int, VectorUDFStructField(col 2:struct, col 1:int) -> 7:string - Statistics: Num rows: 1023 Data size: 196416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 459256 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4480 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4480 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -209,7 +209,7 @@ STAGE PLANS: alias: orc_struct_type filterExpr: (st1.f1 > 500) (type: boolean) Pruned Column Paths: st1.f1 - Statistics: Num rows: 1023 Data size: 196416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 229628 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -218,7 +218,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 4:int, val 500)(children: VectorUDFStructField(col 1:struct, col 0:int) -> 4:int) predicate: (st1.f1 > 500) (type: boolean) - Statistics: Num rows: 341 Data size: 65472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: st1.f1 (type: int) outputColumnNames: _col0 @@ -227,7 +227,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4] selectExpressions: VectorUDFStructField(col 1:struct, col 0:int) -> 4:int - Statistics: Num rows: 341 Data size: 65472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) Group By Vectorization: @@ -241,7 +241,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 341 Data size: 65472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -251,7 +251,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 341 Data size: 65472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -274,17 +274,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 32640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 38158 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 32640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 38158 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2240 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2240 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/order.q.out b/ql/src/test/results/clientpositive/order.q.out index aa0535f97d..266234ce53 100644 --- a/ql/src/test/results/clientpositive/order.q.out +++ b/ql/src/test/results/clientpositive/order.q.out @@ -14,15 +14,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -30,13 +30,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -82,15 +82,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: - - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -98,13 +98,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/order3.q.out b/ql/src/test/results/clientpositive/order3.q.out index bc4c6eb7bf..70f0aaa04a 100644 --- a/ql/src/test/results/clientpositive/order3.q.out +++ b/ql/src/test/results/clientpositive/order3.q.out @@ -38,21 +38,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -60,11 +60,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -79,20 +79,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col1 (type: int) sort order: + - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -130,22 +130,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value1 (type: int) outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(value1) keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int) Execution mode: vectorized @@ -155,11 +155,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -174,7 +174,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col2 (type: int) sort order: + - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int) Execution mode: vectorized @@ -182,13 +182,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -226,22 +226,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value1 (type: int) outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value1) keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -251,11 +251,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -270,7 +270,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col2 (type: int) sort order: + - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -278,13 +278,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), 'AAA' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -322,21 +322,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: @@ -344,7 +344,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -359,20 +359,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -410,22 +410,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value1 (type: int) outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(value1) keys: key (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int) Execution mode: vectorized @@ -435,7 +435,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -450,7 +450,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int) Execution mode: vectorized @@ -458,13 +458,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -502,22 +502,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value1 (type: int) outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value1) keys: key (type: int), 'AAA' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), 'AAA' (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), 'AAA' (type: string) - Statistics: Num rows: 15 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: bigint) Execution mode: vectorized @@ -527,11 +527,11 @@ STAGE PLANS: keys: KEY._col0 (type: int), 'AAA' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -546,7 +546,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -554,13 +554,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), 'AAA' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 7 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/order_by_expr_1.q.out b/ql/src/test/results/clientpositive/order_by_expr_1.q.out index 28602a510a..6b888ea92f 100644 --- a/ql/src/test/results/clientpositive/order_by_expr_1.q.out +++ b/ql/src/test/results/clientpositive/order_by_expr_1.q.out @@ -313,25 +313,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n5 - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: b (type: int), (0 - b) (type: int), (a + 1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int) sort order: ++ - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -476,25 +476,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n5 - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int), (2 * b) (type: int), (a + 1) (type: int), (0 - b) (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5 - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col4 (type: int), _col5 (type: int) sort order: +++ - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.out index 5fcba1362d..d130735a29 100644 --- a/ql/src/test/results/clientpositive/outer_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/outer_join_ppr.q.out @@ -34,44 +34,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -237,13 +237,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -341,44 +341,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -544,13 +544,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/outer_reference_windowed.q.out b/ql/src/test/results/clientpositive/outer_reference_windowed.q.out index ece73a1f50..83f59cd33c 100644 --- a/ql/src/test/results/clientpositive/outer_reference_windowed.q.out +++ b/ql/src/test/results/clientpositive/outer_reference_windowed.q.out @@ -170,19 +170,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: e011_01 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)) outputColumnNames: c1 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(c1) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: @@ -190,7 +190,7 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -206,14 +206,14 @@ STAGE PLANS: key expressions: 0 (type: int) sort order: + Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: decimal(25,2)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -233,14 +233,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: decimal(35,2)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -282,22 +282,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: e011_01 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) outputColumnNames: c1, c2 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(c1) keys: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: @@ -306,7 +306,7 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -322,14 +322,14 @@ STAGE PLANS: key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) sort order: ++ Map-reduce partition columns: _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -349,14 +349,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: decimal(35,2)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -411,36 +411,36 @@ STAGE PLANS: TableScan alias: e011_01 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(15,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(15,2)) TableScan alias: e011_03 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(15,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -449,13 +449,13 @@ STAGE PLANS: 0 _col0 (type: decimal(15,2)) 1 _col0 (type: decimal(15,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) keys: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -471,7 +471,7 @@ STAGE PLANS: key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: @@ -480,7 +480,7 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -496,14 +496,14 @@ STAGE PLANS: key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) sort order: ++ Map-reduce partition columns: _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -523,14 +523,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: decimal(35,2)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -589,35 +589,35 @@ STAGE PLANS: TableScan alias: e011_01 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(15,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: e011_03 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(15,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(15,2)) Reduce Operator Tree: Join Operator @@ -627,13 +627,13 @@ STAGE PLANS: 0 _col0 (type: decimal(15,2)) 1 _col0 (type: decimal(15,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) keys: _col1 (type: decimal(15,2)), _col2 (type: decimal(15,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -649,7 +649,7 @@ STAGE PLANS: key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: @@ -658,7 +658,7 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -674,14 +674,14 @@ STAGE PLANS: key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) sort order: ++ Map-reduce partition columns: _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(25,2)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -701,14 +701,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: decimal(35,2)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -766,36 +766,36 @@ STAGE PLANS: TableScan alias: e011_01 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(15,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(15,2)) TableScan alias: e011_03 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(15,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(15,2)) Reduce Operator Tree: Join Operator @@ -805,13 +805,13 @@ STAGE PLANS: 0 _col0 (type: decimal(15,2)) 1 _col0 (type: decimal(15,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: corr(_col0, _col2) keys: _col1 (type: decimal(15,2)), _col3 (type: decimal(15,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -827,7 +827,7 @@ STAGE PLANS: key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -836,7 +836,7 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -856,14 +856,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parallel.q.out b/ql/src/test/results/clientpositive/parallel.q.out index 24345e4556..2c7658dbdc 100644 --- a/ql/src/test/results/clientpositive/parallel.q.out +++ b/ql/src/test/results/clientpositive/parallel.q.out @@ -40,28 +40,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -77,19 +77,19 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -98,12 +98,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -114,10 +114,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -126,12 +126,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -163,7 +163,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -171,10 +171,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -204,7 +204,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -212,10 +212,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parallel_colstats.q.out b/ql/src/test/results/clientpositive/parallel_colstats.q.out index 35beff3694..9bd1bf4ff4 100644 --- a/ql/src/test/results/clientpositive/parallel_colstats.q.out +++ b/ql/src/test/results/clientpositive/parallel_colstats.q.out @@ -40,28 +40,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -77,19 +77,19 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Forward - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -98,12 +98,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -114,10 +114,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -126,12 +126,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -163,7 +163,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -171,10 +171,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -204,7 +204,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -212,10 +212,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parallel_join0.q.out b/ql/src/test/results/clientpositive/parallel_join0.q.out index 44709bf4b4..23591fcc27 100644 --- a/ql/src/test/results/clientpositive/parallel_join0.q.out +++ b/ql/src/test/results/clientpositive/parallel_join0.q.out @@ -27,32 +27,32 @@ STAGE PLANS: TableScan alias: src filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -62,7 +62,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -77,15 +77,15 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -114,7 +114,7 @@ SELECT src1.key as k1, src1.value as v1, (SELECT * FROM src WHERE src.key < 10) src2 SORT BY k1, v1, k2, v2 POSTHOOK: type: QUERY -{"cboInfo":"Plan not optimized by CBO.","STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE","table:":"src","isTempTable:":"false","OperatorId:":"TS_0","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"FIL_13","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_2","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_6"}}}}}}}},{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE","table:":"src","isTempTable:":"false","OperatorId:":"TS_3","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"FIL_14","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_7"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"columnExprMap:":{"_col0":"0:VALUE._col0","_col1":"0:VALUE._col1","_col2":"1:VALUE._col0","_col3":"1:VALUE._col1"},"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"JOIN_8","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"},"OperatorId:":"FS_15"}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"columns:":["_col0","_col1","_col2","_col3"],"OperatorId:":"TS_16","children":{"Reduce Output Operator":{"columnExprMap:":{"KEY.reducesinkkey0":"_col0","KEY.reducesinkkey1":"_col1","KEY.reducesinkkey2":"_col2","KEY.reducesinkkey3":"_col3"},"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","sort order:":"++++","Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"RS_10"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","columnExprMap:":{"_col0":"KEY.reducesinkkey0","_col1":"KEY.reducesinkkey1","_col2":"KEY.reducesinkkey2","_col3":"KEY.reducesinkkey3"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_11","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 27556 Data size: 612872 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_12"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_17"}}}}}} +{"cboInfo":"Plan not optimized by CBO.","STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE","table:":"src","isTempTable:":"false","OperatorId:":"TS_0","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_13","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_2","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_6"}}}}}}}},{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE","table:":"src","isTempTable:":"false","OperatorId:":"TS_3","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_14","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_5","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"sort order:":"","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_7"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"columnExprMap:":{"_col0":"0:VALUE._col0","_col1":"0:VALUE._col1","_col2":"1:VALUE._col0","_col3":"1:VALUE._col1"},"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"JOIN_8","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"},"OperatorId:":"FS_15"}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"columns:":["_col0","_col1","_col2","_col3"],"OperatorId:":"TS_16","children":{"Reduce Output Operator":{"columnExprMap:":{"KEY.reducesinkkey0":"_col0","KEY.reducesinkkey1":"_col1","KEY.reducesinkkey2":"_col2","KEY.reducesinkkey3":"_col3"},"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","sort order:":"++++","Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"RS_10"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","columnExprMap:":{"_col0":"KEY.reducesinkkey0","_col1":"KEY.reducesinkkey1","_col2":"KEY.reducesinkkey2","_col3":"KEY.reducesinkkey3"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_11","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_12"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_17"}}}}}} Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 FROM diff --git a/ql/src/test/results/clientpositive/parallel_join1.q.out b/ql/src/test/results/clientpositive/parallel_join1.q.out index c15411307a..dd1f2646cb 100644 --- a/ql/src/test/results/clientpositive/parallel_join1.q.out +++ b/ql/src/test/results/clientpositive/parallel_join1.q.out @@ -27,35 +27,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -65,14 +65,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -81,12 +81,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -118,7 +118,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -126,10 +126,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parallel_orderby.q.out b/ql/src/test/results/clientpositive/parallel_orderby.q.out index d60a0a6e21..7c3523a4aa 100644 --- a/ql/src/test/results/clientpositive/parallel_orderby.q.out +++ b/ql/src/test/results/clientpositive/parallel_orderby.q.out @@ -40,24 +40,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src5_n2 - Statistics: Num rows: 1 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 5600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_complex_types_vectorization.q.out b/ql/src/test/results/clientpositive/parquet_complex_types_vectorization.q.out index 29e296bb13..4af0de1395 100644 --- a/ql/src/test/results/clientpositive/parquet_complex_types_vectorization.q.out +++ b/ql/src/test/results/clientpositive/parquet_complex_types_vectorization.q.out @@ -102,7 +102,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_complex_types - Statistics: Num rows: 1023 Data size: 5115 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 120652 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -113,19 +113,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 6, 7, 8, 4] selectExpressions: ListIndexColScalar(col 2:array, col 0:int) -> 6:int, ListIndexColScalar(col 2:array, col 1:int) -> 7:int, ListIndexColColumn(col 2:array, col 4:int) -> 8:int - Statistics: Num rows: 1023 Data size: 5115 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 120652 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -185,7 +185,7 @@ STAGE PLANS: TableScan alias: parquet_complex_types filterExpr: (l1[0] > 1000) (type: boolean) - Statistics: Num rows: 1023 Data size: 5115 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 116760 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -194,7 +194,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 6:int, val 1000)(children: ListIndexColScalar(col 2:array, col 0:int) -> 6:int) predicate: (l1[0] > 1000) (type: boolean) - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l1[1] (type: int), l1[0] (type: int) outputColumnNames: _col0, _col1 @@ -203,7 +203,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 7] selectExpressions: ListIndexColScalar(col 2:array, col 1:int) -> 6:int, ListIndexColScalar(col 2:array, col 0:int) -> 7:int - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) Group By Vectorization: @@ -217,7 +217,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -227,7 +227,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -250,11 +250,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19402 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19402 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -276,7 +276,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19402 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: bigint) Execution mode: vectorized @@ -297,13 +297,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19402 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1140 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1140 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -375,7 +375,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_complex_types - Statistics: Num rows: 1024 Data size: 5120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 120776 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -386,19 +386,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 6, 7, 8, 4] selectExpressions: ListIndexColScalar(col 2:array, col 0:int) -> 6:int, ListIndexColScalar(col 2:array, col 1:int) -> 7:int, ListIndexColColumn(col 2:array, col 4:int) -> 8:int - Statistics: Num rows: 1024 Data size: 5120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 120776 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -458,7 +458,7 @@ STAGE PLANS: TableScan alias: parquet_complex_types filterExpr: (l1[0] > 1000) (type: boolean) - Statistics: Num rows: 1024 Data size: 5120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 116880 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -467,7 +467,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 6:int, val 1000)(children: ListIndexColScalar(col 2:array, col 0:int) -> 6:int) predicate: (l1[0] > 1000) (type: boolean) - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l1[1] (type: int), l1[0] (type: int) outputColumnNames: _col0, _col1 @@ -476,7 +476,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 7] selectExpressions: ListIndexColScalar(col 2:array, col 1:int) -> 6:int, ListIndexColScalar(col 2:array, col 0:int) -> 7:int - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) Group By Vectorization: @@ -490,7 +490,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -500,7 +500,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -523,11 +523,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19403 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19403 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -549,7 +549,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19403 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: bigint) Execution mode: vectorized @@ -570,13 +570,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19403 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1140 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1140 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -648,7 +648,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_complex_types - Statistics: Num rows: 1025 Data size: 5125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1025 Data size: 120900 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -659,19 +659,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 6, 7, 8, 4] selectExpressions: ListIndexColScalar(col 2:array, col 0:int) -> 6:int, ListIndexColScalar(col 2:array, col 1:int) -> 7:int, ListIndexColColumn(col 2:array, col 4:int) -> 8:int - Statistics: Num rows: 1025 Data size: 5125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1025 Data size: 120900 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1170 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -731,7 +731,7 @@ STAGE PLANS: TableScan alias: parquet_complex_types filterExpr: (l1[0] > 1000) (type: boolean) - Statistics: Num rows: 1025 Data size: 5125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1025 Data size: 117000 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -740,7 +740,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 6:int, val 1000)(children: ListIndexColScalar(col 2:array, col 0:int) -> 6:int) predicate: (l1[0] > 1000) (type: boolean) - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l1[1] (type: int), l1[0] (type: int) outputColumnNames: _col0, _col1 @@ -749,7 +749,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 7] selectExpressions: ListIndexColScalar(col 2:array, col 1:int) -> 6:int, ListIndexColScalar(col 2:array, col 0:int) -> 7:int - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1) Group By Vectorization: @@ -763,7 +763,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -773,7 +773,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -796,11 +796,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -822,7 +822,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19404 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: bigint) Execution mode: vectorized @@ -843,13 +843,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 19404 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1140 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1140 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_join.q.out b/ql/src/test/results/clientpositive/parquet_join.q.out index f674411928..5b8ff832fb 100644 --- a/ql/src/test/results/clientpositive/parquet_join.q.out +++ b/ql/src/test/results/clientpositive/parquet_join.q.out @@ -76,35 +76,35 @@ STAGE PLANS: TableScan alias: p1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE TableScan alias: p2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), myvalue (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -114,14 +114,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -166,14 +166,14 @@ STAGE PLANS: TableScan alias: p1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -185,14 +185,14 @@ STAGE PLANS: TableScan alias: p2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), myvalue (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -200,14 +200,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -285,14 +285,14 @@ STAGE PLANS: TableScan alias: p2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/parquet_map_type_vectorization.q.out b/ql/src/test/results/clientpositive/parquet_map_type_vectorization.q.out index b4c75d4751..0ebfd65ddf 100644 --- a/ql/src/test/results/clientpositive/parquet_map_type_vectorization.q.out +++ b/ql/src/test/results/clientpositive/parquet_map_type_vectorization.q.out @@ -114,7 +114,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_map_type - Statistics: Num rows: 1023 Data size: 7161 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 2183412 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -125,19 +125,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 2, 3, 8, 9, 10, 11, 12, 13] selectExpressions: VectorUDFMapIndexStringScalar(col 1:map, key: k2) -> 8:string, VectorUDFMapIndexLongScalar(col 2:map, key: 456) -> 9:int, VectorUDFMapIndexDecimalScalar(col 3:map, key: 123.123) -> 10:double, VectorUDFMapIndexStringCol(col 1:map, key: col 4:string) -> 11:string, VectorUDFMapIndexLongCol(col 2:map, key: col 5:int) -> 12:int, VectorUDFMapIndexDoubleCol(col 3:map, key: col 6:double) -> 13:double - Statistics: Num rows: 1023 Data size: 7161 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 2183412 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 21340 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 21340 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -201,7 +201,7 @@ STAGE PLANS: TableScan alias: parquet_map_type filterExpr: (stringmap['k1'] like 'v100%') (type: boolean) - Statistics: Num rows: 1023 Data size: 7161 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 1992704 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -210,7 +210,7 @@ STAGE PLANS: native: true predicateExpression: FilterStringColLikeStringScalar(col 8:string, pattern v100%)(children: VectorUDFMapIndexStringScalar(col 1:map, key: k1) -> 8:string) predicate: (stringmap['k1'] like 'v100%') (type: boolean) - Statistics: Num rows: 511 Data size: 3577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 995378 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: stringmap['k1'] (type: string), intmap[123] (type: int), doublemap[123.123] (type: double) outputColumnNames: _col0, _col1, _col2 @@ -219,7 +219,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 9, 10] selectExpressions: VectorUDFMapIndexStringScalar(col 1:map, key: k1) -> 8:string, VectorUDFMapIndexLongScalar(col 2:map, key: 123) -> 9:int, VectorUDFMapIndexDecimalScalar(col 3:map, key: 123.123) -> 10:double - Statistics: Num rows: 511 Data size: 3577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 995378 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), sum(_col2) Group By Vectorization: @@ -233,7 +233,7 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 511 Data size: 3577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 995378 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -243,7 +243,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 511 Data size: 3577 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 995378 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: double) Execution mode: vectorized @@ -266,11 +266,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 255 Data size: 1785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 255 Data size: 496715 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col2 (type: double), _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 255 Data size: 1785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 255 Data size: 496715 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -292,7 +292,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 255 Data size: 1785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 255 Data size: 496715 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: bigint), _col1 (type: double) Execution mode: vectorized @@ -313,13 +313,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), VALUE._col1 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 255 Data size: 1785 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 255 Data size: 496715 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 19470 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 19470 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_no_row_serde.q.out b/ql/src/test/results/clientpositive/parquet_no_row_serde.q.out index 02d7586838..bd9a21b830 100644 --- a/ql/src/test/results/clientpositive/parquet_no_row_serde.q.out +++ b/ql/src/test/results/clientpositive/parquet_no_row_serde.q.out @@ -64,7 +64,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_rc - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -75,7 +75,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 2] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(10,0), decimalPlaces -1) -> 2:decimal(11,0) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + @@ -84,7 +84,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(11,0)) Execution mode: vectorized Map Vectorization: @@ -104,10 +104,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -139,15 +139,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_parquet - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: decimal(10,0)), round(val, -1) (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(11,0)) Map Vectorization: enabled: false @@ -161,10 +161,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_struct_type_vectorization.q.out b/ql/src/test/results/clientpositive/parquet_struct_type_vectorization.q.out index e516895a9d..1503d5c637 100644 --- a/ql/src/test/results/clientpositive/parquet_struct_type_vectorization.q.out +++ b/ql/src/test/results/clientpositive/parquet_struct_type_vectorization.q.out @@ -90,7 +90,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_struct_type - Statistics: Num rows: 1023 Data size: 3069 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 459256 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -101,19 +101,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 4, 5, 2, 6, 7] selectExpressions: VectorUDFStructField(col 1:struct, col 0:int) -> 4:int, VectorUDFStructField(col 1:struct, col 1:int) -> 5:string, VectorUDFStructField(col 2:struct, col 0:int) -> 6:int, VectorUDFStructField(col 2:struct, col 1:int) -> 7:string - Statistics: Num rows: 1023 Data size: 3069 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 459256 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4480 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4480 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -209,7 +209,7 @@ STAGE PLANS: alias: parquet_struct_type filterExpr: (st1.f1 > 500) (type: boolean) Pruned Column Paths: st1.f1 - Statistics: Num rows: 1023 Data size: 3069 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023 Data size: 229628 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -218,7 +218,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 4:int, val 500)(children: VectorUDFStructField(col 1:struct, col 0:int) -> 4:int) predicate: (st1.f1 > 500) (type: boolean) - Statistics: Num rows: 341 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: st1.f1 (type: int) outputColumnNames: _col0 @@ -227,7 +227,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4] selectExpressions: VectorUDFStructField(col 1:struct, col 0:int) -> 4:int - Statistics: Num rows: 341 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) Group By Vectorization: @@ -241,7 +241,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 341 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -251,7 +251,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 341 Data size: 1023 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -274,17 +274,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 38158 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 170 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 38158 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2240 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2240 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q.out b/ql/src/test/results/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q.out index e6820ab184..21973f6cc6 100644 --- a/ql/src/test/results/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q.out +++ b/ql/src/test/results/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q.out @@ -463,22 +463,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 59488 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 59488 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), min(_col2), count(_col3), sum(_col4), count(_col4), sum(_col6), sum(_col5), count(_col5) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 59488 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 59488 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: double), _col8 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -487,11 +487,11 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 29744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: tinyint), _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), round((_col4 / _col5), 5) (type: double), round(power(((_col6 - ((_col7 * _col7) / _col8)) / _col8), 0.5), 5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 29744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -506,17 +506,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 29744 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: double), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: int), VALUE._col1 (type: smallint), VALUE._col2 (type: bigint), VALUE._col3 (type: double), VALUE._col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 29744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 29744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -823,22 +823,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 1144 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: cfloat - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 1144 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cfloat (type: float) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 1144 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float) sort order: + Map-reduce partition columns: _col0 (type: float) - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 1144 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -847,7 +847,7 @@ STAGE PLANS: keys: KEY._col0 (type: float) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 572 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -862,17 +862,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: float) sort order: + - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 572 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: float), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 572 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 572 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1207,22 +1207,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 25454 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cchar (type: char(5)) outputColumnNames: cchar - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 25454 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cchar (type: char(5)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 25454 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: char(5)) sort order: + Map-reduce partition columns: _col0 (type: char(5)) - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 25454 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1231,7 +1231,7 @@ STAGE PLANS: keys: KEY._col0 (type: char(5)) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 12727 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1246,17 +1246,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: char(5)) sort order: + - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 12727 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: char(5)), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 12727 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 12727 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1591,22 +1591,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 26884 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cvarchar (type: varchar(10)) outputColumnNames: cvarchar - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 26884 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cvarchar (type: varchar(10)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 26884 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: varchar(10)) sort order: + Map-reduce partition columns: _col0 (type: varchar(10)) - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 26884 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1615,7 +1615,7 @@ STAGE PLANS: keys: KEY._col0 (type: varchar(10)) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 13442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1630,17 +1630,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: varchar(10)) sort order: + - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 13442 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 13442 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 13442 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1975,22 +1975,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 52624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) outputColumnNames: cstring1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 52624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 52624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 52624 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1999,7 +1999,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -2014,17 +2014,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 26312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2358,22 +2358,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 41184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbinary (type: binary) outputColumnNames: cbinary - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 41184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cbinary (type: binary) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 41184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: binary) sort order: + Map-reduce partition columns: _col0 (type: binary) - Statistics: Num rows: 300 Data size: 4200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 41184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -2382,14 +2382,14 @@ STAGE PLANS: keys: KEY._col0 (type: binary) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 20592 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hex(_col0) (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 20592 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 150 Data size: 2100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 150 Data size: 20592 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_types_vectorization.q.out b/ql/src/test/results/clientpositive/parquet_types_vectorization.q.out index 58de65c50a..7b27fcef99 100644 --- a/ql/src/test/results/clientpositive/parquet_types_vectorization.q.out +++ b/ql/src/test/results/clientpositive/parquet_types_vectorization.q.out @@ -183,22 +183,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n0 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4576 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4576 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(_col1), min(_col2), count(_col3), sum(_col4), count(_col4), sum(_col6), sum(_col5), count(_col5) keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4576 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4576 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: double), _col8 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -207,11 +207,11 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2288 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: tinyint), _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), round((_col4 / _col5), 5) (type: double), round(power(((_col6 - ((_col7 * _col7) / _col8)) / _col8), 0.5), 5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2288 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -226,17 +226,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2288 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: double), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: int), VALUE._col1 (type: smallint), VALUE._col2 (type: bigint), VALUE._col3 (type: double), VALUE._col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2288 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2288 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -290,22 +290,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n0 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) outputColumnNames: cfloat - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cfloat (type: float) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: float) sort order: + Map-reduce partition columns: _col0 (type: float) - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -314,7 +314,7 @@ STAGE PLANS: keys: KEY._col0 (type: float) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -329,17 +329,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: float) sort order: + - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: float), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -379,22 +379,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n0 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cchar (type: char(5)) outputColumnNames: cchar - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cchar (type: char(5)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: char(5)) sort order: + Map-reduce partition columns: _col0 (type: char(5)) - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 1958 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -403,7 +403,7 @@ STAGE PLANS: keys: KEY._col0 (type: char(5)) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -418,17 +418,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: char(5)) sort order: + - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: char(5)), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 979 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -481,22 +481,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n0 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2068 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cvarchar (type: varchar(10)) outputColumnNames: cvarchar - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2068 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cvarchar (type: varchar(10)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2068 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: varchar(10)) sort order: + Map-reduce partition columns: _col0 (type: varchar(10)) - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 2068 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -505,7 +505,7 @@ STAGE PLANS: keys: KEY._col0 (type: varchar(10)) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1034 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -520,17 +520,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: varchar(10)) sort order: + - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1034 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1034 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1034 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -579,22 +579,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n0 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4048 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) outputColumnNames: cstring1 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4048 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4048 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4048 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -603,7 +603,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -618,17 +618,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -684,22 +684,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n0 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: timestamp) outputColumnNames: t - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 880 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: t (type: timestamp) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 880 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp) sort order: + Map-reduce partition columns: _col0 (type: timestamp) - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 880 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -708,7 +708,7 @@ STAGE PLANS: keys: KEY._col0 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 440 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -723,17 +723,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: timestamp) sort order: + - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 440 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 440 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 440 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -789,22 +789,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n0 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbinary (type: binary) outputColumnNames: cbinary - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3168 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cbinary (type: binary) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: binary) sort order: + Map-reduce partition columns: _col0 (type: binary) - Statistics: Num rows: 22 Data size: 308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 3168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -813,14 +813,14 @@ STAGE PLANS: keys: KEY._col0 (type: binary) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hex(_col0) (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 154 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1584 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_0.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_0.q.out index 6af7892d9c..4aa26e0ed1 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_0.q.out @@ -29,7 +29,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -40,7 +40,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(ctinyint), max(ctinyint), count(ctinyint), count() Group By Vectorization: @@ -52,7 +52,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -60,7 +60,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: tinyint), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -87,7 +87,7 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -110,7 +110,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -136,10 +136,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: tinyint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -195,7 +195,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -206,7 +206,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ctinyint) Group By Vectorization: @@ -218,7 +218,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -226,7 +226,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -253,7 +253,7 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -276,7 +276,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -301,10 +301,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -370,19 +370,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) Execution mode: vectorized Map Vectorization: @@ -403,11 +403,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col3, _col4, _col7 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -422,7 +422,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col3 (type: double), _col4 (type: double), _col7 (type: double) Execution mode: vectorized Map Vectorization: @@ -442,10 +442,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col2 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -517,7 +517,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -528,7 +528,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(cbigint), max(cbigint), count(cbigint), count() Group By Vectorization: @@ -540,7 +540,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -548,7 +548,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -575,7 +575,7 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -598,7 +598,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -624,10 +624,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -683,7 +683,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -694,7 +694,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(cbigint) Group By Vectorization: @@ -706,7 +706,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -714,7 +714,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -741,7 +741,7 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -764,7 +764,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -789,10 +789,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -858,19 +858,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) Execution mode: vectorized Map Vectorization: @@ -891,11 +891,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col3, _col4, _col7 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -910,7 +910,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col3 (type: double), _col4 (type: double), _col7 (type: double) Execution mode: vectorized Map Vectorization: @@ -930,10 +930,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col2 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1005,7 +1005,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -1016,7 +1016,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [4] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(cfloat), max(cfloat), count(cfloat), count() Group By Vectorization: @@ -1028,7 +1028,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -1036,7 +1036,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1063,7 +1063,7 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1086,7 +1086,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1112,10 +1112,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), VALUE._col0 (type: float), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1171,7 +1171,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -1182,7 +1182,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [4] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(cfloat) Group By Vectorization: @@ -1194,7 +1194,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -1202,7 +1202,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Execution mode: vectorized Map Vectorization: @@ -1229,7 +1229,7 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1252,7 +1252,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -1277,10 +1277,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1346,19 +1346,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) Execution mode: vectorized Map Vectorization: @@ -1379,11 +1379,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col3, _col4, _col7 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1398,7 +1398,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col3 (type: double), _col4 (type: double), _col7 (type: double) Execution mode: vectorized Map Vectorization: @@ -1418,10 +1418,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type: double), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col2 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1532,7 +1532,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 like '%b%') or (CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or ((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (UDFToInteger(ctinyint) = 3569))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -1542,7 +1542,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterDecimalColNotEqualDecimalScalar(col 13:decimal(13,3), val 79.553)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3)), FilterDoubleColLessDoubleColumn(col 14:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterLongColEqualLongScalar(col 11:boolean, val 1), FilterLongColEqualLongScalar(col 0:int, val 3569)(children: col 0:tinyint))) predicate: (((UDFToShort(ctinyint) >= csmallint) and (cboolean2 = 1) and (UDFToInteger(ctinyint) = 3569)) or (CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4 @@ -1551,7 +1551,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4, 0, 14, 17] selectExpressions: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 3:bigint) -> 15:double, CastLongToDouble(col 3:bigint) -> 16:double) -> 17:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1210980 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col4), sum(_col3), count(), sum(_col1), min(_col2) Group By Vectorization: @@ -1563,7 +1563,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -1571,7 +1571,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -1598,14 +1598,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), min(VALUE._col6) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double), (- (UDFToDouble(_col0) / _col1)) (type: double), (-6432.0D + (UDFToDouble(_col0) / _col1)) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) + (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), (-6432.0D + (- (-6432.0D + (UDFToDouble(_col0) / _col1)))) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) / (- (-6432.0D + (UDFToDouble(_col0) / _col1)))) (type: double), _col4 (type: bigint), _col5 (type: double), (((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) % power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5)) (type: double), (- ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END)) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) * (- (UDFToDouble(_col0) / _col1))) (type: double), _col6 (type: tinyint), (- _col6) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1699,23 +1699,23 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%') or ((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0)) or (cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%')) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -1779,13 +1779,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30508,22 +30508,22 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((cint = 45) and (cfloat = 3.02)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 49) and (cfloat = 3.5))) (type: boolean) - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30622,22 +30622,22 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean) - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30738,22 +30738,22 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((cint = 45) or (cfloat = 3.02)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 49) or (cfloat = 3.5))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -30851,24 +30851,24 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (cstring1) IN ('biology', 'history', 'topology') (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (cstring1) IN ('biology', 'history', 'topology') (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 614 Data size: 43146 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: cstring1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 23550 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 23550 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -30933,11 +30933,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 23550 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 23550 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -30966,7 +30966,7 @@ STAGE PLANS: key expressions: _col1 (type: string) null sort order: a sort order: + - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 23550 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -31003,13 +31003,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 23550 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 23550 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_1.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_1.q.out index b72982c1f8..45cdc4c059 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_1.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_1.q.out @@ -55,7 +55,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (cbigint < UDFToLong(ctinyint)) or (UDFToLong(cint) > cbigint) or (cboolean1 < 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -65,7 +65,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0)), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterLongColLessLongScalar(col 10:boolean, val 0)) predicate: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (UDFToLong(cint) > cbigint) or (cbigint < UDFToLong(ctinyint)) or (cboolean1 < 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -74,7 +74,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 4, 2, 5, 13, 16, 14] selectExpressions: CastLongToDouble(col 0:tinyint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 14:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2) Group By Vectorization: @@ -86,7 +86,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -94,7 +94,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: tinyint), _col5 (type: int), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -121,14 +121,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), max(VALUE._col4), max(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), count(VALUE._col9) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((_col0 - ((_col1 * _col1) / _col2)) / _col2) (type: double), (((_col0 - ((_col1 * _col1) / _col2)) / _col2) / -26.28D) (type: double), _col3 (type: double), (-1.389D + _col3) (type: double), (_col3 * (-1.389D + _col3)) (type: double), _col4 (type: tinyint), (- (_col3 * (-1.389D + _col3))) (type: double), _col5 (type: int), (CAST( _col5 AS decimal(10,0)) * 79.553) (type: decimal(16,3)), ((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END) (type: double), (10.175D % (- (_col3 * (-1.389D + _col3)))) (type: double), _col9 (type: bigint), (-563 % _col5) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out index d174a0070d..d6bcc2d3d7 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_10.q.out @@ -61,7 +61,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -71,7 +71,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a)))) predicate: (((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a'))) or (cstring2 <= '10')) (type: boolean) - Statistics: Num rows: 9557 Data size: 114684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 1937820 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -80,13 +80,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 8, 0, 10, 6, 13, 17, 16, 18, 20, 21, 19, 23, 24, 26] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 17:double, DoubleColModuloDoubleScalar(col 18:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 18:double) -> 16:double, DoubleColUnaryMinus(col 5:double) -> 18:double, DoubleColModuloDoubleColumn(col 19:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 21:smallint, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColMultiplyLongColumn(col 3:bigint, col 22:bigint)(children: LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 22:smallint) -> 23:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 25:double)(children: DoubleColAddDoubleColumn(col 5:double, col 24:double)(children: CastLongToDouble(col 1:smallint) -> 24:double) -> 25:double) -> 24:double, DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 5:double) -> 25:double) -> 26:double - Statistics: Num rows: 9557 Data size: 114684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9557 Data size: 114684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_11.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_11.q.out index 5048ad7560..2f07528f6b 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_11.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_11.q.out @@ -43,7 +43,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2381474 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -53,7 +53,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7:string, col 6:string), FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterStringColLikeStringScalar(col 6:string, pattern %a))) predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1190792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639D) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0D) (type: double), (cdouble * -5638.15D) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -62,13 +62,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 10, 5, 8, 13, 14, 15, 17, 16] selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1:int)(children: col 1:smallint) -> 13:int, DoubleColSubtractDoubleScalar(col 5:double, val 9763215.5639) -> 14:double, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleScalar(col 16:double, val 6981.0)(children: DoubleColUnaryMinus(col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleScalar(col 5:double, val -5638.15) -> 16:double - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 953272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 953272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_12.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_12.q.out index 83ca333522..ac165e816d 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_12.q.out @@ -78,7 +78,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (ctimestamp1 is null and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1647554 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -88,7 +88,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10:boolean, col 11:boolean), FilterLongColNotEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint)), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %a), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11:boolean, val 1), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 1:bigint)(children: col 1:smallint)))) predicate: (((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ctimestamp1 is null) (type: boolean) - Statistics: Num rows: 3754 Data size: 45048 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 166 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cboolean1 (type: boolean), cstring1 (type: string), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -97,7 +97,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 10, 6, 5, 13, 16, 14] selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double - Statistics: Num rows: 3754 Data size: 45048 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 166 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), sum(_col5), sum(_col4), sum(_col3), count(_col3), sum(_col0), sum(_col6) Group By Vectorization: @@ -111,7 +111,7 @@ STAGE PLANS: keys: _col3 (type: double), _col0 (type: bigint), _col2 (type: string), _col1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 3754 Data size: 45048 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) sort order: ++++ @@ -121,7 +121,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3754 Data size: 45048 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double) Execution mode: vectorized Map Vectorization: @@ -149,11 +149,11 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1877 Data size: 22524 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0D * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) (type: double), ((-6432.0D * _col0) / -6432.0D) (type: double), (- ((-6432.0D * _col0) / -6432.0D)) (type: double), (_col7 / _col8) (type: double), (- (-6432.0D * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col9 (type: bigint), ((_col7 / _col8) / (-6432.0D * _col0)) (type: double), (- (- ((-6432.0D * _col0) / -6432.0D))) (type: double), (((-6432.0D * _col0) / -6432.0D) + (- (-6432.0D * _col0))) (type: double), power(((_col10 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 1877 Data size: 22524 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -176,7 +176,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1877 Data size: 22524 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) Execution mode: vectorized Map Vectorization: @@ -202,10 +202,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: string), null (type: timestamp), KEY.reducesinkkey0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(22,2)), VALUE._col11 (type: bigint), VALUE._col12 (type: double), VALUE._col8 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1877 Data size: 22524 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1877 Data size: 22524 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out index 6459e29e81..d81692d8dd 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_13.q.out @@ -80,7 +80,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2028982 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -90,7 +90,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28789.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val -28788.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4)))) predicate: (((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean) - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -99,7 +99,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -113,7 +113,7 @@ STAGE PLANS: keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -123,7 +123,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -151,11 +151,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -178,7 +178,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -204,13 +204,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -412,7 +412,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2028982 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -421,7 +421,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28801.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val -28801.336)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4)))) predicate: (((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean) - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -430,7 +430,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -444,7 +444,7 @@ STAGE PLANS: keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -454,7 +454,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 32760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -476,11 +476,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -502,7 +502,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -522,13 +522,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out index 1eab96280b..6d46c5552a 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_14.q.out @@ -80,7 +80,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2139070 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -90,7 +90,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 13:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp)), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 13:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float))) predicate: (((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and (UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint))) (type: boolean) - Statistics: Num rows: 606 Data size: 7272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -99,7 +99,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 4, 6, 10, 5, 14, 13, 4, 15] selectExpressions: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 15:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 16:double) -> 13:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 15:double - Statistics: Num rows: 606 Data size: 7272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) Group By Vectorization: @@ -113,7 +113,7 @@ STAGE PLANS: keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 606 Data size: 7272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -123,7 +123,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 606 Data size: 7272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -151,11 +151,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 303 Data size: 3636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 26432 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 3636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -178,7 +178,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 303 Data size: 3636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Execution mode: vectorized Map Vectorization: @@ -204,10 +204,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 3636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 3636 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_15.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_15.q.out index 2d306cf6c1..a843eb3afb 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_15.q.out @@ -76,7 +76,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -86,7 +86,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %ss%), FilterStringColLikeStringScalar(col 6:string, pattern 10%), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -75), FilterLongColEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -3728.0))) predicate: (((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D)) or (cstring1 like '10%') or (cstring2 like '%ss%')) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -95,7 +95,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 10, 5, 6, 0, 2, 8, 4, 13, 14, 17, 15, 19] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, CastLongToDouble(col 2:int) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 16:double, CastLongToDouble(col 2:int) -> 18:double) -> 19:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col8), sum(_col7), count(_col0), min(_col2), sum(_col10), sum(_col9), count(_col4), sum(_col12), sum(_col11), count(_col5) Group By Vectorization: @@ -109,7 +109,7 @@ STAGE PLANS: keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1278652 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ @@ -119,7 +119,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1278652 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -146,11 +146,11 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 639332 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), power(((_col7 - ((_col8 * _col8) / _col9)) / CASE WHEN ((_col9 = 1L)) THEN (null) ELSE ((_col9 - 1)) END), 0.5) (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col10 (type: double), (_col2 * 79.553D) (type: double), (33.0 % _col0) (type: float), power(((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END), 0.5) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (-23.0D % _col2) (type: double), (- _col4) (type: tinyint), ((_col14 - ((_col15 * _col15) / _col16)) / CASE WHEN ((_col16 = 1L)) THEN (null) ELSE ((_col16 - 1)) END) (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), power(((_col14 - ((_col15 * _col15) / _col16)) / _col16), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -173,7 +173,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) Execution mode: vectorized Map Vectorization: @@ -198,10 +198,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out index fa317902b4..f0d12cacc8 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_16.q.out @@ -53,7 +53,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2308074 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -63,7 +63,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -72,7 +72,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -86,7 +86,7 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -96,7 +96,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -124,14 +124,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 24576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 24576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 24576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out index 9fa2d72ff8..193259b43b 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_17.q.out @@ -61,7 +61,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cbigint > -23L) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1647550 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -71,7 +71,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3))), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float))) predicate: (((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and (cbigint > -23L)) (type: boolean) - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 549274 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -80,7 +80,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 14, 17, 19, 20, 22, 18] selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 14:double, DoubleColAddDoubleColumn(col 5:double, col 18:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 17:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double) -> 17:double, DoubleColDivideDoubleColumn(col 5:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 20:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 21:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 21:decimal(19,0)) -> 22:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 23:double)(children: DoubleColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 23:double) -> 18:double - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -89,7 +89,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -115,10 +115,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_2.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_2.q.out index a5af87ccdc..d86824c11c 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_2.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_2.q.out @@ -59,7 +59,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15)) or ((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2157324 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -69,7 +69,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8:timestamp, col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern b%), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -5638.14990234375)), FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 13:double, val -10669.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterLongColLessLongScalar(col 2:int, val 359)))) predicate: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean) - Statistics: Num rows: 4778 Data size: 57336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 719232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), cfloat (type: float), cbigint (type: bigint), ctinyint (type: tinyint), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -78,7 +78,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 4, 3, 0, 5, 13, 16] selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double - Statistics: Num rows: 4778 Data size: 57336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 719232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count(), min(_col3), sum(_col4), count(_col4) Group By Vectorization: @@ -90,7 +90,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -98,7 +98,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -125,14 +125,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), count(VALUE._col6), min(VALUE._col7), sum(VALUE._col8), count(VALUE._col9) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double), ((UDFToDouble(_col0) / _col1) % -563.0D) (type: double), ((UDFToDouble(_col0) / _col1) + 762.0D) (type: double), _col2 (type: double), ((_col3 - ((_col4 * _col4) / _col5)) / _col5) (type: double), (- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) (type: double), (_col2 - (UDFToDouble(_col0) / _col1)) (type: double), _col6 (type: bigint), (- (_col2 - (UDFToDouble(_col0) / _col1))) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / _col5) - 762.0D) (type: double), _col7 (type: tinyint), ((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) (type: double), (_col8 / _col9) (type: double), (((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) - _col2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_3.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_3.q.out index ffdb68e62b..1da57f4700 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_3.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_3.q.out @@ -64,7 +64,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D)) or ((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1276620 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -74,7 +74,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float), FilterDecimalColNotEqualDecimalScalar(col 14:decimal(22,3), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterDoubleColEqualDoubleScalar(col 13:double, val -29071.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 13:double), FilterDecimalColGreaterEqualDecimalScalar(col 15:decimal(8,3), val 79.553)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(8,3)), FilterTimestampColGreaterTimestampColumn(col 8:timestamp, col 9:timestamp))) predicate: (((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2)) or ((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D))) (type: boolean) - Statistics: Num rows: 2503 Data size: 30036 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 260060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cint (type: int), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -83,7 +83,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 0, 4, 2, 13, 18, 16, 20, 4, 17, 19, 23] selectExpressions: CastLongToDouble(col 1:smallint) -> 13:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 16:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, CastLongToDouble(col 0:tinyint) -> 16:double, DoubleColMultiplyDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 17:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 17:double, CastLongToDouble(col 2:int) -> 19:double, DoubleColMultiplyDoubleColumn(col 21:double, col 22:double)(children: CastLongToDouble(col 2:int) -> 21:double, CastLongToDouble(col 2:int) -> 22:double) -> 23:double - Statistics: Num rows: 2503 Data size: 30036 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 260060 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col7), sum(_col6), count(_col1), sum(_col9), sum(_col8), count(_col2), sum(_col2), sum(_col3), count(_col3), sum(_col11), sum(_col10) Group By Vectorization: @@ -95,7 +95,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -103,7 +103,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: double), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: double), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -130,14 +130,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), sum(VALUE._col9), sum(VALUE._col10), count(VALUE._col11), sum(VALUE._col12), sum(VALUE._col13) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D) (type: double), power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5)) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) % 79.553D) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) (type: double), power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5) (type: double), (- power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), _col9 (type: double), ((- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) / (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (UDFToDouble(_col10) / _col11) (type: double), (-3728.0D - power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), power(((_col12 - ((_col13 * _col13) / _col11)) / _col11), 0.5) (type: double), ((UDFToDouble(_col10) / _col11) / power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_4.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_4.q.out index 998fdb3576..fe199adf33 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_4.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_4.q.out @@ -59,7 +59,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((UDFToInteger(csmallint) >= cint) or ((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D)) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -69,7 +69,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterDoubleColGreaterDoubleScalar(col 5:double, val 79.553)), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 3:bigint, val -563), FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessEqualDoubleScalar(col 5:double, val -3728.0)))) predicate: (((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D)) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or (UDFToInteger(csmallint) >= cint)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cdouble (type: double), ctinyint (type: tinyint), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -78,7 +78,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 5, 0, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col3), sum(_col1), count(_col1), min(_col2) Group By Vectorization: @@ -90,7 +90,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -98,7 +98,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -125,14 +125,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), min(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), (_col0 * -563L) (type: bigint), (-3728L + _col0) (type: bigint), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (- power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5)) (type: double), (_col2 / _col3) (type: double), ((_col0 * -563L) % _col0) (type: bigint), (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)) (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3))) (type: double), ((-3728L + _col0) - (_col0 * -563L)) (type: bigint), _col4 (type: tinyint), _col4 (type: tinyint), (UDFToDouble(_col4) * (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_5.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_5.q.out index 4e490ad871..8ea12bda22 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_5.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_5.q.out @@ -53,7 +53,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cboolean2 is not null and (cstring1 like '%b%')) or ((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2454862 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -63,7 +63,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 11:boolean), FilterStringColLikeStringScalar(col 6:string, pattern %b%)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), SelectColumnIsNotNull(col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern a))) predicate: (((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a')) or (cboolean2 is not null and (cstring1 like '%b%'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7658 Data size: 1529972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) outputColumnNames: ctinyint, csmallint, cint @@ -71,7 +71,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 9216 Data size: 110592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7658 Data size: 1529972 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint) Group By Vectorization: @@ -83,7 +83,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -91,7 +91,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -118,14 +118,14 @@ STAGE PLANS: aggregations: max(VALUE._col0), count(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), max(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: smallint), (UDFToInteger(_col0) * -75) (type: int), _col1 (type: bigint), (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1)) (type: double), (6981 * UDFToInteger(_col0)) (type: int), _col2 (type: smallint), (- _col2) (type: smallint), (197.0D % (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1))) (type: double), _col3 (type: bigint), _col4 (type: tinyint), (- _col4) (type: tinyint), ((- _col4) + _col4) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_6.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_6.q.out index fa649b2378..8dfbd8ec03 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_6.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_6.q.out @@ -55,7 +55,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((ctinyint <> 0Y) and (((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2110130 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -65,7 +65,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10:boolean, val 0), FilterLongColGreaterEqualLongColumn(col 11:boolean, col 10:boolean)), FilterExprAndExpr(children: SelectColumnIsNotNull(col 3:bigint), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %a), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -257.0))))) predicate: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257)))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 11605 Data size: 139260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5951 Data size: 1022000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28D / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -74,13 +74,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 4, 6, 13, 14, 15, 16, 17, 18, 19, 20, 22] selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1:int)(children: col 1:smallint) -> 13:int, LongColUnaryMinus(col 1:smallint) -> 14:smallint, DoubleColUnaryMinus(col 4:float) -> 15:float, DoubleScalarDivideDoubleColumn(val -26.28, col 4:double)(children: col 4:float) -> 16:double, DoubleColMultiplyDoubleScalar(col 4:float, val 359.0) -> 17:float, LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 18:int, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColSubtractLongScalar(col 0:int, val -75)(children: col 0:tinyint) -> 20:int, LongScalarMultiplyLongColumn(val 762, col 21:int)(children: LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 21:int) -> 22:int - Statistics: Num rows: 11605 Data size: 139260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 11605 Data size: 139260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out index 0630e8b08c..a0e53c6c82 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_7.q.out @@ -67,7 +67,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((ctinyint <> 0Y) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -77,7 +77,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28815.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0)))) predicate: (((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -86,7 +86,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -95,7 +95,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -121,13 +121,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -289,7 +289,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((ctinyint <> 0Y) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -298,7 +298,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28792.315)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0)))) predicate: (((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -307,7 +307,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -316,7 +316,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -336,13 +336,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 65532 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_8.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_8.q.out index b4481bfa40..5fd72c9527 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_8.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_8.q.out @@ -63,7 +63,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 is not null and (UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D)) or (cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2983078 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 10.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 16.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0))) predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 742850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -82,7 +82,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, DoubleColAddDoubleColumn(col 22:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 22:float) -> 23:float) -> 22:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -91,7 +91,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -117,13 +117,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -272,7 +272,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 is not null and (UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D)) or (cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2983078 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -281,7 +281,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 12.503)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 11.998)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0))) predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 742850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -290,7 +290,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, DoubleColAddDoubleColumn(col 22:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 22:float) -> 23:float) -> 22:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -299,7 +299,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -319,13 +319,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out index fa317902b4..f0d12cacc8 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_9.q.out @@ -53,7 +53,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2308074 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -63,7 +63,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -72,7 +72,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -86,7 +86,7 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -96,7 +96,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -124,14 +124,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 24576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 24576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 24576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_decimal_date.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_decimal_date.q.out index 716589339e..5c6ffcf866 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_decimal_date.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_decimal_date.q.out @@ -31,7 +31,7 @@ STAGE PLANS: TableScan alias: date_decimal_test_parquet filterExpr: (cint is not null and cdouble is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2101500 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -40,7 +40,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:double)) predicate: (cdouble is not null and cint is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdate (type: date), cdecimal (type: decimal(20,10)) outputColumnNames: _col0, _col1 @@ -48,19 +48,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3] - Statistics: Num rows: 12288 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out index 1baa650dcb..86e8c046ba 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out @@ -18,7 +18,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -29,19 +29,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13] selectExpressions: DoubleColDivideDoubleScalar(col 5:double, val 0.0) -> 13:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 98304 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -194,7 +194,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cbigint > 0L) and (cbigint < 100000000L)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -203,7 +203,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val 0), FilterLongColLessLongScalar(col 3:bigint, val 100000000)) predicate: ((cbigint < 100000000L) and (cbigint > 0L)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cbigint - 988888) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888))) (type: double), (1.2 / CAST( (cbigint - 988888) AS decimal(19,0))) (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 @@ -212,7 +212,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 18] selectExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 13:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 15:double) -> 16:double, DecimalScalarDivideDecimalColumn(val 1.2, col 17:decimal(19,0))(children: CastLongToDecimal(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 17:decimal(19,0)) -> 18:decimal(22,21) - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ @@ -221,7 +221,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(22,21)) Execution mode: vectorized @@ -242,13 +242,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -393,7 +393,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((cdouble >= -500.0D) and (cdouble < -199.0D)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -402,7 +402,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -500.0), FilterDoubleColLessDoubleScalar(col 5:double, val -199.0)) predicate: ((cdouble < -199.0D) and (cdouble >= -500.0D)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), ((cdouble + 200.0D) / (cdouble + 200.0D)) (type: double), (3.0D / (cdouble + 200.0D)) (type: double), (1.2D / (cdouble + 200.0D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col4, _col5 @@ -411,7 +411,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 16, 17, 15, 18] selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 13:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 17:double, DoubleScalarDivideDoubleColumn(val 3.0, col 14:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double) -> 15:double, DoubleScalarDivideDoubleColumn(val 1.2, col 14:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double) -> 18:double - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: double) sort order: ++ @@ -420,7 +420,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) Execution mode: vectorized @@ -441,13 +441,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out index dc9f66361c..597e28b89c 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out @@ -18,20 +18,20 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -90,7 +90,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -100,7 +100,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 @@ -108,7 +108,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ @@ -117,7 +117,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col2 (type: smallint) Execution mode: vectorized @@ -144,13 +144,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -210,7 +210,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -222,7 +222,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 13] selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 1.0) -> 13:double - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col1) Group By Vectorization: @@ -236,7 +236,7 @@ STAGE PLANS: keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -246,7 +246,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized @@ -275,17 +275,17 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: tinyint), (_col1 / _col2) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -345,7 +345,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -356,7 +356,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -368,7 +368,7 @@ STAGE PLANS: keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -378,7 +378,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -405,13 +405,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -471,22 +471,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: ctinyint, cdouble - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT cdouble) keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 104204 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 104204 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Map Vectorization: enabled: true @@ -504,13 +504,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -600,7 +600,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -610,7 +610,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ctinyint) Group By Vectorization: @@ -624,7 +624,7 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -634,7 +634,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -662,7 +662,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -685,7 +685,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -711,13 +711,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out index 9455b941ed..2f1c63c68a 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out @@ -18,21 +18,21 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 16380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 2 Offset of rows: 3 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -86,7 +86,7 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -95,7 +95,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 @@ -103,7 +103,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ @@ -112,7 +112,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: smallint) Execution mode: vectorized @@ -133,14 +133,14 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Offset of rows: 10 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_part_project.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_part_project.q.out index 0786685a3b..d5be54a82f 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_part_project.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_part_project.q.out @@ -64,15 +64,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesparquet_part_n0 - Statistics: Num rows: 200 Data size: 2400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cdouble + 2.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 200 Data size: 2400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -92,13 +92,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/parquet_vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/parquet_vectorization_pushdown.q.out index 2995721a2c..a05041a3e1 100644 --- a/ql/src/test/results/clientpositive/parquet_vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/parquet_vectorization_pushdown.q.out @@ -18,22 +18,22 @@ STAGE PLANS: TableScan alias: alltypesparquet filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 12288 Data size: 147456 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 4096 Data size: 49152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(cbigint), count(cbigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -54,14 +54,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/partial_column_stats.q.out b/ql/src/test/results/clientpositive/partial_column_stats.q.out index ccddad7310..0c1d69bcb6 100644 --- a/ql/src/test/results/clientpositive/partial_column_stats.q.out +++ b/ql/src/test/results/clientpositive/partial_column_stats.q.out @@ -20,29 +20,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n53 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/partition_boolexpr.q.out b/ql/src/test/results/clientpositive/partition_boolexpr.q.out index ddc94d802a..fc26af818c 100644 --- a/ql/src/test/results/clientpositive/partition_boolexpr.q.out +++ b/ql/src/test/results/clientpositive/partition_boolexpr.q.out @@ -51,20 +51,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -72,10 +72,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -143,20 +143,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -164,10 +164,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -194,12 +194,12 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: INPUT__FILE__NAME is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: INPUT__FILE__NAME is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/partition_condition_remover.q.out b/ql/src/test/results/clientpositive/partition_condition_remover.q.out index f1dc9a051f..43e7bf7292 100644 --- a/ql/src/test/results/clientpositive/partition_condition_remover.q.out +++ b/ql/src/test/results/clientpositive/partition_condition_remover.q.out @@ -43,11 +43,11 @@ STAGE PLANS: TableScan alias: foo_n5 filterExpr: (s <> 'bar') (type: boolean) - Statistics: Num rows: 10 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int), s (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from foo_n5 where s not in ('bar') diff --git a/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out b/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out index 9c37c90d5e..0901d3b257 100644 --- a/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out +++ b/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out @@ -67,14 +67,14 @@ STAGE PLANS: TableScan alias: partition_test_partitioned filterExpr: ((UDFToDouble(dt) >= 100.0D) and (UDFToDouble(dt) <= 102.0D)) (type: boolean) - Statistics: Num rows: 75 Data size: 548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 26925 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((UDFToDouble(dt) <= 102.0D) and (UDFToDouble(dt) >= 100.0D)) (type: boolean) - Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2872 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), dt (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2936 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select * from partition_test_partitioned where dt >=100 and dt <= 102 @@ -181,14 +181,14 @@ STAGE PLANS: TableScan alias: partition_test_partitioned filterExpr: ((UDFToDouble(dt) >= 100.0D) and (UDFToDouble(dt) <= 102.0D)) (type: boolean) - Statistics: Num rows: 75 Data size: 548 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 26925 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((UDFToDouble(dt) <= 102.0D) and (UDFToDouble(dt) >= 100.0D)) (type: boolean) - Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2872 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), dt (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 58 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2936 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select * from partition_test_partitioned where dt >=100 and dt <= 102 diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index 68a58bd0cc..5d9493c39e 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -67,21 +67,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: ((ds <= '2000-04-09') and (key < 5)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key < 5) (type: boolean) - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -193,13 +193,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -264,21 +264,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: ((ds <= '2000-04-09') or (key < 5)) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds <= '2000-04-09') or (key < 5)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -439,13 +439,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -547,21 +547,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: ((key < 5) and (value <> 'val_2')) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key < 5) and (value <> 'val_2')) (type: boolean) - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -673,13 +673,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3614 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -746,21 +746,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -872,13 +872,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1390 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -947,21 +947,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1122,13 +1122,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2224 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1207,21 +1207,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1382,13 +1382,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4448 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1471,21 +1471,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: ((ds) IN ('2000-04-08', '2000-04-09') and (key = 14)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 14) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -1596,13 +1596,13 @@ STAGE PLANS: Select Operator expressions: 14 (type: int), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1653,17 +1653,17 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -1774,13 +1774,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1875,17 +1875,17 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: ((ds >= '2000-04-08') or ds is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 auto parallelism: false Execution mode: vectorized @@ -2045,13 +2045,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2164,21 +2164,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -2289,13 +2289,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2357,44 +2357,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -2460,11 +2460,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -2493,7 +2493,7 @@ STAGE PLANS: key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false @@ -2530,13 +2530,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2633,44 +2633,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -2785,11 +2785,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -2818,7 +2818,7 @@ STAGE PLANS: key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false @@ -2855,13 +2855,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2964,21 +2964,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) - Statistics: Num rows: 80 Data size: 640 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80 Data size: 22240 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 auto parallelism: false Execution mode: vectorized @@ -3187,13 +3187,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 48 Data size: 384 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3294,21 +3294,21 @@ STAGE PLANS: TableScan alias: pcr_t1 filterExpr: ((ds > '2000-04-08') or ((ds <= '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds <= '2000-04-09') and (key = 2)) or (ds > '2000-04-08')) (type: boolean) - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 auto parallelism: false Execution mode: vectorized @@ -3468,13 +3468,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3598,18 +3598,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: pcr_t1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3640,29 +3640,29 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -3693,12 +3693,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -3776,13 +3776,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4081,7 +4081,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -4119,13 +4119,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4192,22 +4192,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: pcr_t1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 2) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 2 (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4238,33 +4238,33 @@ STAGE PLANS: Select Operator expressions: 2 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false Filter Operator isSamplingPred: false predicate: (key = 3) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 3 (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4295,12 +4295,12 @@ STAGE PLANS: Select Operator expressions: 3 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -4378,13 +4378,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4683,7 +4683,7 @@ STAGE PLANS: Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -4721,13 +4721,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4785,17 +4785,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 TopN: 10 TopN Hash Memory Usage: 0.1 @@ -4861,16 +4861,16 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -4917,21 +4917,21 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((hr) IN ('11', '12') and (ds = '2008-04-08') and (UDFToDouble(key) = 11.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) = 11.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -5045,13 +5045,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -5109,21 +5109,21 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((hr = '11') and (UDFToDouble(key) = 11.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) = 11.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -5237,13 +5237,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 224000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 224000 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -5524,11 +5524,11 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: explain select key,value from srcpart where hr = cast(11 as double) @@ -5546,11 +5546,11 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: explain select key,value from srcpart where cast(hr as double) = 11 @@ -5568,10 +5568,10 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL ListSink diff --git a/ql/src/test/results/clientpositive/pcs.q.out b/ql/src/test/results/clientpositive/pcs.q.out index 5cfc0932e8..4897fadf8c 100644 --- a/ql/src/test/results/clientpositive/pcs.q.out +++ b/ql/src/test/results/clientpositive/pcs.q.out @@ -101,21 +101,21 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -226,13 +226,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -284,22 +284,22 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: ((struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -454,22 +454,22 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: ((struct(ds,(key + 2))) IN (const struct('2000-04-08',3), const struct('2000-04-09',4)) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(ds,(key + 2))) IN (const struct('2000-04-08',3), const struct('2000-04-09',4)) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -624,28 +624,28 @@ STAGE PLANS: TableScan alias: a filterExpr: ((struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09')) and (struct(ds)) IN (const struct('2000-04-09'), const struct('2000-04-08'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Reduce Output Operator key expressions: ds (type: string) null sort order: a sort order: + Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: key (type: int) auto parallelism: false TableScan alias: b filterExpr: ((struct(ds)) IN (const struct('2000-04-09'), const struct('2000-04-08')) and (struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Reduce Output Operator key expressions: ds (type: string) null sort order: a sort order: + Map-reduce partition columns: ds (type: string) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: key (type: int) auto parallelism: false @@ -760,21 +760,21 @@ STAGE PLANS: 0 ds (type: string) 1 ds (type: string) outputColumnNames: _col0, _col2, _col6, _col8 - Statistics: Num rows: 44 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 800 Data size: 300800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: (struct(_col2,_col0,_col8)) IN (const struct('2000-04-08',1,'2000-04-09'), const struct('2000-04-09',2,'2000-04-08')) (type: boolean) - Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 15040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col6 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -825,22 +825,22 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: ((struct(ds,(key + key))) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) and (struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(ds,(key + key))) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -996,21 +996,21 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: ((struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) and (struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1031,14 +1031,14 @@ STAGE PLANS: window function: GenericUDAFLagEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: lag_window_0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1094,53 +1094,53 @@ STAGE PLANS: TableScan alias: x filterExpr: ((struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) and (struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-08') and (struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09')) and (struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2))) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), '2008-04-08' (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 auto parallelism: false TableScan alias: y filterExpr: ((struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) and (struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2008-04-08') and (struct(ds)) IN (const struct('2000-04-08'), const struct('2000-04-09')) and (struct(ds,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2))) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), '2008-04-08' (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 auto parallelism: false Needs Tagging: false @@ -1148,13 +1148,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 564 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1260,16 +1260,16 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: (const struct(10)) IN (const struct(10), const struct(11)) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3840 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (const struct(10)) IN (const struct(10), const struct(11)) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select ds from pcs_t1 where struct(case when ds='2000-04-08' then 10 else 20 end) in (struct(10),struct(11)) @@ -1316,22 +1316,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: pcs_t1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(ds,key,rand(100))) IN (const struct('2000-04-08',1,0.2), const struct('2000-04-09',2,0.3)) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1472,22 +1472,22 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: (struct(((ds = '2000-04-08') or (key = 2)),key)) IN (const struct(true,2), const struct(false,3)) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 11280 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(((ds = '2000-04-08') or (key = 2)),key)) IN (const struct(true,2), const struct(false,3)) (type: boolean) - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5520 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5520 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1694,22 +1694,22 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: ((key = 3) or ((struct(((ds = '2000-04-08') or (key = 2)),key)) IN (const struct(true,2), const struct(false,3)) and ((key + 5) > 0))) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 11280 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (((struct(((ds = '2000-04-08') or (key = 2)),key)) IN (const struct(true,2), const struct(false,3)) and ((key + 5) > 0)) or (key = 3)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2820 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2760 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 2760 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query1.q.out b/ql/src/test/results/clientpositive/perf/spark/query1.q.out index 19f24ba904..1dbb62ede3 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query1.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query1.q.out @@ -47,220 +47,230 @@ order by c_customer_id limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 10 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_state = 'NM') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_state = 'NM') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 36), Map 13 (PARTITION-LEVEL SORT, 36) - Reducer 12 <- Reducer 11 (GROUP PARTITION-LEVEL SORT, 39) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 36), Map 7 (PARTITION-LEVEL SORT, 36) - Reducer 3 <- Reducer 2 (GROUP, 39) - Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 559), Reducer 3 (PARTITION-LEVEL SORT, 559) - Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 601), Reducer 4 (PARTITION-LEVEL SORT, 601) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 9 <- Map 8 (GROUP PARTITION-LEVEL SORT, 17) #### A masked pattern was here #### Vertices: - Map 1 + Map 8 Map Operator Tree: TableScan alias: store_returns - filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null and sr_customer_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 6891360020 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (sr_customer_sk is not null and sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + predicate: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) + Statistics: Num rows: 53634860 Data size: 6417950124 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_returned_date_sk (type: int), sr_customer_sk (type: int), sr_store_sk (type: int), sr_fee (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 53634860 Data size: 6417950124 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 10 + Statistics: Num rows: 17467258 Data size: 1870797840 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col2 (type: int), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 17467258 Data size: 2081058800 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 17467258 Data size: 2081058800 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + Reducer 9 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13369812 Data size: 1592886816 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 13369812 Data size: 1592886816 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), count(_col2) + keys: _col1 (type: int) + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 29 Data size: 3588 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ((_col1 / _col2) * 1.2) (type: decimal(38,11)), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 29 Data size: 3356 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 Map Operator Tree: TableScan - alias: store_returns - filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_state = 'NM') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_state = 'NM') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 35 Data size: 3150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: sr_returned_date_sk (type: int), sr_customer_sk (type: int), sr_store_sk (type: int), sr_fee (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 35 Data size: 3150 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 16) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 67), Reducer 2 (PARTITION-LEVEL SORT, 67) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: store_returns + filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null and sr_customer_sk is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 6891360020 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: (sr_customer_sk is not null and sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) + Statistics: Num rows: 51757026 Data size: 6193248408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + expressions: sr_returned_date_sk (type: int), sr_customer_sk (type: int), sr_store_sk (type: int), sr_fee (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 51757026 Data size: 6193248408 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 5 + Statistics: Num rows: 16855704 Data size: 1805298496 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col2 (type: int), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 16855704 Data size: 2008197920 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 16855704 Data size: 2008197920 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized - Map 9 + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 8320000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 8320000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 8320000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 8320000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col2 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 12 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 31675133 Data size: 2454207210 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: decimal(17,2)) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 31675133 Data size: 2454207210 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), count(_col2) - keys: _col1 (type: int) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15837566 Data size: 1227103566 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ((_col1 / _col2) * 1.2) (type: decimal(38,11)), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 15837566 Data size: 1227103566 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 15837566 Data size: 1227103566 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(38,11)) Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col2 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 3 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -270,11 +280,11 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 31675133 Data size: 2454207210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12844075 Data size: 1530250220 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 31675133 Data size: 2454207210 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12844075 Data size: 1530250220 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -283,15 +293,17 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2 input vertices: - 1 Map 8 - Statistics: Num rows: 34842647 Data size: 2699627989 Basic stats: COMPLETE Column stats: NONE + 1 Map 6 + Statistics: Num rows: 2129284 Data size: 244475300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34842647 Data size: 2699627989 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2129284 Data size: 244475300 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: decimal(17,2)) - Reducer 4 + Reducer 3 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -300,48 +312,42 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col6 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)), _col6 (type: string) - Reducer 5 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col2, _col6, _col7 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 > _col7) (type: boolean) - Statistics: Num rows: 32266667 Data size: 27749985689 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 32266667 Data size: 27749985689 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Statistics: Num rows: 32266667 Data size: 27749985689 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - Reducer 6 + Statistics: Num rows: 2129284 Data size: 454409816 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2, _col6, _col7 + input vertices: + 1 Reducer 9 + Statistics: Num rows: 2205329 Data size: 714526596 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col2 > _col7) (type: boolean) + Statistics: Num rows: 735109 Data size: 238175316 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 735109 Data size: 73510900 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 735109 Data size: 73510900 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 32266667 Data size: 27749985689 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 735109 Data size: 73510900 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 10000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 10000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query10.q.out b/ql/src/test/results/clientpositive/perf/spark/query10.q.out index b7faa9a130..39dcaf2b07 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query10.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query10.q.out @@ -115,80 +115,31 @@ select limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4, Stage-5 + Stage-1 depends on stages: Stage-2 + Stage-4 is a root stage + Stage-5 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 10 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_moy BETWEEN 4 AND 7 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 13 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_moy BETWEEN 4 AND 7 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-4 - Spark -#### A masked pattern was here #### - Vertices: - Map 16 + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2002) and d_moy BETWEEN 4 AND 7 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -197,51 +148,26 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 12 <- Map 11 (GROUP, 169) - Reducer 15 <- Map 14 (GROUP, 336) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 7 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 597), Reducer 2 (PARTITION-LEVEL SORT, 597) - Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 1009), Reducer 12 (PARTITION-LEVEL SORT, 1009), Reducer 15 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009) - Reducer 5 <- Reducer 4 (GROUP, 1009) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 11 <- Map 10 (GROUP, 2) + Reducer 14 <- Map 13 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: c - filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) - Execution mode: vectorized - Map 11 + Map 10 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151734616 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -250,34 +176,34 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 13 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + 1 Map 12 + Statistics: Num rows: 5675186 Data size: 22557300 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55819 Data size: 221868 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55819 Data size: 221868 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work - Map 14 + Map 13 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 2292391500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285115246 Data size: 2269509840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_ship_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285115246 Data size: 2269509840 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -286,73 +212,34 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 16 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + 1 Map 15 + Statistics: Num rows: 11162598 Data size: 38941196 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55425 Data size: 193356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55425 Data size: 193356 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work - Map 7 - Map Operator Tree: - TableScan - alias: ca - filterExpr: ((ca_county) IN ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((ca_county) IN ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_address_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Map 8 - Map Operator Tree: - TableScan - alias: customer_demographics - filterExpr: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cd_demo_sk (type: int), cd_gender (type: string), cd_marital_status (type: string), cd_education_status (type: string), cd_purchase_estimate (type: int), cd_credit_rating (type: string), cd_dep_count (type: int), cd_dep_employed_count (type: int), cd_dep_college_count (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: int), _col7 (type: int), _col8 (type: int) - Execution mode: vectorized - Map 9 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 4400627472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -361,61 +248,135 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 10 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + 1 Map 9 + Statistics: Num rows: 20713610 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20713610 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55819 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Reducer 12 + Reducer 11 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55819 Data size: 221868 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) - Reducer 15 + Statistics: Num rows: 55819 Data size: 445144 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) + Reducer 14 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55425 Data size: 193356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) + Statistics: Num rows: 55425 Data size: 415056 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 9), Map 6 (PARTITION-LEVEL SORT, 9) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 6), Reducer 2 (PARTITION-LEVEL SORT, 6) + Reducer 4 <- Reducer 3 (GROUP, 2) + Reducer 5 <- Reducer 4 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 948805540 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int) + Execution mode: vectorized + Map 6 + Map Operator Tree: + TableScan + alias: ca + filterExpr: ((ca_county) IN ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((ca_county) IN ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 2000000 Data size: 204000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2000000 Data size: 204000000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2000000 Data size: 204000000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Map 7 + Map Operator Tree: + TableScan + alias: customer_demographics + filterExpr: cd_demo_sk is not null (type: boolean) + Statistics: Num rows: 1861800 Data size: 698175000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cd_demo_sk is not null (type: boolean) + Statistics: Num rows: 1861800 Data size: 698175000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cd_demo_sk (type: int), cd_gender (type: string), cd_marital_status (type: string), cd_education_status (type: string), cd_purchase_estimate (type: int), cd_credit_rating (type: string), cd_dep_count (type: int), cd_dep_employed_count (type: int), cd_dep_college_count (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1861800 Data size: 698175000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1861800 Data size: 698175000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: int), _col7 (type: int), _col8 (type: int) + Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator @@ -425,14 +386,16 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3860070 Data size: 20077712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3860070 Data size: 20077712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reducer 3 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -441,48 +404,44 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - value expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: int), _col12 (type: int), _col13 (type: int) + Statistics: Num rows: 3914656 Data size: 1467996000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + Left Outer Join 0 to 2 + Left Outer Join 0 to 3 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) + outputColumnNames: _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col15, _col17 + input vertices: + 1 Map 8 + 2 Reducer 11 + 3 Reducer 14 + Statistics: Num rows: 2771 Data size: 1050209 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col15 is not null or _col17 is not null) (type: boolean) + Statistics: Num rows: 2771 Data size: 1050209 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: int), _col12 (type: int), _col13 (type: int) + outputColumnNames: _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Statistics: Num rows: 2771 Data size: 1050209 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: int), _col12 (type: int), _col13 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 379 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: int) + sort order: ++++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: int) + Statistics: Num rows: 1 Data size: 379 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col8 (type: bigint) Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - Left Outer Join 0 to 2 - Left Outer Join 0 to 3 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - 3 _col0 (type: int) - outputColumnNames: _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col15, _col17 - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col15 is not null or _col17 is not null) (type: boolean) - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: int), _col12 (type: int), _col13 (type: int) - outputColumnNames: _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: int), _col12 (type: int), _col13 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: int) - sort order: ++++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: int) - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col8 (type: bigint) - Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -490,35 +449,85 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: string), KEY._col5 (type: int), KEY._col6 (type: int), KEY._col7 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 379 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col8 (type: bigint), _col3 (type: int), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6, _col8, _col10, _col12 - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 419 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: int), _col6 (type: string), _col8 (type: int), _col10 (type: int), _col12 (type: int) sort order: ++++++++ - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 419 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: bigint), KEY.reducesinkkey3 (type: int), VALUE._col0 (type: bigint), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: bigint), KEY.reducesinkkey5 (type: int), VALUE._col0 (type: bigint), KEY.reducesinkkey6 (type: int), VALUE._col0 (type: bigint), KEY.reducesinkkey7 (type: int), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 419 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 419 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 419 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 12 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_moy BETWEEN 4 AND 7 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) (type: boolean) + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 15 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_moy BETWEEN 4 AND 7 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) (type: boolean) + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-0 Fetch Operator limit: 100 diff --git a/ql/src/test/results/clientpositive/perf/spark/query11.q.out b/ql/src/test/results/clientpositive/perf/spark/query11.q.out index 87a0cc03eb..b23967fd01 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query11.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query11.q.out @@ -147,308 +147,338 @@ with year_total as ( limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 975), Reducer 10 (PARTITION-LEVEL SORT, 975) - Reducer 12 <- Reducer 11 (GROUP, 481) - Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 154), Map 19 (PARTITION-LEVEL SORT, 154) - Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 706), Reducer 16 (PARTITION-LEVEL SORT, 706) - Reducer 18 <- Reducer 17 (GROUP, 186) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 7 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 398), Map 25 (PARTITION-LEVEL SORT, 398) - Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 975), Reducer 22 (PARTITION-LEVEL SORT, 975) - Reducer 24 <- Reducer 23 (GROUP, 481) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 706), Reducer 2 (PARTITION-LEVEL SORT, 706) - Reducer 4 <- Reducer 3 (GROUP, 186) - Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 444), Reducer 18 (PARTITION-LEVEL SORT, 444), Reducer 24 (PARTITION-LEVEL SORT, 444), Reducer 4 (PARTITION-LEVEL SORT, 444) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 6 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 21 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Reducer 9 (GROUP, 1009) + Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 502), Map 17 (PARTITION-LEVEL SORT, 502) + Reducer 15 <- Reducer 14 (GROUP, 307) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 703), Map 22 (PARTITION-LEVEL SORT, 703) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 502), Map 7 (PARTITION-LEVEL SORT, 502) + Reducer 20 <- Reducer 19 (GROUP, 1009) + Reducer 3 <- Reducer 2 (GROUP, 307) + Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 653), Reducer 15 (PARTITION-LEVEL SORT, 653), Reducer 20 (PARTITION-LEVEL SORT, 653), Reducer 3 (PARTITION-LEVEL SORT, 653) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 703), Map 8 (PARTITION-LEVEL SORT, 703) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 33400258728 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143930993 Data size: 33383634304 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 143930993 Data size: 33383634304 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 6 + Statistics: Num rows: 51391963 Data size: 11709154632 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 51391963 Data size: 11709154632 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + Map 12 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 15 + Map 13 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 33400258728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 33383634304 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 19 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 33383634304 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 16 + Statistics: Num rows: 51391963 Data size: 11709154632 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 51391963 Data size: 11709154632 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 20 + Local Work: + Map Reduce Local Work + Map 17 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 21 + Map 18 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 127618307008 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 116392187420 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525327388 Data size: 116392187420 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 21 + Statistics: Num rows: 187573258 Data size: 37377492516 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 187573258 Data size: 37377492516 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 25 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 26 + Local Work: + Map Reduce Local Work + Map 22 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 8 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 9 + Map 8 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 127618307008 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 116392187420 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525327388 Data size: 116392187420 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 11 + Statistics: Num rows: 187573258 Data size: 37377492516 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 187573258 Data size: 37377492516 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(18,2)) - Reducer 12 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -456,41 +486,25 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(18,2)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 39765530696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(18,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(18,2)) - Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Reducer 17 + Reducer 14 Reduce Operator Tree: Join Operator condition map: @@ -499,24 +513,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 45011290100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 45011290100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: decimal(18,2)) - Reducer 18 + Reducer 15 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -524,57 +538,51 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(18,2)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(18,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(18,2)) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Reducer 22 + Reducer 19 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Reducer 23 + outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Statistics: Num rows: 187573258 Data size: 159019506280 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 187573258 Data size: 159019506280 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col7) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col7 (type: decimal(18,2)) + Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -583,24 +591,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 45011290100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 45011290100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: decimal(18,2)) - Reducer 24 + Reducer 20 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -608,44 +616,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(18,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 55709257626 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 55709257626 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: decimal(18,2)) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(18,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -653,18 +635,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(18,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(18,2)) - Reducer 5 + Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -677,36 +659,62 @@ STAGE PLANS: 2 _col0 (type: string) 3 _col0 (type: string) outputColumnNames: _col1, _col3, _col5, _col7, _col8 - Statistics: Num rows: 1149975359 Data size: 101451160012 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 99976546514 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col8 / _col3))) ELSE ((null > (_col8 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END (type: boolean) - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 49988273257 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col7 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 7971863465 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 7971863465 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 7971863465 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Statistics: Num rows: 187573258 Data size: 159019506280 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 187573258 Data size: 159019506280 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col7) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col7 (type: decimal(18,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query12.q.out b/ql/src/test/results/clientpositive/perf/spark/query12.q.out index 413930c1d8..c428ed49da 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query12.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query12.q.out @@ -77,14 +77,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -96,9 +96,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 174), Map 7 (PARTITION-LEVEL SORT, 174) - Reducer 3 <- Reducer 2 (GROUP, 186) - Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 93) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 16), Map 7 (PARTITION-LEVEL SORT, 16) + Reducer 3 <- Reducer 2 (GROUP, 26) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 26) Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -107,14 +107,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 17276151220 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271855784 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271855784 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -124,12 +124,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 6 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 1851421264 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 1851421264 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized Local Work: @@ -139,19 +139,19 @@ STAGE PLANS: TableScan alias: item filterExpr: ((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 268753408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string), i_current_price (type: decimal(7,2)), i_class (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)), _col4 (type: string), _col5 (type: string) Execution mode: vectorized Reducer 2 @@ -163,18 +163,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3306948112 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col10 (type: string), _col9 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3310972832 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3310972832 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) Reducer 3 Execution mode: vectorized @@ -184,12 +184,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3310972832 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3310972832 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)) Reducer 4 Execution mode: vectorized @@ -197,7 +197,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3310972832 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -217,15 +217,15 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3310972832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3848373248 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string), _col6 (type: string), _col0 (type: string), _col5 (type: decimal(38,17)) sort order: +++++ - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3848373248 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(7,2)), _col4 (type: decimal(17,2)) Reducer 5 @@ -234,13 +234,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(7,2)), VALUE._col1 (type: decimal(17,2)), KEY.reducesinkkey4 (type: decimal(38,17)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4798568 Data size: 3848373248 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query13.q.out b/ql/src/test/results/clientpositive/perf/spark/query13.q.out index 4073113b35..82cc3725c5 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query13.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query13.q.out @@ -99,54 +99,30 @@ select avg(ss_quantity) )) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4 + Stage-1 depends on stages: Stage-2 + Stage-4 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 10 - Map Operator Tree: - TableScan - alias: store - filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s_store_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 5 Map Operator Tree: TableScan alias: household_demographics filterExpr: ((hd_dep_count) IN (3, 1) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 57600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((hd_dep_count) IN (3, 1) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int), hd_dep_count (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -155,13 +131,10 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 133), Map 6 (PARTITION-LEVEL SORT, 133) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 152), Reducer 2 (PARTITION-LEVEL SORT, 152) - Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 166), Reducer 3 (PARTITION-LEVEL SORT, 166) - Reducer 5 <- Reducer 4 (GROUP, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 175), Map 4 (PARTITION-LEVEL SORT, 175) #### A masked pattern was here #### Vertices: Map 1 @@ -169,97 +142,74 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 259636430644 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 152520430 Data size: 68750278196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_cdemo_sk (type: int), ss_hdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)) - Execution mode: vectorized - Map 6 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 152520430 Data size: 68750278196 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + input vertices: + 1 Map 3 + Statistics: Num rows: 54458905 Data size: 22274855684 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 54458905 Data size: 22274855684 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Map 4 Map Operator Tree: TableScan alias: customer_demographics filterExpr: ((cd_marital_status) IN ('M', 'D', 'U') and (cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 340709400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 9 + Map 8 Map Operator Tree: TableScan - alias: customer_address - filterExpr: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ca_address_sk (type: int), ca_state (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 211198404 Data size: 18631984502 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 211198404 Data size: 18631984502 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)) - Reducer 3 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -270,7 +220,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col13, _col14 - Statistics: Num rows: 232318249 Data size: 20495183396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22096687 Data size: 11023711613 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -279,71 +229,115 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col13, _col14, _col16 input vertices: - 1 Map 8 - Statistics: Num rows: 255550079 Data size: 22544702224 Basic stats: COMPLETE Column stats: NONE + 1 Map 5 + Statistics: Num rows: 4017301 Data size: 735166543 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col13 = 'D') and (_col14 = 'Primary') and _col6 BETWEEN 50 AND 100 and (_col16 = 1)) or ((_col13 = 'M') and (_col14 = '4 yr Degree') and _col6 BETWEEN 100 AND 150 and (_col16 = 3)) or ((_col13 = 'U') and (_col14 = 'Advanced Degree') and _col6 BETWEEN 150 AND 200 and (_col16 = 1))) (type: boolean) - Statistics: Num rows: 10647918 Data size: 939362419 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 10647918 Data size: 939362419 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col5 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)) - Reducer 4 + Statistics: Num rows: 30435 Data size: 5570065 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 7 <- Map 6 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: customer_address + filterExpr: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 7480000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 3740000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int), ca_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20000000 Data size: 3740000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5, _col7, _col8, _col9, _col18 + input vertices: + 0 Reducer 2 + Statistics: Num rows: 15218 Data size: 1309092 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((((_col18 = 'KY') or (_col18 = 'GA') or (_col18 = 'NM')) and _col9 BETWEEN 100 AND 200) or (((_col18 = 'MT') or (_col18 = 'OR') or (_col18 = 'IN')) and _col9 BETWEEN 150 AND 300) or (((_col18 = 'WI') or (_col18 = 'MO') or (_col18 = 'WV')) and _col9 BETWEEN 50 AND 250)) (type: boolean) + Statistics: Num rows: 5070 Data size: 436364 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col7, _col8 + input vertices: + 1 Map 8 + Statistics: Num rows: 5070 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col5), count(_col5), sum(_col7), count(_col7), sum(_col8), count(_col8) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(17,2)), _col3 (type: bigint), _col4 (type: decimal(17,2)), _col5 (type: bigint) + Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col5, _col7, _col8, _col9, _col18 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col18 = 'KY') or (_col18 = 'GA') or (_col18 = 'NM')) and _col9 BETWEEN 100 AND 200) or (((_col18 = 'MT') or (_col18 = 'OR') or (_col18 = 'IN')) and _col9 BETWEEN 150 AND 300) or (((_col18 = 'WI') or (_col18 = 'MO') or (_col18 = 'WV')) and _col9 BETWEEN 50 AND 250)) (type: boolean) - Statistics: Num rows: 7333332 Data size: 7442451276 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col5, _col7, _col8 - input vertices: - 1 Map 10 - Statistics: Num rows: 8066665 Data size: 8186696581 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col5), count(_col5), sum(_col7), count(_col7), sum(_col8), count(_col8) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(17,2)), _col3 (type: bigint), _col4 (type: decimal(17,2)), _col5 (type: bigint) - Reducer 5 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), sum(VALUE._col4), count(VALUE._col5) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double), (_col2 / _col3) (type: decimal(37,22)), (_col4 / _col5) (type: decimal(37,22)), CAST( _col4 AS decimal(17,2)) (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 3 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-0 Fetch Operator limit: -1 diff --git a/ql/src/test/results/clientpositive/perf/spark/query15.q.out b/ql/src/test/results/clientpositive/perf/spark/query15.q.out index 67684f6b0b..7795c9d71d 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query15.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query15.q.out @@ -37,18 +37,43 @@ select ca_zip limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 8 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 6 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 927), Reducer 8 (PARTITION-LEVEL SORT, 927) - Reducer 4 <- Reducer 3 (GROUP, 369) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 61), Map 6 (PARTITION-LEVEL SORT, 61) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 129), Reducer 2 (PARTITION-LEVEL SORT, 129) + Reducer 4 <- Reducer 3 (GROUP, 2) Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 8 <- Map 7 (PARTITION-LEVEL SORT, 305), Map 9 (PARTITION-LEVEL SORT, 305) #### A masked pattern was here #### Vertices: Map 1 @@ -56,19 +81,19 @@ STAGE PLANS: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Map 6 @@ -76,19 +101,19 @@ STAGE PLANS: TableScan alias: customer_address filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7160000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7160000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string), ca_zip (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7160000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7160000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 7 @@ -96,40 +121,33 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 34386059012 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 34043140912 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 34043140912 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 8 + Statistics: Num rows: 20154874 Data size: 2172669560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 20154874 Data size: 2172669560 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -139,12 +157,12 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3, _col4 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14320000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14320000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string), _col4 (type: string) Reducer 3 Reduce Operator Tree: @@ -155,25 +173,25 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col3, _col4, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20154874 Data size: 5624851974 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col3 = 'CA') or (_col3 = 'GA') or (_col3 = 'WA') or (_col7 > 500) or (substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792')) (type: boolean) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20154874 Data size: 5624851974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: string), _col7 (type: decimal(7,2)) outputColumnNames: _col4, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20154874 Data size: 5624851974 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col7) keys: _col4 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56210 Data size: 11298210 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56210 Data size: 11298210 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(17,2)) Reducer 4 @@ -184,11 +202,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2555 Data size: 513555 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2555 Data size: 513555 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(17,2)) Reducer 5 @@ -197,33 +215,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: decimal(17,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2555 Data size: 513555 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 20100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 20100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 8 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query16.q.out b/ql/src/test/results/clientpositive/perf/spark/query16.q.out index b5adc856b9..91e3b55a03 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query16.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query16.q.out @@ -74,14 +74,14 @@ STAGE PLANS: TableScan alias: call_center filterExpr: ((cc_county) IN ('Ziebach County', 'Levy County', 'Huron County', 'Franklin Parish', 'Daviess County') and cc_call_center_sk is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cc_county) IN ('Ziebach County', 'Levy County', 'Huron County', 'Franklin Parish', 'Daviess County') and cc_call_center_sk is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cc_call_center_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -99,14 +99,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-04-01 00:00:00' AND TIMESTAMP'2001-05-31 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-04-01 00:00:00' AND TIMESTAMP'2001-05-31 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -118,11 +118,11 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 13 <- Map 12 (GROUP, 24) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 494), Map 9 (PARTITION-LEVEL SORT, 494) - Reducer 3 <- Map 11 (PARTITION-LEVEL SORT, 711), Reducer 2 (PARTITION-LEVEL SORT, 711) - Reducer 4 <- Reducer 13 (PARTITION-LEVEL SORT, 459), Reducer 3 (PARTITION-LEVEL SORT, 459) - Reducer 5 <- Reducer 4 (GROUP, 246) + Reducer 13 <- Map 12 (GROUP, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 59), Map 9 (PARTITION-LEVEL SORT, 59) + Reducer 3 <- Map 11 (PARTITION-LEVEL SORT, 26), Reducer 2 (PARTITION-LEVEL SORT, 26) + Reducer 4 <- Reducer 13 (PARTITION-LEVEL SORT, 10), Reducer 3 (PARTITION-LEVEL SORT, 10) + Reducer 5 <- Reducer 4 (GROUP, 2) Reducer 6 <- Reducer 5 (GROUP, 1) Reducer 7 <- Reducer 6 (SORT, 1) #### A masked pattern was here #### @@ -132,14 +132,14 @@ STAGE PLANS: TableScan alias: cs1 filterExpr: (cs_ship_date_sk is not null and cs_ship_addr_sk is not null and cs_call_center_sk is not null and cs_order_number is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 70085289844 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_call_center_sk is not null and cs_order_number is not null and cs_ship_addr_sk is not null and cs_ship_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283695062 Data size: 69040112396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_ship_date_sk (type: int), cs_ship_addr_sk (type: int), cs_call_center_sk (type: int), cs_warehouse_sk (type: int), cs_order_number (type: int), cs_ext_ship_cost (type: decimal(7,2)), cs_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283695062 Data size: 69040112396 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -149,12 +149,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6 input vertices: 1 Map 8 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31519516 Data size: 7388874644 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31519516 Data size: 7388874644 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized Local Work: @@ -164,24 +164,24 @@ STAGE PLANS: TableScan alias: cs2 filterExpr: (cs_order_number is not null and cs_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 2298154224 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_order_number is not null and cs_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286548719 Data size: 2286654132 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_order_number (type: int), cs_warehouse_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286548719 Data size: 2286654132 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286548719 Data size: 2286654132 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286548719 Data size: 2286654132 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Map 12 @@ -189,39 +189,39 @@ STAGE PLANS: TableScan alias: cr1 filterExpr: cr_order_number is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 115195524 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cr_order_number is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 115195524 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: cr_order_number (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 115195524 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 115195524 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 9 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_state = 'NY') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_state = 'NY') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 13 Execution mode: vectorized @@ -230,16 +230,16 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 14399440 Data size: 1528617286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18238808 Data size: 72955232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14399440 Data size: 1528617286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18238808 Data size: 145910464 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14399440 Data size: 1528617286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18238808 Data size: 145910464 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reducer 2 Local Work: @@ -252,7 +252,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30901534 Data size: 7122617080 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -262,12 +262,12 @@ STAGE PLANS: outputColumnNames: _col3, _col4, _col5, _col6 input vertices: 1 Map 10 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5150256 Data size: 1030384380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int) sort order: + Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5150256 Data size: 1030384380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Reducer 3 Reduce Operator Tree: @@ -279,16 +279,16 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3, _col4, _col5, _col6, _col14 residual filter predicates: {(_col3 <> _col14)} - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5150256 Data size: 1045249784 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) outputColumnNames: _col4, _col5, _col6 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5150256 Data size: 1030384380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int) sort order: + Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5150256 Data size: 1030384380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Reducer 4 Reduce Operator Tree: @@ -299,25 +299,25 @@ STAGE PLANS: 0 _col4 (type: int) 1 _col0 (type: int) outputColumnNames: _col4, _col5, _col6, _col14 - Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5150256 Data size: 1036062880 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col14 is null (type: boolean) - Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) outputColumnNames: _col4, _col5, _col6 - Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col5), sum(_col6) keys: _col4 (type: int) mode: hash outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)) Reducer 5 Execution mode: vectorized @@ -327,15 +327,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), sum(_col1), sum(_col2) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Reducer 6 Execution mode: vectorized @@ -344,15 +344,15 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col0 (type: bigint) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Reducer 7 @@ -361,13 +361,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query17.q.out b/ql/src/test/results/clientpositive/perf/spark/query17.q.out index d0fa81d913..d3591c44d1 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query17.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query17.q.out @@ -88,7 +88,10 @@ limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -96,19 +99,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 16 + Map 13 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -117,221 +120,208 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 306), Map 9 (PARTITION-LEVEL SORT, 306) - Reducer 11 <- Reducer 10 (PARTITION-LEVEL SORT, 374), Reducer 14 (PARTITION-LEVEL SORT, 374) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 36), Map 15 (PARTITION-LEVEL SORT, 36) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 442), Reducer 2 (PARTITION-LEVEL SORT, 442) - Reducer 4 <- Reducer 11 (PARTITION-LEVEL SORT, 850), Reducer 3 (PARTITION-LEVEL SORT, 850) - Reducer 5 <- Reducer 4 (GROUP, 582) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 6 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_customer_sk is not null and ss_item_sk is not null and ss_ticket_number is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: d1 + filterExpr: ((d_quarter_name = '2000Q1') and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 6866606 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_quarter_name = '2000Q1') and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 101 Data size: 9494 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 9494 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan alias: d3 filterExpr: ((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 6866606 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3652 Data size: 343288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 13 - Map Operator Tree: - TableScan - alias: store_returns - filterExpr: (sr_customer_sk is not null and sr_item_sk is not null and sr_ticket_number is not null and sr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_customer_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + Statistics: Num rows: 3652 Data size: 343288 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 15 + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 12 Map Operator Tree: TableScan alias: d2 filterExpr: ((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 6866606 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3652 Data size: 343288 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3652 Data size: 343288 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 7 (PARTITION-LEVEL SORT, 4) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 149), Reducer 9 (PARTITION-LEVEL SORT, 149) + Reducer 4 <- Reducer 3 (GROUP, 1009) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 2), Map 8 (PARTITION-LEVEL SORT, 2) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: d1 - filterExpr: ((d_quarter_name = '2000Q1') and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_customer_sk is not null and ss_item_sk is not null and ss_ticket_number is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 13409244716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_quarter_name = '2000Q1') and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) + Statistics: Num rows: 501694138 Data size: 11679497312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 501694138 Data size: 11679497312 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 6 + Statistics: Num rows: 27749405 Data size: 284128524 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 27749405 Data size: 284128524 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int) Execution mode: vectorized - Map 8 + Local Work: + Map Reduce Local Work + Map 11 + Map Operator Tree: + TableScan + alias: store_returns + filterExpr: (sr_customer_sk is not null and sr_item_sk is not null and sr_ticket_number is not null and sr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 1127638720 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) (type: boolean) + Statistics: Num rows: 53632139 Data size: 1050121008 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_customer_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 53632139 Data size: 1050121008 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 12 + Statistics: Num rows: 2681277 Data size: 27877676 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 2681277 Data size: 27877676 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 9 + Map 8 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 4590562460 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 4544782656 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int), cs_quantity (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) + Statistics: Num rows: 285117831 Data size: 4544782656 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 10 + Statistics: Num rows: 14254135 Data size: 159649964 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col2 (type: int), _col1 (type: int) + Statistics: Num rows: 14254135 Data size: 159649964 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int) Execution mode: vectorized - Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col2 (type: int), _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int), _col1 (type: int) - 1 _col1 (type: int), _col2 (type: int) - outputColumnNames: _col3, _col7, _col8, _col9, _col10 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col7 (type: int), _col8 (type: int), _col9 (type: int) - sort order: +++ - Map-reduce partition columns: _col7 (type: int), _col8 (type: int), _col9 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col10 (type: int) - Reducer 14 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: int) + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int) - Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -340,14 +330,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col9, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27749405 Data size: 8164959544 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) sort order: +++ Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27749405 Data size: 8164959544 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col5 (type: int), _col9 (type: string), _col10 (type: string) - Reducer 4 + Reducer 3 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -358,7 +348,7 @@ STAGE PLANS: 0 _col1 (type: int), _col2 (type: int), _col4 (type: int) 1 _col7 (type: int), _col8 (type: int), _col9 (type: int) outputColumnNames: _col3, _col5, _col9, _col10, _col14, _col21 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 1444597110452 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -367,26 +357,26 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col5, _col9, _col10, _col14, _col21, _col25 input vertices: - 1 Map 16 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + 1 Map 13 + Statistics: Num rows: 4815969644 Data size: 1839596901436 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col25 (type: string), _col5 (type: int), _col21 (type: int), _col14 (type: int), UDFToDouble(_col5) (type: double), (UDFToDouble(_col5) * UDFToDouble(_col5)) (type: double), UDFToDouble(_col21) (type: double), (UDFToDouble(_col21) * UDFToDouble(_col21)) (type: double), UDFToDouble(_col14) (type: double), (UDFToDouble(_col14) * UDFToDouble(_col14)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 1839596901436 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col3), sum(_col3), sum(_col7), sum(_col6), count(_col4), sum(_col4), sum(_col9), sum(_col8), count(_col5), sum(_col5), sum(_col11), sum(_col10) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 2244241854104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 2244241854104 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: double), _col14 (type: double) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -394,34 +384,50 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 2244241854104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint), (UDFToDouble(_col4) / _col3) (type: double), power(((_col5 - ((_col6 * _col6) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (power(((_col5 - ((_col6 * _col6) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) / (UDFToDouble(_col4) / _col3)) (type: double), _col7 (type: bigint), (UDFToDouble(_col8) / _col7) (type: double), power(((_col9 - ((_col10 * _col10) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (power(((_col9 - ((_col10 * _col10) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) / (UDFToDouble(_col8) / _col7)) (type: double), _col11 (type: bigint), (UDFToDouble(_col12) / _col11) (type: double), (power(((_col13 - ((_col14 * _col14) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END), 0.5) / (UDFToDouble(_col12) / _col11)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 2244241854104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 2244241854104 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: double) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: bigint), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col10 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4815969644 Data size: 2244241854104 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 46600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 46600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int), _col1 (type: int) + 1 _col1 (type: int), _col2 (type: int) + outputColumnNames: _col3, _col7, _col8, _col9, _col10 + Statistics: Num rows: 540026342 Data size: 10779803388 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col7 (type: int), _col8 (type: int), _col9 (type: int) + sort order: +++ + Map-reduce partition columns: _col7 (type: int), _col8 (type: int), _col9 (type: int) + Statistics: Num rows: 540026342 Data size: 10779803388 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col10 (type: int) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query18.q.out b/ql/src/test/results/clientpositive/perf/spark/query18.q.out index 3ebd215daf..d18cfa5ae0 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query18.q.out @@ -65,21 +65,71 @@ select i_item_id, limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 + Map Operator Tree: + TableScan + alias: cd2 + filterExpr: cd_demo_sk is not null (type: boolean) + Statistics: Num rows: 1861800 Data size: 7447200 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cd_demo_sk is not null (type: boolean) + Statistics: Num rows: 1861800 Data size: 7447200 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1861800 Data size: 7447200 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 306), Map 9 (PARTITION-LEVEL SORT, 306) - Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 337), Reducer 10 (PARTITION-LEVEL SORT, 337) - Reducer 12 <- Map 15 (PARTITION-LEVEL SORT, 374), Reducer 11 (PARTITION-LEVEL SORT, 374) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 7 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 597), Reducer 2 (PARTITION-LEVEL SORT, 597) - Reducer 4 <- Reducer 12 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009) - Reducer 5 <- Reducer 4 (GROUP, 1009) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 55), Reducer 9 (PARTITION-LEVEL SORT, 55) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 18), Map 6 (PARTITION-LEVEL SORT, 18) + Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 78), Reducer 2 (PARTITION-LEVEL SORT, 78) + Reducer 4 <- Reducer 3 (GROUP, 106) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 361), Map 8 (PARTITION-LEVEL SORT, 361) #### A masked pattern was here #### Vertices: Map 1 @@ -87,172 +137,114 @@ STAGE PLANS: TableScan alias: customer filterExpr: ((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_customer_sk is not null and c_current_cdemo_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 1566410112 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 35631408 Data size: 697667476 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int), c_birth_year (type: int) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 35631408 Data size: 697667476 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 35631408 Data size: 697667476 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col4 (type: int) Execution mode: vectorized - Map 13 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 14 + Map 12 Map Operator Tree: TableScan alias: cd1 filterExpr: ((cd_gender = 'M') and (cd_education_status = 'College') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 348156600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cd_education_status = 'College') and (cd_gender = 'M') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103433 Data size: 19341971 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int), cd_dep_count (type: int) outputColumnNames: _col0, _col3 - Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103433 Data size: 19031672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103433 Data size: 19031672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int) Execution mode: vectorized - Map 15 + Map 13 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 7 + Map 6 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 11400000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5490196 Data size: 1564705860 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_county (type: string), ca_state (type: string), ca_country (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5490196 Data size: 1564705860 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5490196 Data size: 1564705860 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized Map 8 - Map Operator Tree: - TableScan - alias: cd2 - filterExpr: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 9 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_sold_date_sk is not null and cs_item_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 134272441768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283692098 Data size: 132268663440 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_bill_cdemo_sk (type: int), cs_item_sk (type: int), cs_quantity (type: int), cs_list_price (type: decimal(7,2)), cs_sales_price (type: decimal(7,2)), cs_coupon_amt (type: decimal(7,2)), cs_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) + Statistics: Num rows: 283692098 Data size: 132268663440 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + input vertices: + 1 Map 11 + Statistics: Num rows: 100578970 Data size: 46175078124 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 100578970 Data size: 46175078124 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col14 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col14 (type: int) - Reducer 12 Reduce Operator Tree: Join Operator condition map: @@ -261,18 +253,20 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col4, _col5, _col6, _col7, _col8, _col14, _col16 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15983481 Data size: 8462859812 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col16 (type: string), _col1 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col14 (type: int) outputColumnNames: _col1, _col3, _col6, _col7, _col8, _col9, _col10, _col16 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15983481 Data size: 8462859812 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: int) sort order: + Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15983481 Data size: 8462859812 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col6 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)), _col16 (type: int) Reducer 2 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -281,30 +275,24 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col4, _col6, _col7, _col8 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col4 (type: int), _col6 (type: string), _col7 (type: string), _col8 (type: string) + Statistics: Num rows: 4890586 Data size: 1422969750 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col4, _col6, _col7, _col8 + input vertices: + 1 Map 7 + Statistics: Num rows: 4959744 Data size: 1428379996 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4959744 Data size: 1428379996 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: int), _col6 (type: string), _col7 (type: string), _col8 (type: string) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col4, _col6, _col7, _col8 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col6 (type: string), _col7 (type: string), _col8 (type: string) - Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -313,24 +301,24 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col3 (type: int) outputColumnNames: _col4, _col6, _col7, _col8, _col11, _col16, _col17, _col18, _col19, _col20, _col26 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2193811 Data size: 1357789943 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col11 (type: string), _col8 (type: string), _col7 (type: string), _col6 (type: string), CAST( _col16 AS decimal(12,2)) (type: decimal(12,2)), CAST( _col17 AS decimal(12,2)) (type: decimal(12,2)), CAST( _col19 AS decimal(12,2)) (type: decimal(12,2)), CAST( _col18 AS decimal(12,2)) (type: decimal(12,2)), CAST( _col20 AS decimal(12,2)) (type: decimal(12,2)), CAST( _col4 AS decimal(12,2)) (type: decimal(12,2)), CAST( _col26 AS decimal(12,2)) (type: decimal(12,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2193811 Data size: 1357789943 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), count(_col4), sum(_col5), count(_col5), sum(_col6), count(_col6), sum(_col7), count(_col7), sum(_col8), count(_col8), sum(_col9), count(_col9), sum(_col10), count(_col10) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 2108229765 Data size: 285496662075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10969055 Data size: 13480968595 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) - Statistics: Num rows: 2108229765 Data size: 285496662075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10969055 Data size: 13480968595 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(22,2)), _col6 (type: bigint), _col7 (type: decimal(22,2)), _col8 (type: bigint), _col9 (type: decimal(22,2)), _col10 (type: bigint), _col11 (type: decimal(22,2)), _col12 (type: bigint), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: decimal(22,2)), _col16 (type: bigint), _col17 (type: decimal(22,2)), _col18 (type: bigint) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -338,35 +326,51 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 1054114882 Data size: 142748330969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10969055 Data size: 13480968595 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), (_col5 / _col6) (type: decimal(38,18)), (_col7 / _col8) (type: decimal(38,18)), (_col9 / _col10) (type: decimal(38,18)), (_col11 / _col12) (type: decimal(38,18)), (_col13 / _col14) (type: decimal(38,18)), (_col15 / _col16) (type: decimal(38,18)), (_col17 / _col18) (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1054114882 Data size: 142748330969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10969055 Data size: 12778949075 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col0 (type: string) sort order: ++++ - Statistics: Num rows: 1054114882 Data size: 142748330969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10969055 Data size: 12778949075 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col4 (type: decimal(38,18)), _col5 (type: decimal(38,18)), _col6 (type: decimal(38,18)), _col7 (type: decimal(38,18)), _col8 (type: decimal(38,18)), _col9 (type: decimal(38,18)), _col10 (type: decimal(38,18)) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey3 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: decimal(38,18)), VALUE._col1 (type: decimal(38,18)), VALUE._col2 (type: decimal(38,18)), VALUE._col3 (type: decimal(38,18)), VALUE._col4 (type: decimal(38,18)), VALUE._col5 (type: decimal(38,18)), VALUE._col6 (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1054114882 Data size: 142748330969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10969055 Data size: 12778949075 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 116500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 116500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col14 + Statistics: Num rows: 15983481 Data size: 6928445636 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 15983481 Data size: 6928445636 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col14 (type: int) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query19.q.out b/ql/src/test/results/clientpositive/perf/spark/query19.q.out index d2994e6af5..5970d306c3 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query19.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query19.q.out @@ -48,7 +48,8 @@ limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -56,19 +57,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 12 + Map 10 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 158472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 158472 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_zip (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 158472 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col7 (type: int) @@ -77,94 +78,98 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 6 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1009), Reducer 9 (PARTITION-LEVEL SORT, 1009) - Reducer 4 <- Reducer 3 (GROUP, 582) - Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 8 <- Map 10 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 440), Reducer 8 (PARTITION-LEVEL SORT, 440) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: customer - filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Execution mode: vectorized - Map 10 + Map 8 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 11 + Local Work: + Map Reduce Local Work + Map 9 Map Operator Tree: TableScan alias: item filterExpr: ((i_manager_id = 7) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 97468352 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manager_id = 7) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 1547059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand_id (type: int), i_brand (type: string), i_manufact_id (type: int), i_manufact (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 1547127 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 35), Map 6 (PARTITION-LEVEL SORT, 35) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 62), Reducer 2 (PARTITION-LEVEL SORT, 62) + Reducer 4 <- Reducer 3 (GROUP, 6) + Reducer 5 <- Reducer 4 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: customer + filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: string) + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: customer_address filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_zip (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 7 @@ -172,21 +177,43 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null and ss_customer_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70513520748 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501694138 Data size: 61417514116 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Statistics: Num rows: 501694138 Data size: 61417514116 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 8 + Statistics: Num rows: 13737330 Data size: 54949440 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col9, _col10, _col11, _col12 + input vertices: + 1 Map 9 + Statistics: Num rows: 2098703 Data size: 426036693 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 2098703 Data size: 426036693 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col9 (type: int), _col10 (type: string), _col11 (type: int), _col12 (type: string) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -196,12 +223,12 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 7440000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 7440000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Reducer 3 Local Work: @@ -214,7 +241,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col2 (type: int) outputColumnNames: _col3, _col7, _col8, _col13, _col14, _col15, _col16 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 612821256 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -223,26 +250,26 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3, _col8, _col13, _col14, _col15, _col16, _col19 input vertices: - 1 Map 12 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + 1 Map 10 + Statistics: Num rows: 2098703 Data size: 799605819 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (substr(_col3, 1, 5) <> substr(_col19, 1, 5)) (type: boolean) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 799605819 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col8 (type: decimal(7,2)), _col13 (type: int), _col14 (type: string), _col15 (type: int), _col16 (type: string) outputColumnNames: _col8, _col13, _col14, _col15, _col16 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 799605819 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col8) keys: _col14 (type: string), _col13 (type: int), _col15 (type: int), _col16 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 661091309 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: string) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 661091309 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(17,2)) Reducer 4 Execution mode: vectorized @@ -252,15 +279,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 661091309 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int), _col3 (type: string), _col4 (type: decimal(17,2)), _col0 (type: string), _col1 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 879356353 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: decimal(17,2)), _col5 (type: string), _col6 (type: int), _col2 (type: int), _col3 (type: string) sort order: -++++ - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 879356353 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 5 Execution mode: vectorized @@ -268,49 +295,17 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey2 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2098703 Data size: 879356353 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 41900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 41900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 8 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 9 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col9, _col10, _col11, _col12 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col9 (type: int), _col10 (type: string), _col11 (type: int), _col12 (type: string) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query2.q.out b/ql/src/test/results/clientpositive/perf/spark/query2.q.out index f6156613e6..dcfa8158a8 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query2.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query2.q.out @@ -117,181 +117,152 @@ with wscs as order by d_week_seq1 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 459), Map 14 (PARTITION-LEVEL SORT, 459), Map 9 (PARTITION-LEVEL SORT, 459) - Reducer 11 <- Reducer 10 (GROUP, 504) - Reducer 12 <- Map 15 (PARTITION-LEVEL SORT, 253), Reducer 11 (PARTITION-LEVEL SORT, 253) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 459), Map 6 (PARTITION-LEVEL SORT, 459), Map 7 (PARTITION-LEVEL SORT, 459) - Reducer 3 <- Reducer 2 (GROUP, 504) - Reducer 4 <- Map 8 (PARTITION-LEVEL SORT, 529), Reducer 12 (PARTITION-LEVEL SORT, 529), Reducer 3 (PARTITION-LEVEL SORT, 529) - Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: web_sales - filterExpr: ws_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ws_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(7,2)) - Execution mode: vectorized Map 13 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_sold_date_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(7,2)) - Execution mode: vectorized - Map 14 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_week_seq (type: int), d_day_name (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string) - Execution mode: vectorized - Map 15 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2002) and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2002) and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_week_seq (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 6 + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Spark + Edges: + Reducer 10 <- Reducer 9 (GROUP, 29) + Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 389), Map 12 (PARTITION-LEVEL SORT, 389), Map 8 (PARTITION-LEVEL SORT, 389) +#### A masked pattern was here #### + Vertices: + Map 11 Map Operator Tree: TableScan alias: catalog_sales filterExpr: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 33239859504 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 33073641728 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 33073641728 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430516591 Data size: 49769630056 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(7,2)) Execution mode: vectorized - Map 7 + Map 12 Map Operator Tree: TableScan alias: date_dim filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_week_seq (type: int), d_day_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: string) Execution mode: vectorized - Map 8 + Map 7 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2001) and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2001) and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_week_seq (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 (_col0 - 53) (type: int) Execution mode: vectorized - Map 9 + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: web_sales filterExpr: ws_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 16700140548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ws_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 16695988328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 16695988328 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430516591 Data size: 49769630056 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(7,2)) Execution mode: vectorized Reducer 10 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 13152 Data size: 10363776 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 13 + Statistics: Num rows: 652 Data size: 513776 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 (_col0 - 53) (type: int) + Reducer 9 Reduce Operator Tree: Join Operator condition map: @@ -300,54 +271,92 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col4 - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430516591 Data size: 88948489697 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), CASE WHEN ((_col4 = 'Sunday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Monday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Tuesday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Wednesday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Thursday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Friday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Saturday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430516591 Data size: 88948489697 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4576896 Data size: 3606594048 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4576896 Data size: 3606594048 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) - Reducer 11 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 389), Map 5 (PARTITION-LEVEL SORT, 389), Map 6 (PARTITION-LEVEL SORT, 389) + Reducer 3 <- Reducer 2 (GROUP, 29) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: ws_sold_date_sk is not null (type: boolean) + Statistics: Num rows: 144002668 Data size: 16700140548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ws_sold_date_sk is not null (type: boolean) + Statistics: Num rows: 143966864 Data size: 16695988328 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 143966864 Data size: 16695988328 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 430516591 Data size: 49769630056 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(7,2)) + Execution mode: vectorized + Map 5 + Map Operator Tree: + TableScan + alias: catalog_sales + filterExpr: cs_sold_date_sk is not null (type: boolean) + Statistics: Num rows: 287989836 Data size: 33239859504 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cs_sold_date_sk is not null (type: boolean) + Statistics: Num rows: 286549727 Data size: 33073641728 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 286549727 Data size: 33073641728 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 430516591 Data size: 49769630056 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(7,2)) + Execution mode: vectorized + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_week_seq (type: int), d_day_name (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col2 (type: string) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 237595882 Data size: 32218894638 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 237595882 Data size: 32218894638 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) - Reducer 12 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 261355475 Data size: 35440784869 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (_col0 - 53) (type: int) - sort order: + - Map-reduce partition columns: (_col0 - 53) (type: int) - Statistics: Num rows: 261355475 Data size: 35440784869 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) Reducer 2 Reduce Operator Tree: Join Operator @@ -357,69 +366,66 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col4 - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430516591 Data size: 88948489697 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), CASE WHEN ((_col4 = 'Sunday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Monday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Tuesday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Wednesday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Thursday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Friday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col4 = 'Saturday')) THEN (_col1) ELSE (null) END (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430516591 Data size: 88948489697 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4576896 Data size: 3606594048 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4576896 Data size: 3606594048 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) Reducer 3 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 237595882 Data size: 32218894638 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 237595882 Data size: 32218894638 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) + Statistics: Num rows: 13152 Data size: 10363776 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 (_col0 - 53) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + input vertices: + 1 Map 7 + 2 Reducer 10 + Statistics: Num rows: 3602 Data size: 5662344 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), round((_col1 / _col11), 2) (type: decimal(20,2)), round((_col2 / _col12), 2) (type: decimal(20,2)), round((_col3 / _col13), 2) (type: decimal(20,2)), round((_col4 / _col14), 2) (type: decimal(20,2)), round((_col5 / _col15), 2) (type: decimal(20,2)), round((_col6 / _col16), 2) (type: decimal(20,2)), round((_col7 / _col17), 2) (type: decimal(20,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 3602 Data size: 2838376 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 3602 Data size: 2838376 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(20,2)), _col2 (type: decimal(20,2)), _col3 (type: decimal(20,2)), _col4 (type: decimal(20,2)), _col5 (type: decimal(20,2)), _col6 (type: decimal(20,2)), _col7 (type: decimal(20,2)) Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 (_col0 - 53) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 574982057 Data size: 77969728401 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), round((_col1 / _col11), 2) (type: decimal(20,2)), round((_col2 / _col12), 2) (type: decimal(20,2)), round((_col3 / _col13), 2) (type: decimal(20,2)), round((_col4 / _col14), 2) (type: decimal(20,2)), round((_col5 / _col15), 2) (type: decimal(20,2)), round((_col6 / _col16), 2) (type: decimal(20,2)), round((_col7 / _col17), 2) (type: decimal(20,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 574982057 Data size: 77969728401 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 574982057 Data size: 77969728401 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(20,2)), _col2 (type: decimal(20,2)), _col3 (type: decimal(20,2)), _col4 (type: decimal(20,2)), _col5 (type: decimal(20,2)), _col6 (type: decimal(20,2)), _col7 (type: decimal(20,2)) - Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: decimal(20,2)), VALUE._col1 (type: decimal(20,2)), VALUE._col2 (type: decimal(20,2)), VALUE._col3 (type: decimal(20,2)), VALUE._col4 (type: decimal(20,2)), VALUE._col5 (type: decimal(20,2)), VALUE._col6 (type: decimal(20,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 574982057 Data size: 77969728401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3602 Data size: 2838376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 574982057 Data size: 77969728401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3602 Data size: 2838376 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query20.q.out b/ql/src/test/results/clientpositive/perf/spark/query20.q.out index 86e0e725e5..8ac75a5ea0 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query20.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query20.q.out @@ -69,14 +69,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -88,9 +88,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 341), Map 7 (PARTITION-LEVEL SORT, 341) - Reducer 3 <- Reducer 2 (GROUP, 369) - Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 185) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 29), Map 7 (PARTITION-LEVEL SORT, 29) + Reducer 3 <- Reducer 2 (GROUP, 52) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 52) Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -99,14 +99,14 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 34391818848 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 34219840636 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 34219840636 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -116,12 +116,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 6 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31836679 Data size: 3532659788 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31836679 Data size: 3532659788 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized Local Work: @@ -131,19 +131,19 @@ STAGE PLANS: TableScan alias: item filterExpr: ((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 268753408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string), i_current_price (type: decimal(7,2)), i_class (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)), _col4 (type: string), _col5 (type: string) Execution mode: vectorized Reducer 2 @@ -155,18 +155,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 6429759386 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col10 (type: string), _col9 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 6590154362 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 6590154362 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) Reducer 3 Execution mode: vectorized @@ -176,12 +176,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 6590154362 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 6590154362 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)) Reducer 4 Execution mode: vectorized @@ -189,7 +189,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 6590154362 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -209,15 +209,15 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 6590154362 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 7659827722 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string), _col6 (type: string), _col0 (type: string), _col5 (type: decimal(38,17)) sort order: +++++ - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 7659827722 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(7,2)), _col4 (type: decimal(17,2)) Reducer 5 @@ -226,13 +226,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(7,2)), VALUE._col1 (type: decimal(17,2)), KEY.reducesinkkey4 (type: decimal(38,17)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9551005 Data size: 7659827722 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query21.q.out b/ql/src/test/results/clientpositive/perf/spark/query21.q.out index 1673061f27..6ee033a9cb 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query21.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query21.q.out @@ -72,14 +72,14 @@ STAGE PLANS: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -97,14 +97,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -116,8 +116,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 6), Map 6 (PARTITION-LEVEL SORT, 6) - Reducer 3 <- Reducer 2 (GROUP, 7) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 6 (PARTITION-LEVEL SORT, 4) + Reducer 3 <- Reducer 2 (GROUP, 2) Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -126,14 +126,14 @@ STAGE PLANS: TableScan alias: inventory filterExpr: (inv_warehouse_sk is not null and inv_item_sk is not null and inv_date_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -143,12 +143,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col5 input vertices: 1 Map 5 - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4175715 Data size: 435102898 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4175715 Data size: 435102898 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int), _col5 (type: string) Execution mode: vectorized Local Work: @@ -158,19 +158,19 @@ STAGE PLANS: TableScan alias: item filterExpr: (i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 99661408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51333 Data size: 11073480 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51333 Data size: 11073480 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51333 Data size: 11073480 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reducer 2 @@ -184,7 +184,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col5, _col7 - Statistics: Num rows: 45476640 Data size: 718523566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 463966 Data size: 91865272 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -194,22 +194,22 @@ STAGE PLANS: outputColumnNames: _col3, _col5, _col7, _col10 input vertices: 1 Map 7 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 463966 Data size: 136406008 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col10 (type: string), _col7 (type: string), CASE WHEN ((CAST( _col5 AS DATE) < DATE'1998-04-08')) THEN (_col3) ELSE (0) END (type: int), CASE WHEN ((CAST( _col5 AS DATE) >= DATE'1998-04-08')) THEN (_col3) ELSE (0) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 463966 Data size: 136406008 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 231983 Data size: 50108328 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 231983 Data size: 50108328 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reducer 3 Execution mode: vectorized @@ -219,14 +219,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 231983 Data size: 50108328 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col2 > 0L)) THEN ((UDFToDouble(_col3) / UDFToDouble(_col2)) BETWEEN 0.666667D AND 1.5D) ELSE (null) END (type: boolean) - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 115991 Data size: 25054056 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 115991 Data size: 25054056 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: bigint), _col3 (type: bigint) Reducer 4 @@ -235,13 +235,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 115991 Data size: 25054056 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query22.q.out b/ql/src/test/results/clientpositive/perf/spark/query22.q.out index d0970bba16..92bdd48c55 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query22.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query22.q.out @@ -55,14 +55,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -75,14 +75,14 @@ STAGE PLANS: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -94,8 +94,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 11), Map 7 (PARTITION-LEVEL SORT, 11) - Reducer 3 <- Reducer 2 (GROUP, 31) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 7 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 68) Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -104,14 +104,14 @@ STAGE PLANS: TableScan alias: inventory filterExpr: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -121,7 +121,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Map 5 - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4175715 Data size: 42585688 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -131,12 +131,12 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 6 - Statistics: Num rows: 45476640 Data size: 718523566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4175715 Data size: 25882828 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 45476640 Data size: 718523566 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4175715 Data size: 25882828 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int) Execution mode: vectorized Local Work: @@ -146,19 +146,19 @@ STAGE PLANS: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_class (type: string), i_category (type: string), i_product_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) Execution mode: vectorized Reducer 2 @@ -170,18 +170,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col8, _col9, _col10, _col11 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4175715 Data size: 1633533103 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), count(_col3) keys: _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 250121525 Data size: 3951879695 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20878575 Data size: 8622851475 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) - Statistics: Num rows: 250121525 Data size: 3951879695 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20878575 Data size: 8622851475 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: bigint), _col6 (type: bigint) Reducer 3 Execution mode: vectorized @@ -191,16 +191,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 125060762 Data size: 1975939839 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20878575 Data size: 8622851475 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: string), (UDFToDouble(_col5) / _col6) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 125060762 Data size: 1975939839 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20878575 Data size: 8288794275 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: double), _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: +++++ - Statistics: Num rows: 125060762 Data size: 1975939839 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20878575 Data size: 8288794275 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 4 Execution mode: vectorized @@ -208,13 +208,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 125060762 Data size: 1975939839 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20878575 Data size: 8288794275 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 39700 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 39700 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query23.q.out b/ql/src/test/results/clientpositive/perf/spark/query23.q.out index 4ccc2df4b8..2cd7546f00 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query23.q.out @@ -1,5 +1,5 @@ -Warning: Map Join MAPJOIN[285][bigTable=?] in task 'Stage-1:MAPRED' is a cross product -Warning: Map Join MAPJOIN[286][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[367][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[379][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt @@ -103,184 +103,218 @@ from limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3, Stage-5, Stage-7 + Stage-11 depends on stages: Stage-2 + Stage-10 depends on stages: Stage-11 + Stage-9 depends on stages: Stage-10, Stage-12, Stage-14 + Stage-1 depends on stages: Stage-9 + Stage-6 is a root stage + Stage-5 depends on stages: Stage-6 + Stage-8 is a root stage + Stage-7 depends on stages: Stage-8 + Stage-13 is a root stage + Stage-12 depends on stages: Stage-13 + Stage-15 is a root stage + Stage-14 depends on stages: Stage-15 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-4 Spark - Edges: - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 18 (PARTITION-LEVEL SORT, 398) - Reducer 15 <- Map 19 (PARTITION-LEVEL SORT, 975), Reducer 14 (PARTITION-LEVEL SORT, 975) - Reducer 16 <- Reducer 15 (GROUP, 481) - Reducer 17 <- Reducer 16 (GROUP, 1) - Reducer 21 <- Map 20 (PARTITION-LEVEL SORT, 398), Map 25 (PARTITION-LEVEL SORT, 398) - Reducer 22 <- Map 26 (PARTITION-LEVEL SORT, 975), Reducer 21 (PARTITION-LEVEL SORT, 975) - Reducer 23 <- Reducer 22 (GROUP, 481) - Reducer 24 <- Reducer 23 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 13 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 18 + Map 14 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 19 - Map Operator Tree: - TableScan - alias: customer - filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 20 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 13 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68209339028 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 14 + Statistics: Num rows: 18762463 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 25 + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Spark + Edges: + Reducer 11 <- Map 10 (GROUP, 2) + Reducer 12 <- Reducer 11 (GROUP, 1) + Reducer 16 <- Map 15 (GROUP, 2) + Reducer 17 <- Reducer 16 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + filterExpr: (cs_item_sk is not null and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 36684057852 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 285117831 Data size: 36318222704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) + expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int), cs_quantity (type: int), cs_list_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 285117831 Data size: 36318222704 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 2 + Statistics: Num rows: 7751875 Data size: 790075820 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4 + input vertices: + 1 Reducer 5 + Statistics: Num rows: 290 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 10 + Map Operator Tree: + TableScan + alias: customer + filterExpr: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 0 Map 8 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(28,2)) Execution mode: vectorized - Map 26 + Local Work: + Map Reduce Local Work + Map 15 Map Operator Tree: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 0 Map 13 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(28,2)) Execution mode: vectorized - Reducer 14 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(28,2)) - Reducer 16 + Local Work: + Map Reduce Local Work + Reducer 11 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -288,21 +322,21 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 17 + Reducer 12 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -311,67 +345,25 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 1 2 - Reducer 21 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - Reducer 22 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(28,2)) - Reducer 23 + Reducer 16 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -379,21 +371,21 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: decimal(28,2)) outputColumnNames: _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(28,2)) - Reducer 24 + Reducer 17 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -402,185 +394,207 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 1 2 - Stage: Stage-3 + Stage: Stage-11 Spark - Edges: - Reducer 43 <- Map 42 (PARTITION-LEVEL SORT, 398), Map 47 (PARTITION-LEVEL SORT, 398) - Reducer 44 <- Map 48 (PARTITION-LEVEL SORT, 975), Reducer 43 (PARTITION-LEVEL SORT, 975) - Reducer 45 <- Reducer 44 (GROUP, 481) - Reducer 46 <- Reducer 45 (GROUP, 1) - Reducer 50 <- Map 49 (PARTITION-LEVEL SORT, 398), Map 54 (PARTITION-LEVEL SORT, 398) - Reducer 51 <- Map 55 (PARTITION-LEVEL SORT, 975), Reducer 50 (PARTITION-LEVEL SORT, 975) - Reducer 52 <- Reducer 51 (GROUP, 481) - Reducer 53 <- Reducer 52 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 42 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 47 + Map 36 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 48 - Map Operator Tree: - TableScan - alias: customer - filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 49 + Local Work: + Map Reduce Local Work + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 35 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68209339028 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 36 + Statistics: Num rows: 18762463 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 54 + Local Work: + Map Reduce Local Work + + Stage: Stage-9 + Spark + Edges: + Reducer 33 <- Map 32 (GROUP, 2) + Reducer 34 <- Reducer 33 (GROUP, 1) + Reducer 38 <- Map 37 (GROUP, 2) + Reducer 39 <- Reducer 38 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 23 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + filterExpr: (ws_item_sk is not null and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 18427882036 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143930993 Data size: 18418709868 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_customer_sk (type: int), ws_quantity (type: int), ws_list_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 143930993 Data size: 18418709868 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 24 + Statistics: Num rows: 3941102 Data size: 484382552 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4 + input vertices: + 1 Reducer 27 + Statistics: Num rows: 148 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 32 + Map Operator Tree: + TableScan + alias: customer + filterExpr: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 0 Map 30 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(28,2)) Execution mode: vectorized - Map 55 + Local Work: + Map Reduce Local Work + Map 37 Map Operator Tree: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 43 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - Reducer 44 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(28,2)) - Reducer 45 + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 0 Map 35 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 18762463 Data size: 75049968 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(28,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 33 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -588,21 +602,21 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 46 + Reducer 34 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -611,67 +625,25 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 1 2 - Reducer 50 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - Reducer 51 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: int), (CAST( _col2 AS decimal(10,0)) * _col3) (type: decimal(18,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(28,2)) - Reducer 52 + Reducer 38 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -679,21 +651,21 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: decimal(28,2)) outputColumnNames: _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11859 Data size: 1375644 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(28,2)) - Reducer 53 + Reducer 39 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -702,7 +674,7 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -712,226 +684,52 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Reducer 38 (GROUP PARTITION-LEVEL SORT, 481) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 305), Map 35 (PARTITION-LEVEL SORT, 305) - Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 935), Map 30 (PARTITION-LEVEL SORT, 935) - Reducer 29 <- Reducer 28 (GROUP, 437) - Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 376), Reducer 2 (PARTITION-LEVEL SORT, 376) - Reducer 32 <- Map 31 (PARTITION-LEVEL SORT, 154), Map 35 (PARTITION-LEVEL SORT, 154) - Reducer 33 <- Reducer 10 (PARTITION-LEVEL SORT, 209), Reducer 32 (PARTITION-LEVEL SORT, 209) - Reducer 34 <- Reducer 33 (PARTITION-LEVEL SORT, 543), Reducer 58 (PARTITION-LEVEL SORT, 543) - Reducer 37 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 36 (PARTITION-LEVEL SORT, 398) - Reducer 38 <- Map 12 (PARTITION-LEVEL SORT, 442), Reducer 37 (PARTITION-LEVEL SORT, 442) - Reducer 4 <- Reducer 29 (PARTITION-LEVEL SORT, 727), Reducer 3 (PARTITION-LEVEL SORT, 727) - Reducer 5 <- Reducer 34 (GROUP, 1), Reducer 4 (GROUP, 1) - Reducer 58 <- Reducer 28 (GROUP, 437) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 495), Map 22 (PARTITION-LEVEL SORT, 495) + Reducer 20 <- Reducer 19 (GROUP, 250) + Reducer 21 <- Reducer 20 (GROUP, 1), Reducer 42 (GROUP, 1) + Reducer 42 <- Reducer 19 (GROUP, 250) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: (cs_item_sk is not null and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int), cs_quantity (type: int), cs_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_date (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 12 - Map Operator Tree: - TableScan - alias: item - filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_item_desc (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 27 + Map 18 Map Operator Tree: TableScan alias: store_sales filterExpr: ss_customer_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66009032808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_customer_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550080312 Data size: 63039139860 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_customer_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550080312 Data size: 63039139860 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550080312 Data size: 63039139860 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) Execution mode: vectorized - Map 30 + Map 22 Map Operator Tree: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 31 - Map Operator Tree: - TableScan - alias: web_sales - filterExpr: (ws_item_sk is not null and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_customer_sk (type: int), ws_quantity (type: int), ws_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Execution mode: vectorized - Map 35 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 1) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 1) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 36 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Execution mode: vectorized - Reducer 10 + Statistics: Num rows: 80000000 Data size: 320000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col3 (type: bigint) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col3 > 4L) (type: boolean) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col1 (type: int) - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 58079562 Data size: 5123795819 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 58079562 Data size: 5123795819 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 28 + Reducer 19 Reduce Operator Tree: Join Operator condition map: @@ -940,24 +738,24 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550080312 Data size: 63138137196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), (CAST( _col1 AS decimal(10,0)) * _col2) (type: decimal(18,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550080312 Data size: 63138137196 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275040156 Data size: 31904658096 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 275040156 Data size: 31904658096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(28,2)) - Reducer 29 + Reducer 20 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -967,7 +765,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1351933 Data size: 156824228 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -978,172 +776,59 @@ STAGE PLANS: 2 outputColumnNames: _col1, _col2, _col3 input vertices: - 0 Reducer 17 - 1 Reducer 24 - Statistics: Num rows: 316797606 Data size: 137243150824 Basic stats: COMPLETE Column stats: NONE + 0 Reducer 12 + 1 Reducer 17 + Statistics: Num rows: 1351933 Data size: 308240724 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 > (0.95 * _col1)) (type: boolean) - Statistics: Num rows: 105599202 Data size: 45747716941 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450644 Data size: 102746832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 105599202 Data size: 45747716941 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 105599202 Data size: 45747716941 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 32 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 33 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 34 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col3, _col4 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (CAST( _col3 AS decimal(10,0)) * _col4) (type: decimal(18,2)) - outputColumnNames: _col0 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: decimal(28,2)) - Reducer 37 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string) - Reducer 38 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col5, _col6 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: substr(_col6, 1, 30) (type: string), _col5 (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col1 (type: int), _col0 (type: string), _col2 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint) - Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col3, _col4 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (CAST( _col3 AS decimal(10,0)) * _col4) (type: decimal(18,2)) - outputColumnNames: _col0 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: decimal(28,2)) - Reducer 5 + Statistics: Num rows: 450644 Data size: 1802576 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4 + input vertices: + 0 Map 1 + Statistics: Num rows: 97 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (CAST( _col3 AS decimal(10,0)) * _col4) (type: decimal(18,2)) + outputColumnNames: _col0 + Statistics: Num rows: 97 Data size: 10864 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: decimal(28,2)) + Reducer 21 Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 58 + Reducer 42 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -1153,7 +838,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1351933 Data size: 156824228 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1164,21 +849,484 @@ STAGE PLANS: 2 outputColumnNames: _col1, _col2, _col3 input vertices: - 0 Reducer 46 - 1 Reducer 53 - Statistics: Num rows: 316797606 Data size: 137243150824 Basic stats: COMPLETE Column stats: NONE + 0 Reducer 34 + 1 Reducer 39 + Statistics: Num rows: 1351933 Data size: 308240724 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 > (0.95 * _col1)) (type: boolean) - Statistics: Num rows: 105599202 Data size: 45747716941 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450644 Data size: 102746832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 105599202 Data size: 45747716941 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 105599202 Data size: 45747716941 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 450644 Data size: 1802576 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4 + input vertices: + 0 Map 23 + Statistics: Num rows: 50 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (CAST( _col3 AS decimal(10,0)) * _col4) (type: decimal(18,2)) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: decimal(28,2)) + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 8 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 68209339028 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 18762463 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 2609 Data size: 266118 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2609 Data size: 266118 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark + Edges: + Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 16), Map 7 (PARTITION-LEVEL SORT, 16) + Reducer 5 <- Reducer 4 (GROUP PARTITION-LEVEL SORT, 45) +#### A masked pattern was here #### + Vertices: + Map 2 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 1) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 1) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 3 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 4504288760 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 4301601416 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550076554 Data size: 4301601416 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + input vertices: + 1 Map 6 + Statistics: Num rows: 19646398 Data size: 1925347004 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 19646398 Data size: 1925347004 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: string) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 + Map Operator Tree: + TableScan + alias: item + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_item_desc (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col5, _col6 + Statistics: Num rows: 19646398 Data size: 5540284236 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: substr(_col6, 1, 30) (type: string), _col5 (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 19646398 Data size: 5540284236 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col1 (type: int), _col0 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 19646398 Data size: 5697455420 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 19646398 Data size: 5697455420 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint) + Reducer 5 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 19646398 Data size: 5697455420 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col3 (type: bigint) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 19646398 Data size: 235756776 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col3 > 4L) (type: boolean) + Statistics: Num rows: 6548799 Data size: 78585588 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 6548799 Data size: 78585588 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: int) + mode: complete + outputColumnNames: _col0 + Statistics: Num rows: 2134 Data size: 8536 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + + Stage: Stage-13 + Spark +#### A masked pattern was here #### + Vertices: + Map 31 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2609 Data size: 20872 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-12 + Spark +#### A masked pattern was here #### + Vertices: + Map 30 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 68209339028 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 525327388 Data size: 62209210836 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 31 + Statistics: Num rows: 18762463 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-15 + Spark +#### A masked pattern was here #### + Vertices: + Map 28 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 2609 Data size: 266118 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2609 Data size: 266118 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-14 + Spark + Edges: + Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 16), Map 29 (PARTITION-LEVEL SORT, 16) + Reducer 27 <- Reducer 26 (GROUP PARTITION-LEVEL SORT, 45) +#### A masked pattern was here #### + Vertices: + Map 24 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 1) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 1) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 25 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 4504288760 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 4301601416 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550076554 Data size: 4301601416 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + input vertices: + 1 Map 28 + Statistics: Num rows: 19646398 Data size: 1925347004 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 19646398 Data size: 1925347004 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: string) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 29 + Map Operator Tree: + TableScan + alias: item + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_item_desc (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized + Reducer 26 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col5, _col6 + Statistics: Num rows: 19646398 Data size: 5540284236 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: substr(_col6, 1, 30) (type: string), _col5 (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 19646398 Data size: 5540284236 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col1 (type: int), _col0 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 19646398 Data size: 5697455420 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 19646398 Data size: 5697455420 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint) + Reducer 27 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 19646398 Data size: 5697455420 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col3 (type: bigint) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 19646398 Data size: 235756776 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col3 > 4L) (type: boolean) + Statistics: Num rows: 6548799 Data size: 78585588 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 6548799 Data size: 78585588 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: int) + mode: complete + outputColumnNames: _col0 + Statistics: Num rows: 2134 Data size: 8536 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query24.q.out b/ql/src/test/results/clientpositive/perf/spark/query24.q.out index a34d3e8862..46f460db39 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query24.q.out @@ -109,19 +109,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 19 + Map 18 Map Operator Tree: TableScan alias: store filterExpr: ((s_market_id = 7) and s_store_sk is not null and s_zip is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 461728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_market_id = 7) and s_store_sk is not null and s_zip is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 155 Data size: 42005 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_state (type: string), s_zip (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 155 Data size: 42005 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -133,27 +133,27 @@ STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 975), Map 20 (PARTITION-LEVEL SORT, 975) - Reducer 14 <- Map 21 (PARTITION-LEVEL SORT, 486), Reducer 13 (PARTITION-LEVEL SORT, 486) - Reducer 15 <- Map 22 (PARTITION-LEVEL SORT, 564), Reducer 14 (PARTITION-LEVEL SORT, 564) - Reducer 16 <- Map 23 (PARTITION-LEVEL SORT, 899), Reducer 15 (PARTITION-LEVEL SORT, 899) - Reducer 17 <- Reducer 16 (GROUP, 640) - Reducer 18 <- Reducer 17 (GROUP, 1) + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 1009), Map 19 (PARTITION-LEVEL SORT, 1009) + Reducer 13 <- Map 20 (PARTITION-LEVEL SORT, 1009), Reducer 12 (PARTITION-LEVEL SORT, 1009) + Reducer 14 <- Map 21 (PARTITION-LEVEL SORT, 1009), Reducer 13 (PARTITION-LEVEL SORT, 1009) + Reducer 15 <- Map 22 (PARTITION-LEVEL SORT, 1009), Reducer 14 (PARTITION-LEVEL SORT, 1009) + Reducer 16 <- Reducer 15 (GROUP, 1009) + Reducer 17 <- Reducer 16 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 12 + Map 11 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_ticket_number is not null and ss_item_sk is not null and ss_store_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70617009244 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525333486 Data size: 64405834696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525333486 Data size: 64405834696 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -162,97 +162,97 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col8, _col9 input vertices: - 1 Map 19 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + 1 Map 18 + Statistics: Num rows: 385681992 Data size: 146516613484 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385681992 Data size: 146516613484 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 20 + Map 19 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_birth_country is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_birth_country is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized - Map 21 + Map 20 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 177734916 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 177734916 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_current_price (type: decimal(7,2)), i_size (type: string), i_color (type: string), i_units (type: string), i_manager_id (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 177734916 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 177734916 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(7,2)), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int) Execution mode: vectorized - Map 22 + Map 21 Map Operator Tree: TableScan alias: store_returns filterExpr: (sr_ticket_number is not null and sr_item_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sr_item_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_item_sk (type: int), sr_ticket_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 23 + Map 22 Map Operator Tree: TableScan alias: customer_address filterExpr: (upper(ca_country) is not null and ca_zip is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_zip is not null and upper(ca_country) is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_state (type: string), ca_zip (type: string), ca_country (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), upper(_col2) (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), upper(_col2) (type: string) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized - Reducer 13 + Reducer 12 Reduce Operator Tree: Join Operator condition map: @@ -261,14 +261,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3, _col4, _col6, _col8, _col9, _col11, _col12, _col13 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385681992 Data size: 249973931016 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385681992 Data size: 249973931016 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string) - Reducer 14 + Reducer 13 Reduce Operator Tree: Join Operator condition map: @@ -277,14 +277,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3, _col4, _col6, _col8, _col9, _col11, _col12, _col13, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385681992 Data size: 396918634884 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col3 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 385681992 Data size: 396918634884 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int) - Reducer 15 + Reducer 14 Reduce Operator Tree: Join Operator condition map: @@ -293,14 +293,14 @@ STAGE PLANS: 0 _col0 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col4, _col6, _col8, _col9, _col11, _col12, _col13, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 537799796 Data size: 550210281460 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col9 (type: string), _col13 (type: string) sort order: ++ Map-reduce partition columns: _col9 (type: string), _col13 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 537799796 Data size: 550210281460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int) - Reducer 16 + Reducer 15 Reduce Operator Tree: Join Operator condition map: @@ -309,20 +309,20 @@ STAGE PLANS: 0 _col9 (type: string), _col13 (type: string) 1 _col1 (type: string), upper(_col2) (type: string) outputColumnNames: _col4, _col6, _col8, _col11, _col12, _col15, _col16, _col17, _col18, _col19, _col22 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2121289008973 Data size: 1979159997462981 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4) keys: _col11 (type: string), _col12 (type: string), _col6 (type: string), _col8 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int), _col22 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2121289008973 Data size: 1979162645236725 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: string) sort order: ++++++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: string) - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2121289008973 Data size: 1979162645236725 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col10 (type: decimal(17,2)) - Reducer 17 + Reducer 16 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -330,21 +330,21 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: string), KEY._col8 (type: int), KEY._col9 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2121289008973 Data size: 1979162645236725 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col10 (type: decimal(17,2)) outputColumnNames: _col10 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2121289008973 Data size: 1979162645236725 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col10), count(_col10) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(27,2)), _col1 (type: bigint) - Reducer 18 + Reducer 17 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -353,11 +353,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (0.05 * (_col0 / _col1)) (type: decimal(38,12)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -367,19 +367,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 6 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_color = 'orchid') and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 177734916 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_color = 'orchid') and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 7000 Data size: 2693032 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_current_price (type: decimal(7,2)), i_size (type: string), i_units (type: string), i_manager_id (type: int) + outputColumnNames: _col0, _col1, _col2, _col4, _col5 + Statistics: Num rows: 7000 Data size: 2700032 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store filterExpr: ((s_market_id = 7) and s_store_sk is not null and s_zip is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 461728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_market_id = 7) and s_store_sk is not null and s_zip is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 155 Data size: 42005 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_state (type: string), s_zip (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 155 Data size: 42005 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -391,11 +411,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 400), Map 7 (PARTITION-LEVEL SORT, 400) - Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009) - Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 564), Reducer 3 (PARTITION-LEVEL SORT, 564) - Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 899), Reducer 4 (PARTITION-LEVEL SORT, 899) - Reducer 6 <- Reducer 5 (GROUP PARTITION-LEVEL SORT, 640) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 450), Map 8 (PARTITION-LEVEL SORT, 450) + Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 400), Reducer 2 (PARTITION-LEVEL SORT, 400) + Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 745), Reducer 3 (PARTITION-LEVEL SORT, 745) + Reducer 5 <- Reducer 4 (GROUP PARTITION-LEVEL SORT, 1009) #### A masked pattern was here #### Vertices: Map 1 @@ -403,129 +422,103 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_ticket_number is not null and ss_item_sk is not null and ss_store_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70617009244 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525333486 Data size: 64405834696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Statistics: Num rows: 525333486 Data size: 64405834696 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6, _col7, _col9, _col10 + input vertices: + 1 Map 6 + Statistics: Num rows: 76612563 Data size: 29340422980 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15 + input vertices: + 1 Map 7 + Statistics: Num rows: 56246341 Data size: 35448946151 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 56246341 Data size: 35448946151 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col15 (type: string) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 10 - Map Operator Tree: - TableScan - alias: store_returns - filterExpr: (sr_ticket_number is not null and sr_item_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sr_item_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: sr_item_sk (type: int), sr_ticket_number (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 11 Map Operator Tree: TableScan alias: customer_address filterExpr: (upper(ca_country) is not null and ca_zip is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_zip is not null and upper(ca_country) is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_state (type: string), ca_zip (type: string), ca_country (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), upper(_col2) (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), upper(_col2) (type: string) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 10880000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized - Map 7 + Map 8 Map Operator Tree: TableScan - alias: item - filterExpr: ((i_color = 'orchid') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: customer + filterExpr: (c_customer_sk is not null and c_birth_country is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((i_color = 'orchid') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + predicate: (c_birth_country is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int), i_current_price (type: decimal(7,2)), i_size (type: string), i_units (type: string), i_manager_id (type: int) - outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(7,2)), _col2 (type: string), _col4 (type: string), _col5 (type: int) + Statistics: Num rows: 80000000 Data size: 22080000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized Map 9 Map Operator Tree: TableScan - alias: customer - filterExpr: (c_customer_sk is not null and c_birth_country is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + alias: store_returns + filterExpr: (sr_ticket_number is not null and sr_item_sk is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (c_birth_country is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + predicate: (sr_item_sk is not null and sr_ticket_number is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + expressions: sr_item_sk (type: int), sr_ticket_number (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 2 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6, _col7, _col9, _col10 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col15 (type: string) - Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -534,14 +527,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3, _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56246341 Data size: 50617509215 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col3 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56246341 Data size: 50617509215 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col15 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string) - Reducer 4 + Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -550,14 +543,14 @@ STAGE PLANS: 0 _col0 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 92733777 Data size: 84429240891 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col15 (type: string), _col19 (type: string) sort order: ++ Map-reduce partition columns: _col15 (type: string), _col19 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 92733777 Data size: 84429240891 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col17 (type: string), _col18 (type: string) - Reducer 5 + Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -566,20 +559,20 @@ STAGE PLANS: 0 _col15 (type: string), _col19 (type: string) 1 _col1 (type: string), upper(_col2) (type: string) outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col17, _col18, _col22 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365777643230 Data size: 308713683110408 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4) keys: _col17 (type: string), _col18 (type: string), _col12 (type: string), _col22 (type: string), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col14 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365777643230 Data size: 308716330884152 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string) sort order: +++++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365777643230 Data size: 308716330884152 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col9 (type: decimal(17,2)) - Reducer 6 + Reducer 5 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -589,21 +582,21 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: int), KEY._col8 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365777643230 Data size: 308716330884152 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col9 (type: decimal(17,2)) outputColumnNames: _col1, _col2, _col7, _col9 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365777643230 Data size: 308716330884152 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col9) keys: _col1 (type: string), _col2 (type: string), _col7 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 231911707 Data size: 20459318134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 235181232 Data size: 89368868160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string), _col3 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 231911707 Data size: 20459318134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 235181232 Data size: 89368868160 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -612,18 +605,18 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4 input vertices: - 1 Reducer 18 - Statistics: Num rows: 231911707 Data size: 74494745865 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 17 + Statistics: Num rows: 235181232 Data size: 115709166144 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 > _col4) (type: boolean) - Statistics: Num rows: 77303902 Data size: 24831581847 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78393744 Data size: 38569722048 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 77303902 Data size: 24831581847 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78393744 Data size: 29789622720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 77303902 Data size: 24831581847 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78393744 Data size: 29789622720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query25.q.out b/ql/src/test/results/clientpositive/perf/spark/query25.q.out index 3d7f402870..0c51cf783c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query25.q.out @@ -96,7 +96,8 @@ STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -104,19 +105,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 14 + Map 13 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_id (type: string), s_store_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -129,19 +130,44 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 10 + Map 6 + Map Operator Tree: + TableScan + alias: d1 + filterExpr: ((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: d3 filterExpr: (d_moy BETWEEN 4 AND 10 and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -150,23 +176,23 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-4 + Stage: Stage-5 Spark #### A masked pattern was here #### Vertices: - Map 12 + Map 11 Map Operator Tree: TableScan alias: d2 filterExpr: (d_moy BETWEEN 4 AND 10 and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -178,12 +204,11 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 806), Reducer 9 (PARTITION-LEVEL SORT, 806) - Reducer 4 <- Map 13 (PARTITION-LEVEL SORT, 486), Reducer 3 (PARTITION-LEVEL SORT, 486) - Reducer 5 <- Reducer 4 (GROUP, 582) - Reducer 6 <- Reducer 5 (SORT, 1) - Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 374), Map 8 (PARTITION-LEVEL SORT, 374) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 716), Reducer 8 (PARTITION-LEVEL SORT, 716) + Reducer 3 <- Map 12 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009) + Reducer 4 <- Reducer 3 (GROUP, 1009) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 8 <- Map 10 (PARTITION-LEVEL SORT, 11), Map 7 (PARTITION-LEVEL SORT, 11) #### A masked pattern was here #### Vertices: Map 1 @@ -191,34 +216,46 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_item_sk is not null and ss_ticket_number is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 72818289192 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501694138 Data size: 63424975100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)) + Statistics: Num rows: 501694138 Data size: 63424975100 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 6 + Statistics: Num rows: 13737330 Data size: 109898760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) + sort order: +++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) + Statistics: Num rows: 13737330 Data size: 109898760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 11 + Local Work: + Map Reduce Local Work + Map 10 Map Operator Tree: TableScan alias: store_returns filterExpr: (sr_customer_sk is not null and sr_item_sk is not null and sr_ticket_number is not null and sr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 7129926688 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53632139 Data size: 6639791380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_customer_sk (type: int), sr_ticket_number (type: int), sr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53632139 Data size: 6639791380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -227,69 +264,50 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4 input vertices: - 1 Map 12 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + 1 Map 11 + Statistics: Num rows: 1928802 Data size: 21548052 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1928802 Data size: 21548052 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 13 + Map 12 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 7 - Map Operator Tree: - TableScan - alias: d1 - filterExpr: ((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 8 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 35699222868 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 35343209100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int), cs_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 35343209100 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -298,34 +316,18 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3 input vertices: - 1 Map 10 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + 1 Map 9 + Statistics: Num rows: 11162699 Data size: 1333824920 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: int), _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11162699 Data size: 1333824920 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: decimal(7,2)) Execution mode: vectorized Local Work: Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) - sort order: +++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col5 (type: decimal(7,2)) - Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -334,14 +336,14 @@ STAGE PLANS: 0 _col1 (type: int), _col2 (type: int), _col4 (type: int) 1 _col8 (type: int), _col9 (type: int), _col10 (type: int) outputColumnNames: _col1, _col3, _col5, _col12, _col20 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 1189949369836 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 1189949369836 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col5 (type: decimal(7,2)), _col12 (type: decimal(7,2)), _col20 (type: decimal(7,2)) - Reducer 4 + Reducer 3 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -352,7 +354,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col5, _col12, _col20, _col25, _col26 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 2159980891596 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -361,22 +363,22 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col5, _col12, _col20, _col25, _col26, _col28, _col29 input vertices: - 1 Map 14 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + 1 Map 13 + Statistics: Num rows: 3464398292 Data size: 2797485126640 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col5), sum(_col20), sum(_col12) keys: _col25 (type: string), _col26 (type: string), _col28 (type: string), _col29 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 2799233819936 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 2799233819936 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -384,31 +386,31 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 2799233819936 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 2799233819936 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2)), VALUE._col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3464398292 Data size: 2799233819936 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 + Reducer 8 Reduce Operator Tree: Join Operator condition map: @@ -417,12 +419,12 @@ STAGE PLANS: 0 _col2 (type: int), _col1 (type: int) 1 _col1 (type: int), _col2 (type: int) outputColumnNames: _col3, _col8, _col9, _col10, _col11 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 388471350 Data size: 91461615204 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int) sort order: +++ Map-reduce partition columns: _col8 (type: int), _col9 (type: int), _col10 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 388471350 Data size: 91461615204 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: decimal(7,2)), _col11 (type: decimal(7,2)) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/perf/spark/query26.q.out b/ql/src/test/results/clientpositive/perf/spark/query26.q.out index 1ef5753de5..295725868a 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query26.q.out @@ -39,28 +39,69 @@ select i_item_id, limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 2 + Map Operator Tree: + TableScan + alias: customer_demographics + filterExpr: ((cd_gender = 'F') and (cd_marital_status = 'W') and (cd_education_status = 'Primary') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1861800 Data size: 498962400 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 14776 Data size: 3959968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14776 Data size: 3915640 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 3 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 4 Map Operator Tree: TableScan alias: promotion filterExpr: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 400200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 400200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_promo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 400200 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -69,14 +110,8 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 7 (PARTITION-LEVEL SORT, 306) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 336), Reducer 2 (PARTITION-LEVEL SORT, 336) - Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 411), Reducer 3 (PARTITION-LEVEL SORT, 411) - Reducer 5 <- Reducer 4 (GROUP, 447) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -84,147 +119,99 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_bill_cdemo_sk is not null and cs_sold_date_sk is not null and cs_item_sk is not null and cs_promo_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 102017575900 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283691050 Data size: 100494773080 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_cdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_quantity (type: int), cs_list_price (type: decimal(7,2)), cs_sales_price (type: decimal(7,2)), cs_coupon_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Statistics: Num rows: 283691050 Data size: 100494773080 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 2 + Statistics: Num rows: 2283326 Data size: 310164420 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 3 + Statistics: Num rows: 809521 Data size: 3238428 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 4 + Statistics: Num rows: 809521 Data size: 3238424 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 6 <- Map 5 (GROUP, 2) + Reducer 7 <- Reducer 6 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 5 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: customer_demographics - filterExpr: ((cd_gender = 'F') and (cd_marital_status = 'W') and (cd_education_status = 'Primary') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 8 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5, _col6, _col7, _col18 + input vertices: + 0 Map 1 + Statistics: Num rows: 809521 Data size: 80952440 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col4), count(_col4), sum(_col5), count(_col5), sum(_col7), count(_col7), sum(_col6), count(_col6) + keys: _col18 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 310774 Data size: 147928424 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 310774 Data size: 147928424 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(17,2)), _col8 (type: bigint) Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Reducer 3 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col5, _col6, _col7 - input vertices: - 1 Map 9 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col5, _col6, _col7, _col18 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col4), count(_col4), sum(_col5), count(_col5), sum(_col7), count(_col7), sum(_col6), count(_col6) - keys: _col18 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(17,2)), _col8 (type: bigint) - Reducer 5 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -232,30 +219,30 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 147928424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (UDFToDouble(_col1) / _col2) (type: double), (_col3 / _col4) (type: decimal(37,22)), (_col5 / _col6) (type: decimal(37,22)), (_col7 / _col8) (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 137983656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 137983656 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double), _col2 (type: decimal(37,22)), _col3 (type: decimal(37,22)), _col4 (type: decimal(37,22)) - Reducer 6 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double), VALUE._col1 (type: decimal(37,22)), VALUE._col2 (type: decimal(37,22)), VALUE._col3 (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 137983656 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 44400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 44400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query27.q.out b/ql/src/test/results/clientpositive/perf/spark/query27.q.out index 8be0ca9714..335f9685cc 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query27.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query27.q.out @@ -52,19 +52,59 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 5 + Map Operator Tree: + TableScan + alias: customer_demographics + filterExpr: ((cd_gender = 'M') and (cd_marital_status = 'U') and (cd_education_status = '2 yr Degree') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1861800 Data size: 498962400 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 14776 Data size: 3959968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14776 Data size: 3974744 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store filterExpr: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 209 Data size: 18810 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 209 Data size: 18810 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -76,11 +116,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438) - Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 534), Reducer 3 (PARTITION-LEVEL SORT, 534) - Reducer 5 <- Reducer 4 (GROUP, 1009) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 8 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 20) + Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -88,124 +126,74 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 195930972692 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_cdemo_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501690006 Data size: 170655131692 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_cdemo_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_list_price (type: decimal(7,2)), ss_sales_price (type: decimal(7,2)), ss_coupon_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Statistics: Num rows: 501690006 Data size: 170655131692 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 5 + Statistics: Num rows: 4037920 Data size: 16152028 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 6 + Statistics: Num rows: 1441779 Data size: 5767460 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col4, _col5, _col6, _col7, _col15 + input vertices: + 1 Map 7 + Statistics: Num rows: 1427275 Data size: 128455090 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1427275 Data size: 128455090 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col15 (type: string) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: customer_demographics - filterExpr: ((cd_gender = 'M') and (cd_marital_status = 'U') and (cd_education_status = '2 yr Degree') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 8 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Reducer 3 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col5, _col6, _col7, _col15 - input vertices: - 1 Map 9 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col15 (type: string) - Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -214,25 +202,25 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col4, _col5, _col6, _col7, _col15, _col17 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1427275 Data size: 265473490 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col17 (type: string), _col15 (type: string), _col4 (type: int), _col5 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col6 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1427275 Data size: 265473490 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2), sum(_col3), count(_col3), sum(_col4), count(_col4), sum(_col5), count(_col5) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2529945843 Data size: 223192556868 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4281825 Data size: 2440640250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2529945843 Data size: 223192556868 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4281825 Data size: 2440640250 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(17,2)), _col8 (type: bigint), _col9 (type: decimal(17,2)), _col10 (type: bigint) - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -240,30 +228,30 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4281825 Data size: 2440640250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), grouping(_col2, 0) (type: bigint), (UDFToDouble(_col3) / _col4) (type: double), (_col5 / _col6) (type: decimal(37,22)), (_col7 / _col8) (type: decimal(37,22)), (_col9 / _col10) (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4281825 Data size: 2303621850 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4281825 Data size: 2303621850 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: bigint), _col3 (type: double), _col4 (type: decimal(37,22)), _col5 (type: decimal(37,22)), _col6 (type: decimal(37,22)) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: double), VALUE._col2 (type: decimal(37,22)), VALUE._col3 (type: decimal(37,22)), VALUE._col4 (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4281825 Data size: 2303621850 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 53800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 53800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query28.q.out b/ql/src/test/results/clientpositive/perf/spark/query28.q.out index b437829c70..49f8bb47d2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query28.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query28.q.out @@ -112,15 +112,15 @@ STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 11 <- Map 10 (GROUP, 15) + Reducer 11 <- Map 10 (GROUP, 19) Reducer 12 <- Reducer 11 (GROUP, 1) - Reducer 14 <- Map 13 (GROUP, 15) + Reducer 14 <- Map 13 (GROUP, 19) Reducer 15 <- Reducer 14 (GROUP, 1) - Reducer 17 <- Map 16 (GROUP, 15) + Reducer 17 <- Map 16 (GROUP, 19) Reducer 18 <- Reducer 17 (GROUP, 1) - Reducer 5 <- Map 4 (GROUP, 15) + Reducer 5 <- Map 4 (GROUP, 19) Reducer 6 <- Reducer 5 (GROUP, 1) - Reducer 8 <- Map 7 (GROUP, 15) + Reducer 8 <- Map 7 (GROUP, 19) Reducer 9 <- Reducer 8 (GROUP, 1) #### A masked pattern was here #### Vertices: @@ -129,25 +129,25 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_quantity BETWEEN 16 AND 20 and (ss_list_price BETWEEN 142 AND 152 or ss_coupon_amt BETWEEN 3054 AND 4054 or ss_wholesale_cost BETWEEN 80 AND 100)) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 187026142228 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_list_price BETWEEN 142 AND 152 or ss_coupon_amt BETWEEN 3054 AND 4054 or ss_wholesale_cost BETWEEN 80 AND 100) and ss_quantity BETWEEN 16 AND 20) (type: boolean) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_list_price (type: decimal(7,2)) outputColumnNames: ss_list_price - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_list_price), count(ss_list_price) keys: ss_list_price (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(7,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(7,2)) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Map 13 @@ -155,25 +155,25 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_quantity BETWEEN 11 AND 15 and (ss_list_price BETWEEN 66 AND 76 or ss_coupon_amt BETWEEN 920 AND 1920 or ss_wholesale_cost BETWEEN 4 AND 24)) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 187026142228 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_list_price BETWEEN 66 AND 76 or ss_coupon_amt BETWEEN 920 AND 1920 or ss_wholesale_cost BETWEEN 4 AND 24) and ss_quantity BETWEEN 11 AND 15) (type: boolean) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_list_price (type: decimal(7,2)) outputColumnNames: ss_list_price - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_list_price), count(ss_list_price) keys: ss_list_price (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(7,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(7,2)) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Map 16 @@ -181,25 +181,25 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_quantity BETWEEN 6 AND 10 and (ss_list_price BETWEEN 91 AND 101 or ss_coupon_amt BETWEEN 1430 AND 2430 or ss_wholesale_cost BETWEEN 32 AND 52)) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 187026142228 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_list_price BETWEEN 91 AND 101 or ss_coupon_amt BETWEEN 1430 AND 2430 or ss_wholesale_cost BETWEEN 32 AND 52) and ss_quantity BETWEEN 6 AND 10) (type: boolean) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_list_price (type: decimal(7,2)) outputColumnNames: ss_list_price - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_list_price), count(ss_list_price) keys: ss_list_price (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(7,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(7,2)) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Map 4 @@ -207,25 +207,25 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_quantity BETWEEN 26 AND 30 and (ss_list_price BETWEEN 28 AND 38 or ss_coupon_amt BETWEEN 2513 AND 3513 or ss_wholesale_cost BETWEEN 42 AND 62)) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 187026142228 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_list_price BETWEEN 28 AND 38 or ss_coupon_amt BETWEEN 2513 AND 3513 or ss_wholesale_cost BETWEEN 42 AND 62) and ss_quantity BETWEEN 26 AND 30) (type: boolean) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_list_price (type: decimal(7,2)) outputColumnNames: ss_list_price - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_list_price), count(ss_list_price) keys: ss_list_price (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(7,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(7,2)) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Map 7 @@ -233,25 +233,25 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_quantity BETWEEN 21 AND 25 and (ss_list_price BETWEEN 135 AND 145 or ss_coupon_amt BETWEEN 14180 AND 15180 or ss_wholesale_cost BETWEEN 38 AND 58)) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 187026142228 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_list_price BETWEEN 135 AND 145 or ss_coupon_amt BETWEEN 14180 AND 15180 or ss_wholesale_cost BETWEEN 38 AND 58) and ss_quantity BETWEEN 21 AND 25) (type: boolean) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_list_price (type: decimal(7,2)) outputColumnNames: ss_list_price - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21333171 Data size: 6926894260 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_list_price), count(ss_list_price) keys: ss_list_price (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(7,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(7,2)) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Reducer 11 @@ -262,15 +262,15 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(7,2)) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col2), count(_col0) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint) Reducer 12 Execution mode: vectorized @@ -281,11 +281,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -302,15 +302,15 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(7,2)) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col2), count(_col0) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint) Reducer 15 Execution mode: vectorized @@ -321,11 +321,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -342,15 +342,15 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(7,2)) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col2), count(_col0) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint) Reducer 18 Execution mode: vectorized @@ -361,11 +361,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -382,15 +382,15 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(7,2)) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col2), count(_col0) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint) Reducer 6 Execution mode: vectorized @@ -401,11 +401,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -422,15 +422,15 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(7,2)) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10666585 Data size: 2420893656 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col2), count(_col0) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint) Reducer 9 Execution mode: vectorized @@ -441,11 +441,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -458,7 +458,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 15) + Reducer 2 <- Map 1 (GROUP, 23) Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: @@ -467,25 +467,25 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_quantity BETWEEN 0 AND 5 and (ss_list_price BETWEEN 11 AND 21 or ss_coupon_amt BETWEEN 460 AND 1460 or ss_wholesale_cost BETWEEN 14 AND 34)) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 187026142228 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_list_price BETWEEN 11 AND 21 or ss_coupon_amt BETWEEN 460 AND 1460 or ss_wholesale_cost BETWEEN 14 AND 34) and ss_quantity BETWEEN 0 AND 5) (type: boolean) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999513 Data size: 20780682216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_list_price (type: decimal(7,2)) outputColumnNames: ss_list_price - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999513 Data size: 20780682216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_list_price), count(ss_list_price) keys: ss_list_price (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12468667 Data size: 2829895048 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(7,2)) sort order: + Map-reduce partition columns: _col0 (type: decimal(7,2)) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12468667 Data size: 2829895048 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Reducer 2 @@ -496,15 +496,15 @@ STAGE PLANS: keys: KEY._col0 (type: decimal(7,2)) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12468667 Data size: 2829895048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col2), count(_col0) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint) Reducer 3 Execution mode: vectorized @@ -515,11 +515,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -541,17 +541,17 @@ STAGE PLANS: 3 Reducer 12 4 Reducer 15 5 Reducer 18 - Statistics: Num rows: 1 Data size: 1393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint), _col15 (type: decimal(37,22)), _col16 (type: bigint), _col17 (type: bigint), _col12 (type: decimal(37,22)), _col13 (type: bigint), _col14 (type: bigint), _col9 (type: decimal(37,22)), _col10 (type: bigint), _col11 (type: bigint), _col6 (type: decimal(37,22)), _col7 (type: bigint), _col8 (type: bigint), _col3 (type: decimal(37,22)), _col4 (type: bigint), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 1393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 1393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query29.q.out b/ql/src/test/results/clientpositive/perf/spark/query29.q.out index a7347102c1..00c547eff9 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query29.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query29.q.out @@ -93,7 +93,9 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -101,19 +103,44 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 15 + Map 5 + Map Operator Tree: + TableScan + alias: d3 + filterExpr: ((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 1957 Data size: 15656 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1957 Data size: 15656 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 13 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_id (type: string), s_store_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -122,23 +149,48 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-3 + Stage: Stage-4 Spark #### A masked pattern was here #### Vertices: - Map 13 + Map 9 + Map Operator Tree: + TableScan + alias: d1 + filterExpr: ((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 Map Operator Tree: TableScan alias: d2 filterExpr: (d_moy BETWEEN 4 AND 7 and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -150,13 +202,11 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 14 (PARTITION-LEVEL SORT, 486), Reducer 9 (PARTITION-LEVEL SORT, 486) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 6 (PARTITION-LEVEL SORT, 306) - Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 917), Reducer 2 (PARTITION-LEVEL SORT, 917) - Reducer 4 <- Reducer 3 (GROUP, 640) - Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 8 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 476), Reducer 8 (PARTITION-LEVEL SORT, 476) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 66), Reducer 8 (PARTITION-LEVEL SORT, 66) + Reducer 3 <- Reducer 2 (GROUP, 1009) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 7 <- Map 10 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2) + Reducer 8 <- Map 12 (PARTITION-LEVEL SORT, 4), Reducer 7 (PARTITION-LEVEL SORT, 4) #### A masked pattern was here #### Vertices: Map 1 @@ -164,53 +214,46 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 4590562460 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 4544782656 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int), cs_quantity (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) - Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: d1 - filterExpr: ((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 4544782656 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 5 + Statistics: Num rows: 7638375 Data size: 80260844 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 7638375 Data size: 80260844 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + Map 10 Map Operator Tree: TableScan alias: store_returns filterExpr: (sr_customer_sk is not null and sr_item_sk is not null and sr_ticket_number is not null and sr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 1127638720 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53632139 Data size: 1050121008 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_customer_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53632139 Data size: 1050121008 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -219,125 +262,70 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4 input vertices: - 1 Map 13 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + 1 Map 11 + Statistics: Num rows: 1928802 Data size: 15838076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: +++ Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1928802 Data size: 15838076 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 14 + Map 12 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 133056000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 6 - Map Operator Tree: - TableScan - alias: d3 - filterExpr: ((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 7 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_item_sk is not null and ss_ticket_number is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 13409244716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501694138 Data size: 11679497312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int) + Statistics: Num rows: 501694138 Data size: 11679497312 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 9 + Statistics: Num rows: 13737330 Data size: 109898652 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) + sort order: +++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) + Statistics: Num rows: 13737330 Data size: 109898652 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col5 (type: int) Execution mode: vectorized - Reducer 10 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col5, _col10, _col11, _col13, _col18, _col19 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col5, _col10, _col11, _col13, _col18, _col19, _col21, _col22 - input vertices: - 1 Map 15 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col18 (type: string), _col19 (type: string), _col5 (type: int), _col10 (type: int), _col11 (type: int), _col13 (type: int), _col21 (type: string), _col22 (type: string) - outputColumnNames: _col1, _col2, _col8, _col13, _col14, _col16, _col21, _col22 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col14 (type: int), _col13 (type: int) - sort order: ++ - Map-reduce partition columns: _col14 (type: int), _col13 (type: int) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col8 (type: int), _col16 (type: int), _col21 (type: string), _col22 (type: string) Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) - Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -346,21 +334,21 @@ STAGE PLANS: 0 _col1 (type: int), _col2 (type: int) 1 _col14 (type: int), _col13 (type: int) outputColumnNames: _col3, _col7, _col8, _col14, _col22, _col27, _col28 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3389534374 Data size: 1640466475196 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col14), sum(_col22), sum(_col3) keys: _col7 (type: string), _col8 (type: string), _col27 (type: string), _col28 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3389534374 Data size: 1681209049504 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3389534374 Data size: 1681209049504 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint) - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -368,47 +356,31 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3389534374 Data size: 1681209049504 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3389534374 Data size: 1681209049504 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3389534374 Data size: 1681209049504 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 8 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) - sort order: +++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col5 (type: int) - Reducer 9 + Reducer 7 Reduce Operator Tree: Join Operator condition map: @@ -417,13 +389,45 @@ STAGE PLANS: 0 _col1 (type: int), _col2 (type: int), _col4 (type: int) 1 _col1 (type: int), _col2 (type: int), _col3 (type: int) outputColumnNames: _col1, _col3, _col5, _col10, _col11, _col13 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17201109 Data size: 287905228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17201109 Data size: 287905228 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col5 (type: int), _col10 (type: int), _col11 (type: int), _col13 (type: int) + Reducer 8 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col5, _col10, _col11, _col13, _col18, _col19 + Statistics: Num rows: 17201109 Data size: 5104215748 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col10, _col11, _col13, _col18, _col19, _col21, _col22 + input vertices: + 1 Map 13 + Statistics: Num rows: 17201109 Data size: 8324169120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col18 (type: string), _col19 (type: string), _col5 (type: int), _col10 (type: int), _col11 (type: int), _col13 (type: int), _col21 (type: string), _col22 (type: string) + outputColumnNames: _col1, _col2, _col8, _col13, _col14, _col16, _col21, _col22 + Statistics: Num rows: 17201109 Data size: 8324169120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col14 (type: int), _col13 (type: int) + sort order: ++ + Map-reduce partition columns: _col14 (type: int), _col13 (type: int) + Statistics: Num rows: 17201109 Data size: 8324169120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string), _col8 (type: int), _col16 (type: int), _col21 (type: string), _col22 (type: string) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query3.q.out b/ql/src/test/results/clientpositive/perf/spark/query3.q.out index 5604cef7cd..b9bd56d07c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query3.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query3.q.out @@ -39,118 +39,112 @@ select dt.d_year limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 400), Map 6 (PARTITION-LEVEL SORT, 400) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438) - Reducer 4 <- Reducer 3 (GROUP, 481) - Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 6 + Map 4 Map Operator Tree: TableScan alias: item filterExpr: ((i_manufact_id = 436) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 51734844 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manufact_id = 436) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 669 Data size: 74920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand_id (type: int), i_brand (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 669 Data size: 74924 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: dt filterExpr: ((d_moy = 12) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 12) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5619 Data size: 67428 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_year (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 5619 Data size: 67428 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66112867736 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4, _col5 + input vertices: + 1 Map 4 + Statistics: Num rows: 7666836 Data size: 797351056 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4, _col5, _col8 + input vertices: + 1 Map 5 + Statistics: Num rows: 589741 Data size: 63692136 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col8 (type: int), _col4 (type: int), _col5 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 274400 Data size: 60368000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 274400 Data size: 60368000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int), _col5 (type: string) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col5, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col8 (type: int), _col4 (type: int), _col5 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -158,26 +152,26 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 274400 Data size: 60368000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col3 (type: decimal(17,2)), _col1 (type: int) sort order: +-+ - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 274400 Data size: 60368000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: string) - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 274400 Data size: 60368000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query30.q.out b/ql/src/test/results/clientpositive/perf/spark/query30.q.out index 46c62e821f..c6b14f28d1 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query30.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query30.q.out @@ -59,141 +59,222 @@ with customer_total_return as limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 10 <- Reducer 16 (PARTITION-LEVEL SORT, 262), Reducer 9 (PARTITION-LEVEL SORT, 262) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 11), Map 17 (PARTITION-LEVEL SORT, 11) - Reducer 15 <- Map 18 (PARTITION-LEVEL SORT, 329), Reducer 14 (PARTITION-LEVEL SORT, 329) - Reducer 16 <- Reducer 15 (GROUP PARTITION-LEVEL SORT, 349) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 697), Map 5 (PARTITION-LEVEL SORT, 697) - Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 656), Reducer 2 (PARTITION-LEVEL SORT, 656) - Reducer 4 <- Reducer 3 (SORT, 1) - Reducer 7 <- Map 11 (PARTITION-LEVEL SORT, 11), Map 6 (PARTITION-LEVEL SORT, 11) - Reducer 8 <- Map 12 (PARTITION-LEVEL SORT, 329), Reducer 7 (PARTITION-LEVEL SORT, 329) - Reducer 9 <- Reducer 8 (GROUP, 349) #### A masked pattern was here #### Vertices: - Map 1 + Map 14 Map Operator Tree: TableScan - alias: customer - filterExpr: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: c_customer_sk (type: int), c_customer_id (type: string), c_current_addr_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_day (type: int), c_birth_month (type: int), c_birth_year (type: int), c_birth_country (type: string), c_login (type: string), c_email_address (type: string), c_last_review_date (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Spark + Edges: + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 32), Map 15 (PARTITION-LEVEL SORT, 32) + Reducer 13 <- Reducer 12 (GROUP PARTITION-LEVEL SORT, 4) +#### A masked pattern was here #### + Vertices: Map 11 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: web_returns + filterExpr: (wr_returned_date_sk is not null and wr_returning_addr_sk is not null) (type: boolean) + Statistics: Num rows: 14398467 Data size: 1705036196 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: (wr_returned_date_sk is not null and wr_returning_addr_sk is not null) (type: boolean) + Statistics: Num rows: 13130761 Data size: 1554917120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + expressions: wr_returned_date_sk (type: int), wr_returning_customer_sk (type: int), wr_returning_addr_sk (type: int), wr_return_amt (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 13130761 Data size: 1554917120 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 14 + Statistics: Num rows: 3923529 Data size: 399892396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 3923529 Data size: 399892396 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + Map 15 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 13 - Map Operator Tree: - TableScan - alias: web_returns - filterExpr: (wr_returned_date_sk is not null and wr_returning_addr_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (wr_returned_date_sk is not null and wr_returning_addr_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: wr_returned_date_sk (type: int), wr_returning_customer_sk (type: int), wr_returning_addr_sk (type: int), wr_return_amt (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 12 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col7 + Statistics: Num rows: 3923529 Data size: 723986502 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col7 (type: string), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1961764 Data size: 395093240 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1961764 Data size: 395093240 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) + Reducer 13 Execution mode: vectorized - Map 17 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1961764 Data size: 395093240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1961764 Data size: 395093240 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), count(_col2) + keys: _col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ((_col1 / _col2) * 1.2) (type: decimal(38,11)), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 1188 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 532), Map 5 (PARTITION-LEVEL SORT, 532) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 12), Reducer 8 (PARTITION-LEVEL SORT, 12) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 7 <- Map 10 (PARTITION-LEVEL SORT, 32), Map 6 (PARTITION-LEVEL SORT, 32) + Reducer 8 <- Reducer 7 (GROUP, 3) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: customer + filterExpr: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 67966407276 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 67966407276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int), c_customer_id (type: string), c_current_addr_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_day (type: int), c_birth_month (type: int), c_birth_year (type: int), c_birth_country (type: string), c_login (type: string), c_email_address (type: string), c_last_review_date (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Statistics: Num rows: 80000000 Data size: 67966407276 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 80000000 Data size: 67966407276 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string) Execution mode: vectorized - Map 18 + Map 10 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 5 @@ -201,130 +282,52 @@ STAGE PLANS: TableScan alias: customer_address filterExpr: ((ca_state = 'IL') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_state = 'IL') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: web_returns filterExpr: (wr_returned_date_sk is not null and wr_returning_addr_sk is not null and wr_returning_customer_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1705036196 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (wr_returned_date_sk is not null and wr_returning_addr_sk is not null and wr_returning_customer_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12539215 Data size: 1484867476 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_returned_date_sk (type: int), wr_returning_customer_sk (type: int), wr_returning_addr_sk (type: int), wr_return_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 24200000 Data size: 24560094211 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 > _col3) (type: boolean) - Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: decimal(17,2)) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 14 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col7 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col7 (type: string), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 16 + Statistics: Num rows: 12539215 Data size: 1484867476 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 3746772 Data size: 381877020 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 3746772 Data size: 381877020 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: decimal(17,2)) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), count(_col2) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ((_col1 / _col2) * 1.2) (type: decimal(38,11)), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(38,11)) + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -334,12 +337,12 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1568628 Data size: 1308235764 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1568628 Data size: 1308235764 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string) Reducer 3 Reduce Operator Tree: @@ -350,15 +353,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col18 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 601923 Data size: 567011478 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col18 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 601923 Data size: 567011478 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: decimal(17,2)) sort order: +++++++++++++ - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 601923 Data size: 567011478 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 4 Execution mode: vectorized @@ -366,34 +369,18 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: string), KEY.reducesinkkey10 (type: string), KEY.reducesinkkey11 (type: string), KEY.reducesinkkey12 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 601923 Data size: 567011478 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 94212 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 94212 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 7 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 8 Reduce Operator Tree: Join Operator condition map: @@ -402,38 +389,57 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col7 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3746772 Data size: 691370520 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col7 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1873386 Data size: 377294180 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1873386 Data size: 377294180 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)) - Reducer 9 + Reducer 8 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1841880 Data size: 370948968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: string), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + Statistics: Num rows: 1841880 Data size: 370948968 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2, _col3 + input vertices: + 1 Reducer 13 + Statistics: Num rows: 1841880 Data size: 418837848 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col2 > _col3) (type: boolean) + Statistics: Num rows: 613960 Data size: 139612620 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 613960 Data size: 139612620 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 613960 Data size: 139612620 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query31.q.out b/ql/src/test/results/clientpositive/perf/spark/query31.q.out index 81deedeb99..e8480e7704 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query31.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query31.q.out @@ -101,390 +101,211 @@ with ss as order by ss1.d_year POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4, Stage-5, Stage-8 + Stage-9 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-9 + Stage-4 is a root stage + Stage-6 is a root stage + Stage-5 depends on stages: Stage-6, Stage-7 + Stage-7 is a root stage + Stage-8 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 754), Reducer 9 (PARTITION-LEVEL SORT, 754) - Reducer 11 <- Reducer 10 (GROUP, 481) - Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 398), Map 18 (PARTITION-LEVEL SORT, 398) - Reducer 16 <- Map 19 (PARTITION-LEVEL SORT, 754), Reducer 15 (PARTITION-LEVEL SORT, 754) - Reducer 17 <- Reducer 16 (GROUP, 481) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 6 (PARTITION-LEVEL SORT, 398) - Reducer 21 <- Map 20 (PARTITION-LEVEL SORT, 154), Map 25 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Map 26 (PARTITION-LEVEL SORT, 486), Reducer 21 (PARTITION-LEVEL SORT, 486) - Reducer 23 <- Reducer 22 (GROUP, 186) - Reducer 24 <- Reducer 23 (PARTITION-LEVEL SORT, 278), Reducer 30 (PARTITION-LEVEL SORT, 278), Reducer 36 (PARTITION-LEVEL SORT, 278) - Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 154), Map 31 (PARTITION-LEVEL SORT, 154) - Reducer 29 <- Map 32 (PARTITION-LEVEL SORT, 486), Reducer 28 (PARTITION-LEVEL SORT, 486) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 754), Reducer 2 (PARTITION-LEVEL SORT, 754) - Reducer 30 <- Reducer 29 (GROUP, 186) - Reducer 34 <- Map 33 (PARTITION-LEVEL SORT, 154), Map 37 (PARTITION-LEVEL SORT, 154) - Reducer 35 <- Map 38 (PARTITION-LEVEL SORT, 486), Reducer 34 (PARTITION-LEVEL SORT, 486) - Reducer 36 <- Reducer 35 (GROUP, 186) - Reducer 4 <- Reducer 3 (GROUP, 481) - Reducer 5 <- Reducer 11 (PARTITION-LEVEL SORT, 925), Reducer 17 (PARTITION-LEVEL SORT, 925), Reducer 24 (PARTITION-LEVEL SORT, 925), Reducer 4 (PARTITION-LEVEL SORT, 925) - Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 398), Map 8 (PARTITION-LEVEL SORT, 398) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_addr_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_addr_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 12 + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Spark + Edges: + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 45), Map 15 (PARTITION-LEVEL SORT, 45) + Reducer 13 <- Reducer 12 (GROUP, 2) + Reducer 17 <- Map 16 (PARTITION-LEVEL SORT, 42), Map 20 (PARTITION-LEVEL SORT, 42) + Reducer 18 <- Reducer 17 (GROUP, 2) + Reducer 7 <- Map 10 (PARTITION-LEVEL SORT, 45), Map 6 (PARTITION-LEVEL SORT, 45) + Reducer 8 <- Reducer 7 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_county (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 14 + Map 11 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_addr_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66009205624 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327191 Data size: 60202592680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 18 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327191 Data size: 60202592680 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 14 + Statistics: Num rows: 37399561 Data size: 1596235092 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 37399561 Data size: 1596235092 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized - Map 19 + Local Work: + Map Reduce Local Work + Map 15 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_county (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 20 + Map 16 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 17276008716 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_addr_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143931246 Data size: 17267440236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + Statistics: Num rows: 143931246 Data size: 17267440236 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 19 + Statistics: Num rows: 10246882 Data size: 1184472168 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 10246882 Data size: 1184472168 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized - Map 25 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 26 - Map Operator Tree: - TableScan - alias: customer_address - filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_address_sk (type: int), ca_county (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 27 - Map Operator Tree: - TableScan - alias: web_sales - filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ws_bill_addr_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 31 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 32 - Map Operator Tree: - TableScan - alias: customer_address - filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_address_sk (type: int), ca_county (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 33 - Map Operator Tree: - TableScan - alias: web_sales - filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ws_bill_addr_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 37 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 38 + Local Work: + Map Reduce Local Work + Map 20 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_county (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 6 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: customer_address - filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_address_sk (type: int), ca_county (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 8 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_addr_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66009205624 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327191 Data size: 60202592680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + Statistics: Num rows: 525327191 Data size: 60202592680 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 9 + Statistics: Num rows: 37399561 Data size: 1596235092 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 37399561 Data size: 1596235092 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized - Reducer 10 + Local Work: + Map Reduce Local Work + Reducer 12 Reduce Operator Tree: Join Operator condition map: @@ -493,51 +314,37 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37399561 Data size: 5206337122 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col7 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33705 Data size: 7078050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33705 Data size: 7078050 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)) - Reducer 11 + Reducer 13 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 16 + Statistics: Num rows: 1605 Data size: 337050 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + 3 _col0 (type: string) + Reducer 17 Reduce Operator Tree: Join Operator condition map: @@ -546,67 +353,50 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246882 Data size: 2147821508 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col7 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3960 Data size: 831600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3960 Data size: 831600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)) - Reducer 17 + Reducer 18 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 21 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 22 + Statistics: Num rows: 440 Data size: 92400 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5 + input vertices: + 1 Reducer 23 + 2 Reducer 28 + Statistics: Num rows: 440 Data size: 190960 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + 3 _col0 (type: string) + Reducer 7 Reduce Operator Tree: Join Operator condition map: @@ -615,69 +405,122 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37399561 Data size: 5206337122 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col7 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33705 Data size: 7078050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33705 Data size: 7078050 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)) - Reducer 23 + Reducer 8 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 24 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col5 - Statistics: Num rows: 191667561 Data size: 26061245363 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 191667561 Data size: 26061245363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col5 (type: decimal(17,2)) - Reducer 28 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 29 + Statistics: Num rows: 1605 Data size: 337050 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + 3 _col0 (type: string) + + Stage: Stage-9 + Spark +#### A masked pattern was here #### + Vertices: + Map 4 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 45), Map 5 (PARTITION-LEVEL SORT, 45) + Reducer 3 <- Reducer 2 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_addr_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66009205624 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_addr_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 525327191 Data size: 60202592680 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 525327191 Data size: 60202592680 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 37399561 Data size: 1596235092 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 37399561 Data size: 1596235092 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 5 + Map Operator Tree: + TableScan + alias: customer_address + filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int), ca_county (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized + Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -686,20 +529,225 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37399561 Data size: 5206337122 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col7 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33705 Data size: 7078050 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33705 Data size: 7078050 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)) Reducer 3 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1605 Data size: 337050 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + Inner Join 0 to 3 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + 3 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5, _col7, _col9, _col11 + input vertices: + 1 Reducer 8 + 2 Reducer 13 + 3 Reducer 18 + Statistics: Num rows: 440 Data size: 338800 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (CASE WHEN ((_col1 > 0)) THEN (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > (_col5 / _col1))) ELSE ((null > (_col5 / _col1))) END) ELSE (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > null)) ELSE (null) END) END and CASE WHEN ((_col3 > 0)) THEN (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > (_col1 / _col3))) ELSE ((null > (_col1 / _col3))) END) ELSE (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > null)) ELSE (null) END) END) (type: boolean) + Statistics: Num rows: 110 Data size: 84700 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), 2000 (type: int), (_col9 / _col7) (type: decimal(37,20)), (_col1 / _col3) (type: decimal(37,20)), (_col11 / _col9) (type: decimal(37,20)), (_col5 / _col1) (type: decimal(37,20)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 110 Data size: 60500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 110 Data size: 60500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 14 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 24 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark + Edges: + Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 42), Map 25 (PARTITION-LEVEL SORT, 42) + Reducer 23 <- Reducer 22 (GROUP, 2) + Reducer 27 <- Map 26 (PARTITION-LEVEL SORT, 42), Map 30 (PARTITION-LEVEL SORT, 42) + Reducer 28 <- Reducer 27 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 21 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17276008716 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_addr_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143931246 Data size: 17267440236 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 143931246 Data size: 17267440236 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 24 + Statistics: Num rows: 10246882 Data size: 1184472168 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 10246882 Data size: 1184472168 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 25 + Map Operator Tree: + TableScan + alias: customer_address + filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int), ca_county (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized + Map 26 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17276008716 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_addr_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143931246 Data size: 17267440236 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 143931246 Data size: 17267440236 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 29 + Statistics: Num rows: 10246882 Data size: 1184472168 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 10246882 Data size: 1184472168 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 30 + Map Operator Tree: + TableScan + alias: customer_address + filterExpr: (ca_address_sk is not null and ca_county is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ca_address_sk is not null and ca_county is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int), ca_county (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 40000000 Data size: 4080000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized + Reducer 22 Reduce Operator Tree: Join Operator condition map: @@ -708,51 +756,36 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246882 Data size: 2147821508 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col7 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3960 Data size: 831600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3960 Data size: 831600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)) - Reducer 30 + Reducer 23 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 34 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 35 + Statistics: Num rows: 440 Data size: 92400 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + Reducer 27 Reduce Operator Tree: Join Operator condition map: @@ -761,93 +794,85 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246882 Data size: 2147821508 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col7 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3960 Data size: 831600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3960 Data size: 831600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)) - Reducer 36 + Reducer 28 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 4 + Statistics: Num rows: 440 Data size: 92400 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 29 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 5 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - Inner Join 0 to 3 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - 3 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col5, _col7, _col9, _col11 - Statistics: Num rows: 1149975359 Data size: 101451160012 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (CASE WHEN ((_col1 > 0)) THEN (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > (_col5 / _col1))) ELSE ((null > (_col5 / _col1))) END) ELSE (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > null)) ELSE (null) END) END and CASE WHEN ((_col3 > 0)) THEN (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > (_col1 / _col3))) ELSE ((null > (_col1 / _col3))) END) ELSE (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > null)) ELSE (null) END) END) (type: boolean) - Statistics: Num rows: 287493839 Data size: 25362789936 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), 2000 (type: int), (_col9 / _col7) (type: decimal(37,20)), (_col1 / _col3) (type: decimal(37,20)), (_col11 / _col9) (type: decimal(37,20)), (_col5 / _col1) (type: decimal(37,20)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 287493839 Data size: 25362789936 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 287493839 Data size: 25362789936 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) + Local Work: + Map Reduce Local Work + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 19 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query32.q.out b/ql/src/test/results/clientpositive/perf/spark/query32.q.out index af121c5549..d28a54a7e4 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query32.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query32.q.out @@ -53,29 +53,30 @@ and cs_ext_discount_amt limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4 + Stage-1 depends on stages: Stage-2 + Stage-4 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 4 + Map 7 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 3691396 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + predicate: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 669 Data size: 5348 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) + expressions: i_item_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 669 Data size: 5352 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -84,23 +85,25 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-3 + Stage: Stage-2 Spark + Edges: + Reducer 5 <- Map 4 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 8 + Map 3 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -108,29 +111,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 520), Reducer 7 (PARTITION-LEVEL SORT, 520) - Reducer 3 <- Reducer 2 (GROUP, 1) - Reducer 6 <- Map 5 (GROUP, 336) - Reducer 7 <- Map 9 (PARTITION-LEVEL SORT, 171), Reducer 6 (PARTITION-LEVEL SORT, 171) -#### A masked pattern was here #### - Vertices: - Map 1 + Map 4 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 34391703152 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 34219725500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 34219725500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -139,30 +132,72 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2 input vertices: - 1 Map 4 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) + 1 Map 6 + Statistics: Num rows: 31836679 Data size: 3532544652 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), count(_col2) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 97314 Data size: 12066936 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 97314 Data size: 12066936 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 5 + Reducer 5 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6951 Data size: 861924 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6951 Data size: 806316 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 7 + Statistics: Num rows: 97 Data size: 11252 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col2 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 34391703152 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 34219725500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 34219725500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -171,122 +206,81 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2 input vertices: - 1 Map 8 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), count(_col2) - keys: _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) + 1 Map 3 + Statistics: Num rows: 31836679 Data size: 3532544652 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col2, _col6 + input vertices: + 1 Reducer 5 + Statistics: Num rows: 7434 Data size: 832720 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) (type: boolean) + Statistics: Num rows: 2478 Data size: 277648 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: decimal(7,2)) + outputColumnNames: _col2 + Statistics: Num rows: 2478 Data size: 277648 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: decimal(17,2)) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 9 - Map Operator Tree: - TableScan - alias: item - filterExpr: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col2, _col6 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) (type: boolean) - Statistics: Num rows: 116155905 Data size: 15729842913 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: decimal(7,2)) - outputColumnNames: _col2 - Statistics: Num rows: 116155905 Data size: 15729842913 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: decimal(17,2)) - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 6 + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(37,22)) - Reducer 7 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(37,22)) + Local Work: + Map Reduce Local Work Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query33.q.out b/ql/src/test/results/clientpositive/perf/spark/query33.q.out index 39851fb403..8b57a53310 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query33.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query33.q.out @@ -147,31 +147,66 @@ where i_category in ('Books')) limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-6 + Stage-7 depends on stages: Stage-5 + Stage-9 depends on stages: Stage-7 + Stage-8 depends on stages: Stage-9 + Stage-10 depends on stages: Stage-8 + Stage-1 depends on stages: Stage-10 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark Edges: - Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 11 <- Map 13 (PARTITION-LEVEL SORT, 596), Reducer 10 (PARTITION-LEVEL SORT, 596) - Reducer 15 <- Map 1 (PARTITION-LEVEL SORT, 7), Reducer 19 (PARTITION-LEVEL SORT, 7) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 375), Reducer 22 (PARTITION-LEVEL SORT, 375) - Reducer 17 <- Reducer 16 (GROUP, 406) - Reducer 19 <- Map 18 (GROUP, 3) - Reducer 21 <- Map 12 (PARTITION-LEVEL SORT, 305), Map 20 (PARTITION-LEVEL SORT, 305) - Reducer 22 <- Map 13 (PARTITION-LEVEL SORT, 494), Reducer 21 (PARTITION-LEVEL SORT, 494) - Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 7), Reducer 30 (PARTITION-LEVEL SORT, 7) - Reducer 27 <- Reducer 26 (PARTITION-LEVEL SORT, 191), Reducer 33 (PARTITION-LEVEL SORT, 191) - Reducer 28 <- Reducer 27 (GROUP, 204) - Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 487), Reducer 15 (PARTITION-LEVEL SORT, 487) - Reducer 30 <- Map 18 (GROUP, 3) - Reducer 32 <- Map 31 (PARTITION-LEVEL SORT, 154), Map 34 (PARTITION-LEVEL SORT, 154) - Reducer 33 <- Map 35 (PARTITION-LEVEL SORT, 327), Reducer 32 (PARTITION-LEVEL SORT, 327) - Reducer 4 <- Reducer 3 (GROUP, 529) - Reducer 5 <- Reducer 17 (GROUP, 569), Reducer 28 (GROUP, 569), Reducer 4 (GROUP, 569) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 3 <- Map 2 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 2 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_category = 'Books') and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 43423396 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_category = 'Books') and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 46085 Data size: 4331534 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_manufact_id (type: int) + outputColumnNames: i_manufact_id + Statistics: Num rows: 46085 Data size: 4331534 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: i_manufact_id (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 70 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 70 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 3 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-2 + Spark #### A masked pattern was here #### Vertices: Map 1 @@ -179,238 +214,417 @@ STAGE PLANS: TableScan alias: item filterExpr: (i_manufact_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 3691396 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_sk is not null and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 460848 Data size: 3682192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_manufact_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Statistics: Num rows: 460848 Data size: 3682192 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 3 + Statistics: Num rows: 46018 Data size: 363552 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_moy = 3) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark + Edges: + Reducer 13 <- Map 12 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 12 Map Operator Tree: TableScan - alias: customer_address - filterExpr: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: ((i_category = 'Books') and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 43423396 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + predicate: ((i_category = 'Books') and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 46085 Data size: 4331534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ca_address_sk (type: int) + expressions: i_manufact_id (type: int) + outputColumnNames: i_manufact_id + Statistics: Num rows: 46085 Data size: 4331534 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: i_manufact_id (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 70 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 70 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 13 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 + Map Operator Tree: + TableScan + alias: item + filterExpr: (i_manufact_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 3691396 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (i_item_sk is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 460848 Data size: 3682192 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_manufact_id (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 460848 Data size: 3682192 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 13 + Statistics: Num rows: 46018 Data size: 363552 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 17 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 3) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 18 + Local Work: + Map Reduce Local Work + + Stage: Stage-9 + Spark + Edges: + Reducer 21 <- Map 20 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 20 Map Operator Tree: TableScan alias: item filterExpr: ((i_category = 'Books') and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 43423396 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_category = 'Books') and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46085 Data size: 4331534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_manufact_id (type: int) outputColumnNames: i_manufact_id - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46085 Data size: 4331534 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: i_manufact_id (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 70 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 70 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 20 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: (cs_sold_date_sk is not null and cs_bill_addr_sk is not null and cs_item_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 21 Execution mode: vectorized - Map 25 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 69 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 19 Map Operator Tree: TableScan alias: item filterExpr: (i_manufact_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 3691396 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_sk is not null and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 460848 Data size: 3682192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_manufact_id (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Statistics: Num rows: 460848 Data size: 3682192 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 21 + Statistics: Num rows: 46018 Data size: 363552 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) Execution mode: vectorized - Map 31 + Local Work: + Map Reduce Local Work + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 25 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null and ws_item_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 3) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 34 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 15 <- Map 10 (PARTITION-LEVEL SORT, 14), Map 14 (PARTITION-LEVEL SORT, 14) + Reducer 16 <- Reducer 15 (GROUP, 2) + Reducer 23 <- Map 22 (PARTITION-LEVEL SORT, 11), Map 26 (PARTITION-LEVEL SORT, 11) + Reducer 24 <- Reducer 23 (GROUP, 2) + Reducer 5 <- Map 10 (PARTITION-LEVEL SORT, 8), Map 4 (PARTITION-LEVEL SORT, 8) + Reducer 6 <- Reducer 5 (GROUP, 2) + Reducer 7 <- Reducer 16 (GROUP, 2), Reducer 24 (GROUP, 2), Reducer 6 (GROUP, 2) + Reducer 8 <- Reducer 7 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 3) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: customer_address + filterExpr: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) + expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Map 14 + Map Operator Tree: + TableScan + alias: catalog_sales + filterExpr: (cs_sold_date_sk is not null and cs_bill_addr_sk is not null and cs_item_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 35538021432 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 285117733 Data size: 35183603168 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 285117733 Data size: 35183603168 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 17 + Statistics: Num rows: 7751872 Data size: 764931900 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 7751872 Data size: 764931900 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 35 + Local Work: + Map Reduce Local Work + Map 22 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null and ws_item_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17852019388 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143931246 Data size: 17843165220 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 143931246 Data size: 17843165220 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 25 + Statistics: Num rows: 3941109 Data size: 468766936 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 3941109 Data size: 468766936 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 26 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 9 + Map 4 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_addr_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313188164 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327191 Data size: 62303901444 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525327191 Data size: 62303901444 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 14384447 Data size: 57537904 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 14384447 Data size: 57537904 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - outputColumnNames: _col3, _col5 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) + Local Work: + Map Reduce Local Work Reducer 15 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -418,37 +632,35 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1550375 Data size: 20250108 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col4, _col5 + Statistics: Num rows: 1550375 Data size: 20250108 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 11 + Statistics: Num rows: 2229 Data size: 4436 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col4 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 17 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -456,107 +668,58 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(27,2)) - Reducer 19 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reducer 21 + Reducer 23 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - Reducer 22 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col3 + Statistics: Num rows: 788222 Data size: 87410040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - outputColumnNames: _col4, _col5 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 26 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Reducer 27 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col3 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 28 + expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col3, _col5 + Statistics: Num rows: 788222 Data size: 87410040 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 19 + Statistics: Num rows: 1134 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 24 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -564,71 +727,22 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 95833781 Data size: 13030622757 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(27,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col3 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 30 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reducer 32 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 33 + Reducer 5 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -637,18 +751,34 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2876890 Data size: 11507672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: decimal(7,2)) outputColumnNames: _col3, _col5 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 4 + Statistics: Num rows: 2876890 Data size: 11507672 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 1 + Statistics: Num rows: 4136 Data size: 12064 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -656,20 +786,20 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(27,2)) - Reducer 5 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -677,26 +807,26 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: decimal(27,2)) sort order: + - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: int) - Reducer 6 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: decimal(27,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query34.q.out b/ql/src/test/results/clientpositive/perf/spark/query34.q.out index 88279a30a7..65f3d1fcbf 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query34.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query34.q.out @@ -68,19 +68,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (2000, 2001, 2002) and (d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 869 Data size: 10428 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 869 Data size: 10428 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: household_demographics filterExpr: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 748800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 480 Data size: 49920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 480 Data size: 49920 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -88,19 +108,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 9 + Map 8 Map Operator Tree: TableScan alias: store filterExpr: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 173808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 11424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 11424 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -112,10 +132,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 567), Reducer 6 (PARTITION-LEVEL SORT, 567) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 223), Reducer 5 (PARTITION-LEVEL SORT, 223) Reducer 3 <- Reducer 2 (SORT, 1) - Reducer 5 <- Map 4 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 6 <- Reducer 5 (GROUP, 529) + Reducer 5 <- Map 4 (GROUP, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -123,19 +142,19 @@ STAGE PLANS: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 28480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 28480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 28480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 28480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) Execution mode: vectorized Map 4 @@ -143,40 +162,59 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_hdemo_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 11105263900 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 479121995 Data size: 9237528672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year) IN (2000, 2001, 2002) and (d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (2000, 2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 16232 Data size: 18163608 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 16232 Data size: 18163608 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 16232 Data size: 18163608 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 479121995 Data size: 9237528672 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 6 + Statistics: Num rows: 228012750 Data size: 3389532324 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4 + input vertices: + 1 Map 7 + Statistics: Num rows: 15200851 Data size: 60803412 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col4 + input vertices: + 1 Map 8 + Statistics: Num rows: 8063963 Data size: 32255856 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col1 (type: int), _col4 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 8063963 Data size: 96767560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 8063963 Data size: 96767560 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -186,15 +224,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895995 Data size: 326142180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col2 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: int), _col7 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895995 Data size: 326142180 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: +++- - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895995 Data size: 326142180 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: int), _col5 (type: bigint) Reducer 3 Execution mode: vectorized @@ -202,59 +240,15 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895995 Data size: 326142180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895995 Data size: 326142180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col4 - input vertices: - 1 Map 9 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col1 (type: int), _col4 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) - Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -262,19 +256,19 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8063963 Data size: 96767560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8063963 Data size: 96767560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 BETWEEN 15 AND 20 (type: boolean) - Statistics: Num rows: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895995 Data size: 10751944 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895995 Data size: 10751944 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: bigint) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/perf/spark/query35.q.out b/ql/src/test/results/clientpositive/perf/spark/query35.q.out index 22e007d1b8..e9c5c3953a 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query35.q.out @@ -111,302 +111,269 @@ select limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4, Stage-5 + Stage-1 depends on stages: Stage-2 + Stage-4 is a root stage + Stage-5 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 10 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 154), Map 15 (PARTITION-LEVEL SORT, 154) - Reducer 14 <- Reducer 13 (GROUP, 169) - Reducer 17 <- Map 16 (PARTITION-LEVEL SORT, 305), Map 19 (PARTITION-LEVEL SORT, 305) - Reducer 18 <- Reducer 17 (GROUP, 336) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 7 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 597), Reducer 2 (PARTITION-LEVEL SORT, 597) - Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 1009), Reducer 14 (PARTITION-LEVEL SORT, 1009), Reducer 18 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009) - Reducer 5 <- Reducer 4 (GROUP, 1009) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: c - filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) - Execution mode: vectorized - Map 11 + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_qoy < 4) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Spark + Edges: + Reducer 11 <- Map 10 (GROUP, 2) + Reducer 14 <- Map 13 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151734616 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 12 + Statistics: Num rows: 17104380 Data size: 68274076 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 168231 Data size: 671516 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 168231 Data size: 671516 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 15 + Local Work: + Map Reduce Local Work + Map 13 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_qoy < 4) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + filterExpr: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 2292391500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 285115246 Data size: 2269509840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + expressions: cs_sold_date_sk (type: int), cs_ship_customer_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 285115246 Data size: 2269509840 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 15 + Statistics: Num rows: 33642830 Data size: 128862124 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 167041 Data size: 639820 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 167041 Data size: 639820 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 16 + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan - alias: catalog_sales - filterExpr: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 4400627472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: cs_sold_date_sk (type: int), cs_ship_customer_sk (type: int) + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 9 + Statistics: Num rows: 62428523 Data size: 155171512 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 62428523 Data size: 155171512 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 168231 Data size: 418156 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 11 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 168231 Data size: 671516 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 168231 Data size: 1344440 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) + Reducer 14 Execution mode: vectorized - Map 19 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 167041 Data size: 639820 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 167041 Data size: 1307984 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 36), Map 6 (PARTITION-LEVEL SORT, 36) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 60), Reducer 2 (PARTITION-LEVEL SORT, 60) + Reducer 4 <- Reducer 3 (GROUP, 2) + Reducer 5 <- Reducer 4 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_qoy < 4) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: c + filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 948805540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int) Execution mode: vectorized - Map 7 + Map 6 Map Operator Tree: TableScan alias: ca filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 8 + Map 7 Map Operator Tree: TableScan alias: customer_demographics filterExpr: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 346294800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 346294800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int), cd_gender (type: string), cd_marital_status (type: string), cd_dep_count (type: int), cd_dep_employed_count (type: int), cd_dep_college_count (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 346294800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 346294800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Execution mode: vectorized - Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reducer 13 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col1 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reducer 14 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) - Reducer 17 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col1 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reducer 18 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) Reducer 2 Reduce Operator Tree: Join Operator @@ -416,14 +383,16 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 77201384 Data size: 7246127248 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 77201384 Data size: 7246127248 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col4 (type: string) Reducer 3 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -432,48 +401,44 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col4, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) + Statistics: Num rows: 78293105 Data size: 21295724560 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + Left Outer Join 0 to 2 + Left Outer Join 0 to 3 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + 3 _col0 (type: int) + outputColumnNames: _col4, _col6, _col7, _col8, _col9, _col10, _col12, _col14 + input vertices: + 1 Map 8 + 2 Reducer 11 + 3 Reducer 14 + Statistics: Num rows: 161199 Data size: 44490924 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col12 is not null or _col14 is not null) (type: boolean) + Statistics: Num rows: 161199 Data size: 44490924 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) + outputColumnNames: _col4, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 161199 Data size: 44490924 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), sum(_col8), count(_col8), max(_col8), sum(_col9), count(_col9), max(_col9), sum(_col10), count(_col10), max(_col10) + keys: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: int), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: int) Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - Left Outer Join 0 to 2 - Left Outer Join 0 to 3 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - 3 _col0 (type: int) - outputColumnNames: _col4, _col6, _col7, _col8, _col9, _col10, _col12, _col14 - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col12 is not null or _col14 is not null) (type: boolean) - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) - outputColumnNames: _col4, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col8), count(_col8), max(_col8), sum(_col9), count(_col9), max(_col9), sum(_col10), count(_col10), max(_col10) - keys: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) - sort order: ++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) - Statistics: Num rows: 2090864244 Data size: 184456650574 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: int), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: int) - Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -481,35 +446,85 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col6 (type: bigint), (UDFToDouble(_col7) / _col8) (type: double), _col9 (type: int), _col7 (type: bigint), _col4 (type: int), (UDFToDouble(_col10) / _col11) (type: double), _col12 (type: int), _col10 (type: bigint), _col5 (type: int), (UDFToDouble(_col13) / _col14) (type: double), _col15 (type: int), _col13 (type: bigint), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9, _col10, _col11, _col12, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col17 (type: int), _col7 (type: int), _col12 (type: int) sort order: ++++++ - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: int), _col6 (type: bigint), _col9 (type: double), _col10 (type: int), _col11 (type: bigint), _col14 (type: double), _col15 (type: int), _col16 (type: bigint) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: double), VALUE._col2 (type: int), VALUE._col3 (type: bigint), KEY.reducesinkkey4 (type: int), VALUE._col0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: int), VALUE._col6 (type: bigint), KEY.reducesinkkey5 (type: int), VALUE._col0 (type: bigint), VALUE._col7 (type: double), VALUE._col8 (type: int), VALUE._col9 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 1045432122 Data size: 92228325287 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 12 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_qoy < 4) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 15 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_qoy < 4) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-0 Fetch Operator limit: -1 diff --git a/ql/src/test/results/clientpositive/perf/spark/query36.q.out b/ql/src/test/results/clientpositive/perf/spark/query36.q.out index 694e57905d..e6dd6bdff2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query36.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query36.q.out @@ -66,19 +66,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 6 + Map Operator Tree: + TableScan + alias: d1 + filterExpr: ((d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store filterExpr: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 278 Data size: 25020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 278 Data size: 25020 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -90,11 +110,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 486), Reducer 2 (PARTITION-LEVEL SORT, 486) - Reducer 4 <- Reducer 3 (GROUP, 1009) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 793) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 14), Map 8 (PARTITION-LEVEL SORT, 14) + Reducer 3 <- Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2) + Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -102,89 +121,64 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 129922564376 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 118494313600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: d1 - filterExpr: ((d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 118494313600 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 6 + Statistics: Num rows: 187574154 Data size: 38128218376 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4 + input vertices: + 1 Map 7 + Statistics: Num rows: 30601888 Data size: 1682778560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 30601888 Data size: 1682778560 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)) Execution mode: vectorized - Map 9 + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_class (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Reducer 2 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)) - Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -193,24 +187,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col4, _col10, _col11 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30601888 Data size: 7129914624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col11 (type: string), _col10 (type: string), _col4 (type: decimal(7,2)), _col3 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30601888 Data size: 7129914624 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85680 Data size: 35471520 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85680 Data size: 35471520 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -218,24 +212,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1266840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1266840 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (grouping(_col4, 1) + grouping(_col4, 0)) (type: bigint), CASE WHEN ((grouping(_col4, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string), (_col2 / _col3) (type: decimal(37,20)) sort order: +++ Map-reduce partition columns: (grouping(_col4, 1) + grouping(_col4, 0)) (type: bigint), CASE WHEN ((grouping(_col4, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string) - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1266840 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: bigint) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: decimal(17,2)), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1266840 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -256,30 +250,30 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1266840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col2 / _col3) (type: decimal(37,20)), _col0 (type: string), _col1 (type: string), (grouping(_col4, 1) + grouping(_col4, 0)) (type: bigint), rank_window_0 (type: int), CASE WHEN (((grouping(_col4, 1) + grouping(_col4, 0)) = 0)) THEN (_col0) ELSE (null) END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1499400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: bigint), _col5 (type: string), _col4 (type: int) sort order: -++ - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1499400 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: decimal(37,20)), _col1 (type: string), _col2 (type: string) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: decimal(37,20)), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1499400 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query37.q.out b/ql/src/test/results/clientpositive/perf/spark/query37.q.out index bce0d683e5..fad08e558c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query37.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query37.q.out @@ -31,28 +31,29 @@ select i_item_id limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 7 + Map 6 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-06-02 00:00:00' AND TIMESTAMP'2001-08-01 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-06-02 00:00:00' AND TIMESTAMP'2001-08-01 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -61,66 +62,44 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 5 (PARTITION-LEVEL SORT, 306), Map 6 (PARTITION-LEVEL SORT, 306) - Reducer 3 <- Reducer 2 (GROUP, 671) - Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: cs_item_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cs_item_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_item_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 5 + Map 4 Map Operator Tree: TableScan alias: item filterExpr: ((i_manufact_id) IN (678, 964, 918, 849) and i_current_price BETWEEN 22 AND 52 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 186512804 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manufact_id) IN (678, 964, 918, 849) and i_current_price BETWEEN 22 AND 52 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 297 Data size: 119988 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string), i_current_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)) + Statistics: Num rows: 297 Data size: 119988 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) Execution mode: vectorized - Map 6 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: inventory filterExpr: (inv_quantity_on_hand BETWEEN 100 AND 500 and inv_item_sk is not null and inv_date_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 443485108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) (type: boolean) - Statistics: Num rows: 4176000 Data size: 65980122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4176000 Data size: 49276128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4176000 Data size: 65980122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4176000 Data size: 49276128 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -129,66 +108,91 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 7 - Statistics: Num rows: 4593600 Data size: 72578135 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4593600 Data size: 72578135 Basic stats: COMPLETE Column stats: NONE + 1 Map 6 + Statistics: Num rows: 463969 Data size: 1855876 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 368) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: catalog_sales + filterExpr: cs_item_sk is not null (type: boolean) + Statistics: Num rows: 287989836 Data size: 1151959344 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cs_item_sk is not null (type: boolean) + Statistics: Num rows: 287989836 Data size: 1151959344 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cs_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 287989836 Data size: 1151959344 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + outputColumnNames: _col2, _col3, _col4 + input vertices: + 1 Map 4 + 2 Map 5 + Statistics: Num rows: 118943936 Data size: 47101798656 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 118943936 Data size: 47101798656 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + Statistics: Num rows: 118943936 Data size: 47101798656 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: vectorized Local Work: Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col1 (type: int) - outputColumnNames: _col2, _col3, _col4 - Statistics: Num rows: 633577652 Data size: 85799141554 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 633577652 Data size: 85799141554 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) - Statistics: Num rows: 633577652 Data size: 85799141554 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: decimal(7,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26286282 Data size: 10409367672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26286282 Data size: 10409367672 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string), _col2 (type: decimal(7,2)) - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26286282 Data size: 10409367672 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 39600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 39600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query38.q.out b/ql/src/test/results/clientpositive/perf/spark/query38.q.out index 0064177f96..000b37b48b 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query38.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query38.q.out @@ -59,14 +59,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -84,14 +84,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -109,14 +109,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -128,14 +128,14 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Reducer 9 (GROUP PARTITION-LEVEL SORT, 369) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 706), Map 17 (PARTITION-LEVEL SORT, 706) - Reducer 15 <- Reducer 14 (GROUP PARTITION-LEVEL SORT, 186) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 975), Map 12 (PARTITION-LEVEL SORT, 975) - Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 481) - Reducer 4 <- Reducer 10 (GROUP, 259), Reducer 15 (GROUP, 259), Reducer 3 (GROUP, 259) + Reducer 10 <- Reducer 9 (GROUP PARTITION-LEVEL SORT, 68) + Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 128), Map 17 (PARTITION-LEVEL SORT, 128) + Reducer 15 <- Reducer 14 (GROUP PARTITION-LEVEL SORT, 35) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 159), Map 12 (PARTITION-LEVEL SORT, 159) + Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 125) + Reducer 4 <- Reducer 10 (GROUP, 234), Reducer 15 (GROUP, 234), Reducer 3 (GROUP, 234) Reducer 5 <- Reducer 4 (GROUP, 1) - Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 873), Map 8 (PARTITION-LEVEL SORT, 873) + Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 140), Map 8 (PARTITION-LEVEL SORT, 140) #### A masked pattern was here #### Vertices: Map 1 @@ -143,14 +143,14 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 4400627472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -160,12 +160,12 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 5625297490 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 5625297490 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Execution mode: vectorized Local Work: @@ -175,19 +175,19 @@ STAGE PLANS: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 13 @@ -195,14 +195,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_sold_date_sk is not null and ws_bill_customer_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151734616 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -212,12 +212,12 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 16 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 1566997880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 1566997880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Execution mode: vectorized Local Work: @@ -227,19 +227,19 @@ STAGE PLANS: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 8 @@ -247,14 +247,14 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_sold_date_sk is not null and cs_bill_customer_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 2292401892 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 2269540704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 2269540704 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -264,12 +264,12 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 11 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 3098704958 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 3098704958 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Execution mode: vectorized Local Work: @@ -281,28 +281,28 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 87116929 Data size: 11797382219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8933080662 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col3) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 29901741408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 29901741408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint) Reducer 14 Reduce Operator Tree: @@ -313,17 +313,17 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Reducer 15 Execution mode: vectorized Reduce Operator Tree: @@ -331,28 +331,28 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 43560808 Data size: 5923010113 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4509529116 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col3) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 29901741408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 29901741408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -363,17 +363,17 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized Reduce Operator Tree: @@ -381,28 +381,28 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 16459131630 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col3) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 29901741408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 29901741408 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint) Reducer 4 Execution mode: vectorized @@ -412,24 +412,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 152458212 Data size: 16545889939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 29901741408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: bigint) outputColumnNames: _col3 - Statistics: Num rows: 152458212 Data size: 16545889939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 106034544 Data size: 848276352 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 = 3L) (type: boolean) - Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: bigint) Reducer 5 @@ -439,13 +439,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -459,17 +459,17 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query39.q.out b/ql/src/test/results/clientpositive/perf/spark/query39.q.out index 71c029b92b..8ae0ee1b2a 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query39.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query39.q.out @@ -51,54 +51,50 @@ order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov ,inv2.d_moy,inv2.mean, inv2.cov POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 10 Map Operator Tree: TableScan - alias: warehouse - filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 1848000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 1848000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + expressions: i_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 462000 Data size: 1848000 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - - Stage: Stage-3 - Spark -#### A masked pattern was here #### - Vertices: - Map 16 + Map 11 Map Operator Tree: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -106,321 +102,303 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work + Map 9 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 5) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 5) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 5), Map 14 (PARTITION-LEVEL SORT, 5) - Reducer 12 <- Map 15 (PARTITION-LEVEL SORT, 11), Reducer 11 (PARTITION-LEVEL SORT, 11) - Reducer 13 <- Reducer 12 (GROUP, 7) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 5), Map 7 (PARTITION-LEVEL SORT, 5) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 11), Reducer 2 (PARTITION-LEVEL SORT, 11) - Reducer 4 <- Reducer 3 (GROUP, 7) - Reducer 5 <- Reducer 13 (PARTITION-LEVEL SORT, 4), Reducer 4 (PARTITION-LEVEL SORT, 4) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 8 <- Map 7 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 7 Map Operator Tree: TableScan alias: inventory filterExpr: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 1032514 Data size: 8260116 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col7 + input vertices: + 1 Map 10 + Statistics: Num rows: 1032514 Data size: 8260116 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col7, _col8, _col9 + input vertices: + 1 Map 11 + Statistics: Num rows: 1032514 Data size: 111511516 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col9 (type: string), _col8 (type: int), _col7 (type: int), _col3 (type: int), UDFToDouble(_col3) (type: double), (UDFToDouble(_col3) * UDFToDouble(_col3)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1032514 Data size: 111511516 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3), count(_col3), sum(_col5), sum(_col4) + keys: _col1 (type: int), _col2 (type: int), _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 36099 Data size: 5053860 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 36099 Data size: 5053860 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double) Execution mode: vectorized - Map 10 - Map Operator Tree: - TableScan - alias: inventory - filterExpr: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Reducer 8 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 36099 Data size: 5053860 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 + Statistics: Num rows: 36099 Data size: 1443960 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + predicate: CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (false) ELSE (((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4)) > 1.0D)) END (type: boolean) + Statistics: Num rows: 18049 Data size: 721960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) + expressions: _col0 (type: int), _col1 (type: int), (UDFToDouble(_col3) / _col4) (type: double), CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (null) ELSE ((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4))) END (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) - Execution mode: vectorized - Map 14 + Statistics: Num rows: 18049 Data size: 433176 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 4 Map Operator Tree: TableScan alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 5) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + filterExpr: ((d_year = 1999) and (d_moy = 4) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_moy = 5) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 15 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 1848000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 1848000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 1848000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 4) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: warehouse + filterExpr: w_warehouse_sk is not null (type: boolean) + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + predicate: w_warehouse_sk is not null (type: boolean) + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 8 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: item - filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: inventory + filterExpr: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 4 + Statistics: Num rows: 1032514 Data size: 8260116 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col7 + input vertices: + 1 Map 5 + Statistics: Num rows: 1032514 Data size: 8260116 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col7, _col8, _col9 + input vertices: + 1 Map 6 + Statistics: Num rows: 1032514 Data size: 111511516 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col9 (type: string), _col8 (type: int), _col7 (type: int), _col3 (type: int), UDFToDouble(_col3) (type: double), (UDFToDouble(_col3) * UDFToDouble(_col3)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1032514 Data size: 111511516 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3), count(_col3), sum(_col5), sum(_col4) + keys: _col1 (type: int), _col2 (type: int), _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 36099 Data size: 5053860 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 36099 Data size: 5053860 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double) Execution mode: vectorized - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int) - Reducer 12 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7 - Statistics: Num rows: 45476640 Data size: 718523566 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col7, _col8, _col9 - input vertices: - 1 Map 16 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col9 (type: string), _col8 (type: int), _col7 (type: int), _col3 (type: int), UDFToDouble(_col3) (type: double), (UDFToDouble(_col3) * UDFToDouble(_col3)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3), count(_col3), sum(_col5), sum(_col4) - keys: _col1 (type: int), _col2 (type: int), _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double) - Reducer 13 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) - keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 - Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (false) ELSE (((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4)) > 1.0D)) END (type: boolean) - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), (UDFToDouble(_col3) / _col4) (type: double), CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (null) ELSE ((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4))) END (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: double), _col3 (type: double) Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int) - Reducer 3 + Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7 - Statistics: Num rows: 45476640 Data size: 718523566 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col7, _col8, _col9 - input vertices: - 1 Map 9 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col9 (type: string), _col8 (type: int), _col7 (type: int), _col3 (type: int), UDFToDouble(_col3) (type: double), (UDFToDouble(_col3) * UDFToDouble(_col3)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3), count(_col3), sum(_col5), sum(_col4) - keys: _col1 (type: int), _col2 (type: int), _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) - Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double) - Reducer 4 - Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36099 Data size: 5053860 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 - Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36099 Data size: 1443960 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (false) ELSE (((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4)) > 1.0D)) END (type: boolean) - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18049 Data size: 721960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (UDFToDouble(_col3) / _col4) (type: double), CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (null) ELSE ((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4))) END (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: double), _col3 (type: double) - Reducer 5 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col1 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: double), _col3 (type: double), _col6 (type: double), _col7 (type: double) - sort order: ++++++ - Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col5 (type: int) - Reducer 6 + Statistics: Num rows: 18049 Data size: 433176 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Reducer 8 + Statistics: Num rows: 189509 Data size: 9096432 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: double), _col3 (type: double), _col6 (type: double), _col7 (type: double) + sort order: ++++++ + Statistics: Num rows: 189509 Data size: 9096432 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: int), _col5 (type: int) + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), 4 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), 5 (type: int), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 189509 Data size: 10612504 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 189509 Data size: 10612504 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query4.q.out b/ql/src/test/results/clientpositive/perf/spark/query4.q.out index 347261396c..0cf487d08e 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query4.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query4.q.out @@ -215,432 +215,498 @@ union all limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-6 + Stage-1 depends on stages: Stage-7 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 975), Reducer 10 (PARTITION-LEVEL SORT, 975) - Reducer 12 <- Reducer 11 (GROUP, 481) - Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 306), Map 19 (PARTITION-LEVEL SORT, 306) - Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 873), Reducer 16 (PARTITION-LEVEL SORT, 873) - Reducer 18 <- Reducer 17 (GROUP, 369) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 7 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 154), Map 25 (PARTITION-LEVEL SORT, 154) - Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 706), Reducer 22 (PARTITION-LEVEL SORT, 706) - Reducer 24 <- Reducer 23 (GROUP, 186) - Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 306), Map 31 (PARTITION-LEVEL SORT, 306) - Reducer 29 <- Map 32 (PARTITION-LEVEL SORT, 873), Reducer 28 (PARTITION-LEVEL SORT, 873) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 706), Reducer 2 (PARTITION-LEVEL SORT, 706) - Reducer 30 <- Reducer 29 (GROUP, 369) - Reducer 34 <- Map 33 (PARTITION-LEVEL SORT, 398), Map 37 (PARTITION-LEVEL SORT, 398) - Reducer 35 <- Map 38 (PARTITION-LEVEL SORT, 975), Reducer 34 (PARTITION-LEVEL SORT, 975) - Reducer 36 <- Reducer 35 (GROUP, 481) - Reducer 4 <- Reducer 3 (GROUP, 186) - Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 690), Reducer 18 (PARTITION-LEVEL SORT, 690), Reducer 24 (PARTITION-LEVEL SORT, 690), Reducer 30 (PARTITION-LEVEL SORT, 690), Reducer 36 (PARTITION-LEVEL SORT, 690), Reducer 4 (PARTITION-LEVEL SORT, 690) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 6 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 21 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 26 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 31 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Reducer 9 (GROUP, 1009) + Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 762), Map 17 (PARTITION-LEVEL SORT, 762) + Reducer 15 <- Reducer 14 (GROUP, 604) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 592), Map 22 (PARTITION-LEVEL SORT, 592) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 592), Map 7 (PARTITION-LEVEL SORT, 592) + Reducer 20 <- Reducer 19 (GROUP, 307) + Reducer 24 <- Map 23 (PARTITION-LEVEL SORT, 762), Map 27 (PARTITION-LEVEL SORT, 762) + Reducer 25 <- Reducer 24 (GROUP, 604) + Reducer 29 <- Map 28 (PARTITION-LEVEL SORT, 989), Map 32 (PARTITION-LEVEL SORT, 989) + Reducer 3 <- Reducer 2 (GROUP, 307) + Reducer 30 <- Reducer 29 (GROUP, 1009) + Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 876), Reducer 15 (PARTITION-LEVEL SORT, 876), Reducer 20 (PARTITION-LEVEL SORT, 876), Reducer 25 (PARTITION-LEVEL SORT, 876), Reducer 3 (PARTITION-LEVEL SORT, 876), Reducer 30 (PARTITION-LEVEL SORT, 876) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 989), Map 8 (PARTITION-LEVEL SORT, 989) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 65648831896 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143930993 Data size: 65616156304 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 143930993 Data size: 65616156304 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 6 + Statistics: Num rows: 51391963 Data size: 23212933912 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 51391963 Data size: 23212933912 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 12 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 15 + Map 13 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 130666820708 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 129363734000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Statistics: Num rows: 285117831 Data size: 129363734000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 16 + Statistics: Num rows: 101084444 Data size: 45045874736 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 101084444 Data size: 45045874736 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 19 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 20 + Local Work: + Map Reduce Local Work + Map 17 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 21 + Map 18 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 65648831896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 65616156304 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Statistics: Num rows: 143930993 Data size: 65616156304 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 21 + Statistics: Num rows: 51391963 Data size: 23212933912 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 51391963 Data size: 23212933912 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 25 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 26 + Local Work: + Map Reduce Local Work + Map 22 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 27 + Map 23 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 130666820708 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 129363734000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Execution mode: vectorized - Map 31 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 129363734000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 26 + Statistics: Num rows: 101084444 Data size: 45045874736 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 101084444 Data size: 45045874736 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 32 + Local Work: + Map Reduce Local Work + Map 27 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 33 + Map 28 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 250835077552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 228770025580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Execution mode: vectorized - Map 37 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 228770025580 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 31 + Statistics: Num rows: 187573258 Data size: 74098405556 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 187573258 Data size: 74098405556 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 38 + Local Work: + Map Reduce Local Work + Map 32 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 8 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string), c_birth_country (type: string), c_login (type: string), c_email_address (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 52480000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) Execution mode: vectorized - Map 9 + Map 8 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 250835077552 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 228770025580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Statistics: Num rows: 525327388 Data size: 228770025580 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 11 + Statistics: Num rows: 187573258 Data size: 74098405556 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 187573258 Data size: 74098405556 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(24,6)) - Reducer 12 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -648,41 +714,25 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 39765530696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(24,6)) - Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Reducer 17 + Reducer 14 Reduce Operator Tree: Join Operator condition map: @@ -691,24 +741,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 110554293408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 110554293408 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 77228515216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 77228515216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: decimal(24,6)) - Reducer 18 + Reducer 15 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -716,57 +766,51 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 77228515216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 21429902128 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33694814 Data size: 7143300568 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33694814 Data size: 7143300568 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 33694814 Data size: 7143300568 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(24,6)) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Reducer 22 + Reducer 19 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Reducer 23 + outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + Statistics: Num rows: 51391963 Data size: 56515069380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 51391963 Data size: 56515069380 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col7) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col7 (type: decimal(24,6)) + Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -775,24 +819,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 56515069380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 56515069380 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: decimal(24,6)) - Reducer 24 + Reducer 20 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -800,67 +844,25 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(24,6)) - Reducer 28 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Reducer 29 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(24,6)) - Reducer 3 + Reducer 24 Reduce Operator Tree: Join Operator condition map: @@ -869,24 +871,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 110554293408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 110554293408 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 77228515216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 77228515216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: decimal(24,6)) - Reducer 30 + Reducer 25 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -894,34 +896,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 77228515216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 21429902128 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101084444 Data size: 21429902128 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(24,6)) - Reducer 34 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) - Reducer 35 + Reducer 29 Reduce Operator Tree: Join Operator condition map: @@ -930,24 +916,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 195740419320 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 195740419320 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: decimal(24,6)) - Reducer 36 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -955,18 +941,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 39263459732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + expressions: _col0 (type: string), _col7 (type: decimal(24,6)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: decimal(24,6)) - Reducer 4 + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(24,6)) + Reducer 30 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -974,18 +960,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(24,6)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 187573258 Data size: 55709257626 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(24,6)) - Reducer 5 + Statistics: Num rows: 187573258 Data size: 55709257626 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: decimal(24,6)) + Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -1002,36 +988,62 @@ STAGE PLANS: 4 _col0 (type: string) 5 _col0 (type: string) outputColumnNames: _col1, _col3, _col5, _col7, _col9, _col11, _col12 - Statistics: Num rows: 1916625598 Data size: 169085266687 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 141992956306 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > (_col12 / _col3))) ELSE ((null > (_col12 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > null)) ELSE (null) END) END and CASE WHEN (_col7 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > (_col1 / _col7))) ELSE ((null > (_col1 / _col7))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > null)) ELSE (null) END) END) (type: boolean) - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46893314 Data size: 35498238698 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col11 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46893314 Data size: 3985931690 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46893314 Data size: 3985931690 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 479156399 Data size: 42271316627 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46893314 Data size: 3985931690 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 8500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + Statistics: Num rows: 187573258 Data size: 195740419320 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 187573258 Data size: 195740419320 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col7) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + Statistics: Num rows: 187573258 Data size: 143305969112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col7 (type: decimal(24,6)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query40.q.out b/ql/src/test/results/clientpositive/perf/spark/query40.q.out index 6cdac29e9b..1961801a5c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query40.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query40.q.out @@ -68,14 +68,14 @@ STAGE PLANS: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2430 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2430 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int), w_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2430 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -93,14 +93,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -112,9 +112,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 329), Map 6 (PARTITION-LEVEL SORT, 329) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 370), Reducer 2 (PARTITION-LEVEL SORT, 370) - Reducer 4 <- Reducer 3 (GROUP, 447) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 311), Map 6 (PARTITION-LEVEL SORT, 311) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 52), Reducer 2 (PARTITION-LEVEL SORT, 52) + Reducer 4 <- Reducer 3 (GROUP, 6) Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -123,19 +123,19 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_warehouse_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 36689969600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285115816 Data size: 36323818824 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_warehouse_sk (type: int), cs_item_sk (type: int), cs_order_number (type: int), cs_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285115816 Data size: 36323818824 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285115816 Data size: 36323818824 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col4 (type: decimal(7,2)) Execution mode: vectorized Map 6 @@ -143,19 +143,19 @@ STAGE PLANS: TableScan alias: catalog_returns filterExpr: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3391394488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3391394488 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_item_sk (type: int), cr_order_number (type: int), cr_refunded_cash (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3391394488 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3391394488 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized Map 8 @@ -163,19 +163,19 @@ STAGE PLANS: TableScan alias: item filterExpr: (i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 99661408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51333 Data size: 11073480 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51333 Data size: 11073480 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51333 Data size: 11073480 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reducer 2 @@ -189,7 +189,7 @@ STAGE PLANS: 0 _col2 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col4, _col7 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285115816 Data size: 55419846296 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -199,12 +199,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col4, _col7, _col9 input vertices: 1 Map 7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677367 Data size: 6613653970 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677367 Data size: 6613653970 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col4 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col9 (type: string) Reducer 3 Local Work: @@ -217,7 +217,7 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col4, _col7, _col9, _col11 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3519685 Data size: 925799782 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -227,22 +227,22 @@ STAGE PLANS: outputColumnNames: _col4, _col7, _col9, _col11, _col14 input vertices: 1 Map 9 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3519685 Data size: 1220120888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col14 (type: string), _col11 (type: string), CASE WHEN ((CAST( _col9 AS DATE) < DATE'1998-04-08')) THEN ((_col4 - COALESCE(_col7,0))) ELSE (0) END (type: decimal(13,2)), CASE WHEN ((CAST( _col9 AS DATE) >= DATE'1998-04-08')) THEN ((_col4 - COALESCE(_col7,0))) ELSE (0) END (type: decimal(13,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3519685 Data size: 1220120888 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1759842 Data size: 721535220 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1759842 Data size: 721535220 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(23,2)), _col3 (type: decimal(23,2)) Reducer 4 @@ -253,11 +253,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 769995 Data size: 315697950 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 769995 Data size: 315697950 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(23,2)), _col3 (type: decimal(23,2)) Reducer 5 @@ -266,13 +266,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(23,2)), VALUE._col1 (type: decimal(23,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 769995 Data size: 315697950 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query42.q.out b/ql/src/test/results/clientpositive/perf/spark/query42.q.out index 8d9777f086..7a14bbcf44 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query42.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query42.q.out @@ -41,117 +41,112 @@ select dt.d_year limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 6 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 440), Reducer 2 (PARTITION-LEVEL SORT, 440) - Reducer 4 <- Reducer 3 (GROUP, 481) - Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 6 + Map 4 Map Operator Tree: TableScan alias: dt filterExpr: ((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: item filterExpr: ((i_manager_id = 1) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 47114948 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manager_id = 1) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 747830 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_category_id (type: int), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 7333 Data size: 747898 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66112867736 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 15062131 Data size: 60248636 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col7, _col8 + input vertices: + 1 Map 5 + Statistics: Num rows: 2301098 Data size: 216303256 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col7 (type: int), _col8 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 120 Data size: 24720 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 120 Data size: 24720 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col7 (type: int), _col8 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -159,29 +154,29 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 22660 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 34980 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: decimal(17,2)), _col0 (type: int), _col1 (type: string) sort order: -++ - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 34980 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 1998 (type: int), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 23100 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query43.q.out b/ql/src/test/results/clientpositive/perf/spark/query43.q.out index 3e234a1384..53bf3ed7b2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query43.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query43.q.out @@ -44,19 +44,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 6 + Map 4 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 64548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_day_name (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 652 Data size: 64548 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: store filterExpr: ((s_gmt_offset = -6) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 517120 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_gmt_offset = -6) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 103552 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_id (type: string), s_store_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 103664 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -68,9 +88,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 5 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Reducer 2 (GROUP, 481) - Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -78,81 +97,55 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66009029132 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 60202741740 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 5 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_day_name (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) + Statistics: Num rows: 525329897 Data size: 60202741740 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col5 + input vertices: + 1 Map 4 + Statistics: Num rows: 187574154 Data size: 36085560718 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col5, _col7, _col8 + input vertices: + 1 Map 5 + Statistics: Num rows: 37536846 Data size: 12029151074 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col8 (type: string), _col7 (type: string), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Tuesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 37536846 Data size: 12029151074 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7), sum(_col8) + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 176297 Data size: 171360684 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 176297 Data size: 171360684 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) Execution mode: vectorized - Reducer 2 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col5, _col7, _col8 - input vertices: - 1 Map 6 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col8 (type: string), _col7 (type: string), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Tuesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7), sum(_col8) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) - Reducer 3 + Reducer 2 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -160,25 +153,25 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3751 Data size: 3645972 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) sort order: +++++++++ - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3751 Data size: 3645972 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: decimal(17,2)), KEY.reducesinkkey3 (type: decimal(17,2)), KEY.reducesinkkey4 (type: decimal(17,2)), KEY.reducesinkkey5 (type: decimal(17,2)), KEY.reducesinkkey6 (type: decimal(17,2)), KEY.reducesinkkey7 (type: decimal(17,2)), KEY.reducesinkkey8 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3751 Data size: 3645972 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 97200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 97200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query44.q.out b/ql/src/test/results/clientpositive/perf/spark/query44.q.out index 6410815a0a..91defbcb81 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query44.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query44.q.out @@ -1,5 +1,5 @@ -Warning: Shuffle Join JOIN[20][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 7' is a cross product -Warning: Shuffle Join JOIN[49][tables = [$hdt$_3, $hdt$_4]] in Work 'Reducer 15' is a cross product +Warning: Map Join MAPJOIN[83][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[85][bigTable=?] in task 'Stage-4:MAPRED' is a cross product PREHOOK: query: explain select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing from(select * @@ -69,196 +69,173 @@ order by asceding.rnk limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4 + Stage-1 depends on stages: Stage-2 + Stage-5 is a root stage + Stage-4 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark Edges: - Reducer 10 <- Map 17 (GROUP, 100) - Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 1009), Reducer 16 (PARTITION-LEVEL SORT, 1009) - Reducer 14 <- Map 13 (GROUP, 199) - Reducer 15 <- Reducer 14 (PARTITION-LEVEL SORT, 1), Reducer 18 (PARTITION-LEVEL SORT, 1) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 1009) - Reducer 18 <- Map 17 (GROUP, 100) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1009), Reducer 8 (PARTITION-LEVEL SORT, 1009) - Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009) - Reducer 4 <- Reducer 3 (SORT, 1) - Reducer 6 <- Map 13 (GROUP, 199) - Reducer 7 <- Reducer 10 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1) - Reducer 8 <- Reducer 7 (PARTITION-LEVEL SORT, 1009) + Reducer 7 <- Map 6 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 6 Map Operator Tree: TableScan - alias: i1 - filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66010018768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + predicate: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) + Statistics: Num rows: 287946 Data size: 32999156 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int), i_product_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + expressions: ss_net_profit (type: decimal(7,2)) + outputColumnNames: _col1 + Statistics: Num rows: 287946 Data size: 32999156 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1), count(_col1) + keys: 410 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 258 Data size: 31992 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 258 Data size: 31992 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: i2 - filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_product_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Reducer 7 Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (_col1 / _col2) (type: decimal(37,22)) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-2 + Spark + Edges: + Reducer 4 <- Map 3 (GROUP, 4) + Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 2) +#### A masked pattern was here #### + Vertices: + Map 3 Map Operator Tree: TableScan alias: ss1 filterExpr: (ss_store_sk = 410) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66113679180 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_store_sk = 410) (type: boolean) - Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6399952 Data size: 734596648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_item_sk (type: int), ss_net_profit (type: decimal(7,2)) outputColumnNames: ss_item_sk, ss_net_profit - Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6399952 Data size: 734596648 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_net_profit), count(ss_net_profit) keys: ss_item_sk (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3199976 Data size: 396797024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3199976 Data size: 396797024 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized - Map 17 + Map 8 Map Operator Tree: TableScan - alias: store_sales - filterExpr: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: i2 + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 51282000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 51282000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_net_profit (type: decimal(7,2)) - outputColumnNames: _col1 - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1), count(_col1) - keys: 410 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) - Execution mode: vectorized - Reducer 10 + expressions: i_item_sk (type: int), i_product_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 51282000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + input vertices: + 1 Reducer 11 + Statistics: Num rows: 6951 Data size: 771561 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col3 (type: int) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (_col1 / _col2) (type: decimal(37,22)) - outputColumnNames: _col0 - Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(37,22)) - Reducer 12 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 14 + Local Work: + Map Reduce Local Work + Reducer 4 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62562 Data size: 7757688 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: decimal(37,22)) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10367842752596232 Data size: 1839676035841599918 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col1 > (0.9 * _col2)) (type: boolean) - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: 0 (type: int), _col1 (type: decimal(37,22)) - sort order: +- - Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: int) - Reducer 16 + Statistics: Num rows: 62562 Data size: 7257192 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Reducer 7 + Statistics: Num rows: 62562 Data size: 14264136 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 > (0.9 * _col2)) (type: boolean) + Statistics: Num rows: 20854 Data size: 4754712 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 0 (type: int), _col1 (type: decimal(37,22)) + sort order: ++ + Map-reduce partition columns: 0 (type: int) + Statistics: Num rows: 20854 Data size: 4754712 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: int) + Reducer 5 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: decimal(37,22)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20854 Data size: 2419064 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -268,7 +245,7 @@ STAGE PLANS: Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 DESC NULLS LAST + order by: _col1 ASC NULLS FIRST partition by: 0 raw input shape: window functions: @@ -279,134 +256,218 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20854 Data size: 2419064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((rank_window_0 < 11) and _col0 is not null) (type: boolean) - Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6951 Data size: 806316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), rank_window_0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Reducer 18 + Statistics: Num rows: 6951 Data size: 55608 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: i1 + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 51282000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 51282000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_product_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 51282000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + input vertices: + 1 Reducer 5 + Statistics: Num rows: 6951 Data size: 771561 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col3, _col5 + input vertices: + 1 Map 8 + Statistics: Num rows: 6951 Data size: 1515318 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: int), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6951 Data size: 1515318 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 6951 Data size: 1515318 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (_col1 / _col2) (type: decimal(37,22)) - outputColumnNames: _col0 - Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(37,22)) + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 1267180808338276 Data size: 224849298143006048 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col3 (type: int) - outputColumnNames: _col1, _col3, _col5 - Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: int), _col1 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string), _col2 (type: string) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1393898919384048 Data size: 247334233318131680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6951 Data size: 1515318 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 17700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 17700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 6 + + Stage: Stage-5 + Spark + Edges: + Reducer 13 <- Map 12 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 12 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66010018768 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) + Statistics: Num rows: 287946 Data size: 32999156 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_net_profit (type: decimal(7,2)) + outputColumnNames: _col1 + Statistics: Num rows: 287946 Data size: 32999156 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1), count(_col1) + keys: 410 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 258 Data size: 31992 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 258 Data size: 31992 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) + Execution mode: vectorized + Reducer 13 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: decimal(37,22)) - Reducer 7 + expressions: (_col1 / _col2) (type: decimal(37,22)) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-4 + Spark + Edges: + Reducer 10 <- Map 9 (GROUP, 4) + Reducer 11 <- Reducer 10 (PARTITION-LEVEL SORT, 2) +#### A masked pattern was here #### + Vertices: + Map 9 + Map Operator Tree: + TableScan + alias: ss1 + filterExpr: (ss_store_sk = 410) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66113679180 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_store_sk = 410) (type: boolean) + Statistics: Num rows: 6399952 Data size: 734596648 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_item_sk (type: int), ss_net_profit (type: decimal(7,2)) + outputColumnNames: ss_item_sk, ss_net_profit + Statistics: Num rows: 6399952 Data size: 734596648 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(ss_net_profit), count(ss_net_profit) + keys: ss_item_sk (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 3199976 Data size: 396797024 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 3199976 Data size: 396797024 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) + Execution mode: vectorized + Reducer 10 + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10367842752596232 Data size: 1839676035841599918 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col1 > (0.9 * _col2)) (type: boolean) - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: 0 (type: int), _col1 (type: decimal(37,22)) - sort order: ++ - Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: int) - Reducer 8 + Statistics: Num rows: 62562 Data size: 7757688 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 62562 Data size: 7257192 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Reducer 13 + Statistics: Num rows: 62562 Data size: 14264136 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 > (0.9 * _col2)) (type: boolean) + Statistics: Num rows: 20854 Data size: 4754712 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 0 (type: int), _col1 (type: decimal(37,22)) + sort order: +- + Map-reduce partition columns: 0 (type: int) + Statistics: Num rows: 20854 Data size: 4754712 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: int) + Reducer 11 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: decimal(37,22)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20854 Data size: 2419064 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -416,7 +477,7 @@ STAGE PLANS: Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col1 ASC NULLS FIRST + order by: _col1 DESC NULLS LAST partition by: 0 raw input shape: window functions: @@ -427,20 +488,18 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 3455947584198744 Data size: 613225345280533248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20854 Data size: 2419064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((rank_window_0 < 11) and _col0 is not null) (type: boolean) - Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6951 Data size: 806316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), rank_window_0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1151982528066248 Data size: 204408448426844416 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 6951 Data size: 55608 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query45.q.out b/ql/src/test/results/clientpositive/perf/spark/query45.q.out index cac3d05170..1e64853852 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query45.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query45.q.out @@ -39,40 +39,42 @@ select ca_zip, ca_county, sum(ws_sales_price) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 16 <- Map 15 (GROUP, 1) + Reducer 14 <- Map 13 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 15 + Map 13 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1144 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_id (type: string) outputColumnNames: i_item_id - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(i_item_id) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized - Reducer 16 + Reducer 14 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -81,126 +83,166 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 1 - Stage: Stage-1 + Stage: Stage-3 Spark Edges: - Reducer 11 <- Map 10 (GROUP, 6) - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 154), Map 14 (PARTITION-LEVEL SORT, 154) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 6 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 777), Reducer 9 (PARTITION-LEVEL SORT, 777) - Reducer 4 <- Reducer 3 (GROUP, 230) - Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 8 <- Map 7 (PARTITION-LEVEL SORT, 8), Reducer 11 (PARTITION-LEVEL SORT, 8) - Reducer 9 <- Reducer 13 (PARTITION-LEVEL SORT, 174), Reducer 8 (PARTITION-LEVEL SORT, 174) + Reducer 10 <- Map 9 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: customer - filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Execution mode: vectorized - Map 10 + Map 9 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1144 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_id (type: string) outputColumnNames: i_item_id - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: i_item_id (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 12 - Map Operator Tree: - TableScan - alias: web_sales - filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null and ws_item_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_customer_sk (type: int), ws_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 10 Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 12 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 65), Map 6 (PARTITION-LEVEL SORT, 65) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 137), Reducer 8 (PARTITION-LEVEL SORT, 137) + Reducer 4 <- Reducer 3 (GROUP, 12) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 8 <- Map 11 (PARTITION-LEVEL SORT, 10), Map 7 (PARTITION-LEVEL SORT, 10) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: customer + filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized + Map 11 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null and ws_item_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17852012776 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143930993 Data size: 17843127236 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_customer_sk (type: int), ws_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 143930993 Data size: 17843127236 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 12 + Statistics: Num rows: 10246864 Data size: 1225450924 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 10246864 Data size: 1225450924 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 6 Map Operator Tree: TableScan alias: customer_address filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7640000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7640000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_county (type: string), ca_zip (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7640000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7640000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 7 @@ -208,55 +250,33 @@ STAGE PLANS: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Execution mode: vectorized - Reducer 11 + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 1 Reducer 10 + Statistics: Num rows: 462000 Data size: 48048032 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048032 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col3 (type: boolean) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) - Reducer 13 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -266,12 +286,12 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col3, _col4 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15280000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15280000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string), _col4 (type: string) Reducer 3 Local Work: @@ -284,7 +304,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col6 (type: int) outputColumnNames: _col3, _col4, _col6, _col8, _col12 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246864 Data size: 4123608912 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -293,30 +313,30 @@ STAGE PLANS: 1 outputColumnNames: _col3, _col4, _col6, _col8, _col12, _col16, _col17 input vertices: - 1 Reducer 16 - Statistics: Num rows: 191667562 Data size: 29319594068 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 14 + Statistics: Num rows: 10246864 Data size: 4287558736 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col12 (type: decimal(7,2)), _col3 (type: string), _col4 (type: string), _col6 (type: string), _col16 (type: bigint), _col17 (type: bigint), _col8 (type: boolean) outputColumnNames: _col3, _col7, _col8, _col13, _col14, _col15, _col17 - Statistics: Num rows: 191667562 Data size: 29319594068 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246864 Data size: 4287558736 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or CASE WHEN ((_col14 = 0L)) THEN (false) WHEN (_col17 is not null) THEN (true) WHEN (_col13 is null) THEN (null) WHEN ((_col15 < _col14)) THEN (null) ELSE (false) END) (type: boolean) - Statistics: Num rows: 191667562 Data size: 29319594068 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246864 Data size: 4287558736 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: decimal(7,2)), _col7 (type: string), _col8 (type: string) outputColumnNames: _col3, _col7, _col8 - Statistics: Num rows: 191667562 Data size: 29319594068 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246864 Data size: 4287558736 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col8 (type: string), _col7 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 191667562 Data size: 29319594068 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4858260 Data size: 1452619740 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 191667562 Data size: 29319594068 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4858260 Data size: 1452619740 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(17,2)) Reducer 4 @@ -327,11 +347,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 95833781 Data size: 14659797034 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285780 Data size: 85448220 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 95833781 Data size: 14659797034 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285780 Data size: 85448220 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(17,2)) Reducer 5 @@ -340,34 +360,18 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 95833781 Data size: 14659797034 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285780 Data size: 85448220 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 15200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 29900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 15200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 29900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 8 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: boolean) - Reducer 9 Reduce Operator Tree: Join Operator condition map: @@ -376,12 +380,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col1, _col3, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246864 Data size: 2248289356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col6 (type: int) sort order: + Map-reduce partition columns: _col6 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10246864 Data size: 2248289356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: boolean), _col7 (type: decimal(7,2)) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/perf/spark/query46.q.out b/ql/src/test/results/clientpositive/perf/spark/query46.q.out index 2b925a344f..c81c7c7f4d 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query46.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query46.q.out @@ -76,19 +76,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 11 + Map 10 Map Operator Tree: TableScan alias: store filterExpr: ((s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 165288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 8245 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 8245 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col4 (type: int) @@ -96,19 +96,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 12 + Map 11 Map Operator Tree: TableScan alias: household_demographics filterExpr: (((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1855 Data size: 22260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1855 Data size: 22260 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -116,16 +116,35 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work + Map 9 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 783 Data size: 9396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 783 Data size: 9396 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 5 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 882), Reducer 9 (PARTITION-LEVEL SORT, 882) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 148), Map 5 (PARTITION-LEVEL SORT, 148) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 225), Reducer 8 (PARTITION-LEVEL SORT, 225) Reducer 4 <- Reducer 3 (SORT, 1) - Reducer 7 <- Map 10 (PARTITION-LEVEL SORT, 398), Map 6 (PARTITION-LEVEL SORT, 398) - Reducer 8 <- Map 13 (PARTITION-LEVEL SORT, 846), Reducer 7 (PARTITION-LEVEL SORT, 846) - Reducer 9 <- Reducer 8 (GROUP, 582) + Reducer 7 <- Map 12 (PARTITION-LEVEL SORT, 31), Map 6 (PARTITION-LEVEL SORT, 31) + Reducer 8 <- Reducer 7 (GROUP, 52) #### A masked pattern was here #### Vertices: Map 1 @@ -133,58 +152,39 @@ STAGE PLANS: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string) Execution mode: vectorized - Map 10 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 13 + Map 12 Map Operator Tree: TableScan alias: customer_address filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_city (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 5 @@ -192,19 +192,19 @@ STAGE PLANS: TableScan alias: current_addr filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_city (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 6 @@ -212,21 +212,53 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 136523505560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 457565061 Data size: 108452881252 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_hdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_coupon_amt (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Statistics: Num rows: 457565061 Data size: 108452881252 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 9 + Statistics: Num rows: 196204013 Data size: 42932884708 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7 + input vertices: + 1 Map 10 + Statistics: Num rows: 78993142 Data size: 14099798740 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col5, _col6, _col7 + input vertices: + 1 Map 11 + Statistics: Num rows: 20351707 Data size: 81407060 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 20351707 Data size: 81407060 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -236,12 +268,12 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col5 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22160000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22160000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col5 (type: string) Reducer 3 Reduce Operator Tree: @@ -252,18 +284,18 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col2, _col3, _col5, _col6, _col8, _col9, _col10 - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 12088913958 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col5 <> _col8) (type: boolean) - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 12088913958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col2 (type: string), _col5 (type: string), _col8 (type: string), _col6 (type: int), _col9 (type: decimal(17,2)), _col10 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 12088913958 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int) sort order: +++++ - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 12088913958 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) Reducer 4 @@ -272,56 +304,18 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: int), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 12088913958 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 59400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 59400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 7 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7 - input vertices: - 1 Map 11 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col5, _col6, _col7 - input vertices: - 1 Map 12 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Reducer 8 Reduce Operator Tree: Join Operator condition map: @@ -330,20 +324,20 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col17 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 1974115811 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col7) keys: _col1 (type: int), _col17 (type: string), _col3 (type: int), _col5 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 6532897955 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 6532897955 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) - Reducer 9 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -351,16 +345,16 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 6532897955 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col0 (type: int), _col1 (type: string), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 6532897951 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20351707 Data size: 6532897951 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/perf/spark/query47.q.out b/ql/src/test/results/clientpositive/perf/spark/query47.q.out index 690b1054c1..73b7b5b26e 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query47.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query47.q.out @@ -102,7 +102,10 @@ STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-6 + Stage-1 depends on stages: Stage-7 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -110,19 +113,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 10 + Map 9 Map Operator Tree: TableScan alias: store filterExpr: (s_store_sk is not null and s_store_name is not null and s_company_name is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_company_name is not null and s_store_name is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -135,19 +138,44 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 19 + Map 7 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 17 Map Operator Tree: TableScan alias: store filterExpr: (s_store_sk is not null and s_store_name is not null and s_company_name is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_company_name is not null and s_store_name is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -156,23 +184,48 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-4 + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 15 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-6 Spark #### A masked pattern was here #### Vertices: - Map 27 + Map 24 Map Operator Tree: TableScan alias: store filterExpr: (s_store_sk is not null and s_store_name is not null and s_company_name is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_company_name is not null and s_store_name is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -181,24 +234,46 @@ STAGE PLANS: Local Work: Map Reduce Local Work + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 22 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-1 Spark Edges: - Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 17 (PARTITION-LEVEL SORT, 398) - Reducer 13 <- Map 18 (PARTITION-LEVEL SORT, 442), Reducer 12 (PARTITION-LEVEL SORT, 442) - Reducer 14 <- Reducer 13 (GROUP, 529) - Reducer 15 <- Reducer 14 (PARTITION-LEVEL SORT, 265) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 265) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 8 (PARTITION-LEVEL SORT, 398) - Reducer 21 <- Map 20 (PARTITION-LEVEL SORT, 398), Map 25 (PARTITION-LEVEL SORT, 398) - Reducer 22 <- Map 26 (PARTITION-LEVEL SORT, 442), Reducer 21 (PARTITION-LEVEL SORT, 442) - Reducer 23 <- Reducer 22 (GROUP, 529) - Reducer 24 <- Reducer 23 (PARTITION-LEVEL SORT, 265) - Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 442), Reducer 2 (PARTITION-LEVEL SORT, 442) - Reducer 4 <- Reducer 3 (GROUP, 529) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 265) - Reducer 6 <- Reducer 16 (PARTITION-LEVEL SORT, 551), Reducer 24 (PARTITION-LEVEL SORT, 551), Reducer 5 (PARTITION-LEVEL SORT, 551) - Reducer 7 <- Reducer 6 (SORT, 1) + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 196), Map 16 (PARTITION-LEVEL SORT, 196) + Reducer 12 <- Reducer 11 (GROUP, 827) + Reducer 13 <- Reducer 12 (PARTITION-LEVEL SORT, 775) + Reducer 14 <- Reducer 13 (PARTITION-LEVEL SORT, 775) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 196), Map 23 (PARTITION-LEVEL SORT, 196) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 196), Map 8 (PARTITION-LEVEL SORT, 196) + Reducer 20 <- Reducer 19 (GROUP, 827) + Reducer 21 <- Reducer 20 (PARTITION-LEVEL SORT, 775) + Reducer 3 <- Reducer 2 (GROUP, 827) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 775) + Reducer 5 <- Reducer 14 (PARTITION-LEVEL SORT, 1009), Reducer 21 (PARTITION-LEVEL SORT, 1009), Reducer 4 (PARTITION-LEVEL SORT, 1009) + Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -206,198 +281,158 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 + input vertices: + 1 Map 7 + Statistics: Num rows: 216343183 Data size: 24949638264 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 216343183 Data size: 24949638264 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int) Execution mode: vectorized - Map 11 + Local Work: + Map Reduce Local Work + Map 10 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 17 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 + input vertices: + 1 Map 15 + Statistics: Num rows: 216343183 Data size: 24949638264 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 216343183 Data size: 24949638264 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int) Execution mode: vectorized - Map 18 + Local Work: + Map Reduce Local Work + Map 16 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 20 + Map 18 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 25 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 + input vertices: + 1 Map 22 + Statistics: Num rows: 216343183 Data size: 24949638264 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 216343183 Data size: 24949638264 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int) Execution mode: vectorized - Map 26 + Local Work: + Map Reduce Local Work + Map 23 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 8 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) - Execution mode: vectorized - Map 9 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Reducer 12 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int) - Reducer 13 + Reducer 11 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -408,7 +443,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col5, _col6, _col8, _col9 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 216343183 Data size: 65189470302 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -417,21 +452,21 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3, _col5, _col6, _col8, _col9, _col11, _col12 input vertices: - 1 Map 19 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + 1 Map 17 + Statistics: Num rows: 216343183 Data size: 103144060775 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 216343183 Data size: 105791816487 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 216343183 Data size: 105791816487 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col6 (type: decimal(17,2)) - Reducer 14 + Reducer 12 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -439,20 +474,20 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int) sort order: +++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col6 (type: decimal(17,2)) - Reducer 15 + Reducer 13 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey4 (type: int), VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -472,23 +507,23 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)) outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int) sort order: ++++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE value expressions: avg_window_0 (type: decimal(21,6)), _col6 (type: decimal(17,2)) - Reducer 16 + Reducer 14 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: decimal(21,6)), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 121860298560 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -509,60 +544,62 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 121860298560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 > 0) and (_col1 = 2000) and rank_window_1 is not null) (type: boolean) - Statistics: Num rows: 63887519 Data size: 5636175475 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 603460 Data size: 362679460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_1 (type: int), _col0 (type: decimal(21,6)), _col1 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: decimal(17,2)) outputColumnNames: rank_window_1, _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 63887519 Data size: 5636175475 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 603460 Data size: 362679460 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col0 > 0)) THEN (((abs((_col7 - _col0)) / _col0) > 0.1)) ELSE (null) END (type: boolean) - Statistics: Num rows: 31943759 Data size: 2818087693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301730 Data size: 182546650 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: string), _col3 (type: string), _col5 (type: string), _col6 (type: string), _col1 (type: int), _col2 (type: int), _col7 (type: decimal(17,2)), _col0 (type: decimal(21,6)), rank_window_1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 31943759 Data size: 2818087693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301730 Data size: 182546650 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col8 (type: int) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col8 (type: int) - Statistics: Num rows: 31943759 Data size: 2818087693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301730 Data size: 182546650 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: int), _col5 (type: int), _col6 (type: decimal(17,2)), _col7 (type: decimal(21,6)) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int) - Reducer 21 + Reducer 19 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int) - Reducer 22 + outputColumnNames: _col2, _col3, _col5, _col6, _col8, _col9 + Statistics: Num rows: 216343183 Data size: 65189470302 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col5, _col6, _col8, _col9, _col11, _col12 + input vertices: + 1 Map 24 + Statistics: Num rows: 216343183 Data size: 103144060775 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 216343183 Data size: 105791816487 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 216343183 Data size: 105791816487 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col6 (type: decimal(17,2)) + Reducer 2 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -573,7 +610,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col5, _col6, _col8, _col9 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 216343183 Data size: 65189470302 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -582,21 +619,21 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3, _col5, _col6, _col8, _col9, _col11, _col12 input vertices: - 1 Map 27 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + 1 Map 9 + Statistics: Num rows: 216343183 Data size: 103144060775 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 216343183 Data size: 105791816487 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 216343183 Data size: 105791816487 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col6 (type: decimal(17,2)) - Reducer 23 + Reducer 20 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -604,19 +641,19 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int) sort order: ++++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col6 (type: decimal(17,2)) - Reducer 24 + Reducer 21 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -637,55 +674,21 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: rank_window_0 is not null (type: boolean) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 98339841600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), (_col5 - 1) (type: int) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), (_col5 - 1) (type: int) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 98339841600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(17,2)) Reducer 3 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col5, _col6, _col8, _col9 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col5, _col6, _col8, _col9, _col11, _col12 - input vertices: - 1 Map 10 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - sort order: ++++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col6 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -693,19 +696,19 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col1 (type: int) sort order: ++++++ Map-reduce partition columns: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col6 (type: decimal(17,2)) - Reducer 5 + Reducer 4 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -726,21 +729,21 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: rank_window_0 is not null (type: boolean) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 99150891840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 98339841600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), (_col5 + 1) (type: int) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), (_col5 + 1) (type: int) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 202762560 Data size: 98339841600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(17,2)) - Reducer 6 + Reducer 5 Reduce Operator Tree: Join Operator condition map: @@ -751,30 +754,30 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col8 (type: int) 2 _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), (_col5 - 1) (type: int) outputColumnNames: _col4, _col6, _col10, _col11, _col12, _col13, _col19 - Statistics: Num rows: 843315280 Data size: 74397518857 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301730 Data size: 164744580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col6 (type: string), _col10 (type: int), _col11 (type: int), _col13 (type: decimal(21,6)), _col12 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col19 (type: decimal(17,2)), (_col12 - _col13) (type: decimal(22,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 843315280 Data size: 74397518857 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301730 Data size: 198538340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col7 (type: decimal(22,6)), _col2 (type: int) sort order: ++ - Statistics: Num rows: 843315280 Data size: 74397518857 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301730 Data size: 198538340 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: int), _col3 (type: decimal(21,6)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) - Reducer 7 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col2 (type: decimal(21,6)), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: decimal(17,2)), VALUE._col5 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 843315280 Data size: 74397518857 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 301730 Data size: 198538340 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 65800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 65800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query48.q.out b/ql/src/test/results/clientpositive/perf/spark/query48.q.out index 38ccff2a66..ef0326da54 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query48.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query48.q.out @@ -129,43 +129,59 @@ select sum (ss_quantity) ) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 2 Map Operator Tree: TableScan - alias: store - filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: - 0 _col3 (type: int) + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 3 + Map Operator Tree: + TableScan + alias: customer_demographics + filterExpr: ((cd_marital_status = 'M') and (cd_education_status = '4 yr Degree') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1861800 Data size: 340709400 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 29552 Data size: 5408016 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 29552 Data size: 5437568 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 133), Map 6 (PARTITION-LEVEL SORT, 133) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 147), Reducer 2 (PARTITION-LEVEL SORT, 147) - Reducer 4 <- Map 8 (PARTITION-LEVEL SORT, 319), Reducer 3 (PARTITION-LEVEL SORT, 319) - Reducer 5 <- Reducer 4 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -173,145 +189,116 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and ss_store_sk is not null and ss_cdemo_sk is not null and ss_addr_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 134219337972 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 159705893 Data size: 37214898936 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_cdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6 - Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 191998545 Data size: 16938167362 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) + Statistics: Num rows: 159705893 Data size: 37214898936 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col6 + input vertices: + 1 Map 2 + Statistics: Num rows: 57024544 Data size: 6379494836 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col6 + input vertices: + 1 Map 3 + Statistics: Num rows: 2570826 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 6 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: customer_demographics - filterExpr: ((cd_marital_status = 'M') and (cd_education_status = '4 yr Degree') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: cd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 465450 Data size: 179296539 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 8 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 5 <- Map 4 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 4 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 7480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20000000 Data size: 3740000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 20000000 Data size: 3740000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4, _col6, _col13 + input vertices: + 0 Map 1 + Statistics: Num rows: 1285413 Data size: 110545638 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((((_col13 = 'KY') or (_col13 = 'GA') or (_col13 = 'NM')) and _col6 BETWEEN 0 AND 2000) or (((_col13 = 'MT') or (_col13 = 'OR') or (_col13 = 'IN')) and _col6 BETWEEN 150 AND 3000) or (((_col13 = 'WI') or (_col13 = 'MO') or (_col13 = 'WV')) and _col6 BETWEEN 50 AND 25000)) (type: boolean) + Statistics: Num rows: 321351 Data size: 27636306 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4 + input vertices: + 1 Map 6 + Statistics: Num rows: 321351 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col4) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col6 - Statistics: Num rows: 211198404 Data size: 18631984502 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 211198404 Data size: 18631984502 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col6 - Statistics: Num rows: 232318249 Data size: 20495183396 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 232318249 Data size: 20495183396 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) - Reducer 4 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col4, _col6, _col13 - Statistics: Num rows: 255550079 Data size: 22544702224 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col13 = 'KY') or (_col13 = 'GA') or (_col13 = 'NM')) and _col6 BETWEEN 0 AND 2000) or (((_col13 = 'MT') or (_col13 = 'OR') or (_col13 = 'IN')) and _col6 BETWEEN 150 AND 3000) or (((_col13 = 'WI') or (_col13 = 'MO') or (_col13 = 'WV')) and _col6 BETWEEN 50 AND 25000)) (type: boolean) - Statistics: Num rows: 85183359 Data size: 7514900682 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4 - input vertices: - 1 Map 9 - Statistics: Num rows: 93701696 Data size: 8266390929 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col4) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) Reducer 5 Execution mode: vectorized Reduce Operator Tree: @@ -319,10 +306,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query49.q.out b/ql/src/test/results/clientpositive/perf/spark/query49.q.out index 16cc603f9a..98a69e6017 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query49.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query49.q.out @@ -251,189 +251,265 @@ select limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 13 <- Map 10 (PARTITION-LEVEL SORT, 12), Map 12 (PARTITION-LEVEL SORT, 12) - Reducer 14 <- Map 19 (PARTITION-LEVEL SORT, 21), Reducer 13 (PARTITION-LEVEL SORT, 21) - Reducer 15 <- Reducer 14 (GROUP, 14) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 7) - Reducer 17 <- Reducer 16 (PARTITION-LEVEL SORT, 7) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 6), Map 10 (PARTITION-LEVEL SORT, 6) - Reducer 21 <- Map 10 (PARTITION-LEVEL SORT, 15), Map 20 (PARTITION-LEVEL SORT, 15) - Reducer 22 <- Map 27 (PARTITION-LEVEL SORT, 28), Reducer 21 (PARTITION-LEVEL SORT, 28) - Reducer 23 <- Reducer 22 (GROUP, 18) - Reducer 24 <- Reducer 23 (PARTITION-LEVEL SORT, 9) - Reducer 25 <- Reducer 24 (PARTITION-LEVEL SORT, 9) - Reducer 3 <- Map 11 (PARTITION-LEVEL SORT, 10), Reducer 2 (PARTITION-LEVEL SORT, 10) - Reducer 4 <- Reducer 3 (GROUP, 7) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 4) - Reducer 6 <- Reducer 5 (PARTITION-LEVEL SORT, 4) - Reducer 7 <- Reducer 17 (GROUP, 7), Reducer 6 (GROUP, 7) - Reducer 8 <- Reducer 25 (GROUP, 10), Reducer 7 (GROUP, 10) - Reducer 9 <- Reducer 8 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 9 Map Operator Tree: TableScan - alias: ws - filterExpr: ((ws_net_profit > 1) and (ws_net_paid > 0) and (ws_quantity > 0) and ws_order_number is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2000) and (d_moy = 12) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ws_net_paid > 0) and (ws_net_profit > 1) and (ws_quantity > 0) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 5333432 Data size: 725192506 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_moy = 12) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_net_paid (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5333432 Data size: 725192506 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5333432 Data size: 725192506 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and (d_moy = 12) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 12) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 11 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 23 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2000) and (d_moy = 12) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 12) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 10), Map 17 (PARTITION-LEVEL SORT, 10) + Reducer 13 <- Reducer 12 (GROUP, 2) + Reducer 14 <- Reducer 13 (PARTITION-LEVEL SORT, 2) + Reducer 15 <- Reducer 14 (PARTITION-LEVEL SORT, 2) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 19), Map 24 (PARTITION-LEVEL SORT, 19) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 5), Map 10 (PARTITION-LEVEL SORT, 5) + Reducer 20 <- Reducer 19 (GROUP, 2) + Reducer 21 <- Reducer 20 (PARTITION-LEVEL SORT, 2) + Reducer 22 <- Reducer 21 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2) + Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 2) + Reducer 6 <- Reducer 15 (GROUP, 2), Reducer 5 (GROUP, 2) + Reducer 7 <- Reducer 22 (GROUP, 2), Reducer 6 (GROUP, 2) + Reducer 8 <- Reducer 7 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ws + filterExpr: ((ws_net_profit > 1) and (ws_net_paid > 0) and (ws_quantity > 0) and ws_order_number is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 34556343856 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((ws_net_paid > 0) and (ws_net_profit > 1) and (ws_quantity > 0) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 15996318 Data size: 3838639200 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_net_paid (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 15996318 Data size: 3838639200 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 9 + Statistics: Num rows: 438010 Data size: 53852024 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 438010 Data size: 53852024 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 10 Map Operator Tree: TableScan alias: wr filterExpr: ((wr_return_amt > 10000) and wr_order_number is not null and wr_item_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((wr_return_amt > 10000) and wr_item_sk is not null and wr_order_number is not null) (type: boolean) - Statistics: Num rows: 4799489 Data size: 441731394 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4799489 Data size: 570075356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_item_sk (type: int), wr_order_number (type: int), wr_return_quantity (type: int), wr_return_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4799489 Data size: 441731394 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4799489 Data size: 570075356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 4799489 Data size: 441731394 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4799489 Data size: 570075356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 12 + Map 11 Map Operator Tree: TableScan alias: cs filterExpr: ((cs_net_profit > 1) and (cs_net_paid > 0) and (cs_quantity > 0) and cs_order_number is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 68944803192 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cs_net_paid > 0) and (cs_net_profit > 1) and (cs_quantity > 0) and cs_item_sk is not null and cs_order_number is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 10666290 Data size: 1444429931 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31838858 Data size: 7622226792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_order_number (type: int), cs_quantity (type: int), cs_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10666290 Data size: 1444429931 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10666290 Data size: 1444429931 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Statistics: Num rows: 31838858 Data size: 7622226792 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 16 + Statistics: Num rows: 865646 Data size: 88877820 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 865646 Data size: 88877820 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) Execution mode: vectorized - Map 19 + Local Work: + Map Reduce Local Work + Map 17 Map Operator Tree: TableScan alias: cr filterExpr: ((cr_return_amount > 10000) and cr_order_number is not null and cr_item_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cr_return_amount > 10000) and cr_item_sk is not null and cr_order_number is not null) (type: boolean) - Statistics: Num rows: 9599627 Data size: 1019078226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9599627 Data size: 1168064292 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_item_sk (type: int), cr_order_number (type: int), cr_return_quantity (type: int), cr_return_amount (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9599627 Data size: 1019078226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9599627 Data size: 1168064292 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 9599627 Data size: 1019078226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9599627 Data size: 1168064292 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 20 + Map 18 Map Operator Tree: TableScan alias: sts filterExpr: ((ss_net_profit > 1) and (ss_net_paid > 0) and (ss_quantity > 0) and ss_ticket_number is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 132226521672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ss_net_paid > 0) and (ss_net_profit > 1) and (ss_quantity > 0) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61119617 Data size: 14030721704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Statistics: Num rows: 61119617 Data size: 14030721704 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 23 + Statistics: Num rows: 1673571 Data size: 13388684 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 1673571 Data size: 13388684 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) Execution mode: vectorized - Map 27 + Local Work: + Map Reduce Local Work + Map 24 Map Operator Tree: TableScan alias: sr filterExpr: ((sr_return_amt > 10000) and sr_ticket_number is not null and sr_item_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((sr_return_amt > 10000) and sr_item_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 19197050 Data size: 1487398277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19197050 Data size: 2302516152 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_item_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int), sr_return_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 19197050 Data size: 1487398277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19197050 Data size: 2302516152 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 19197050 Data size: 1487398277 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19197050 Data size: 2302516152 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Reducer 13 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 11732919 Data size: 1588872958 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 11732919 Data size: 1588872958 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 14 + Reducer 12 Reduce Operator Tree: Join Operator condition map: @@ -442,24 +518,24 @@ STAGE PLANS: 0 _col1 (type: int), _col2 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col1, _col3, _col4, _col11, _col12 - Statistics: Num rows: 12906211 Data size: 1747760291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 865646 Data size: 163540716 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), COALESCE(_col11,0) (type: int), COALESCE(_col3,0) (type: int), COALESCE(_col12,0) (type: decimal(12,2)), COALESCE(_col4,0) (type: decimal(12,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12906211 Data size: 1747760291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 865646 Data size: 163540716 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12906211 Data size: 1747760291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12906211 Data size: 1747760291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 15 + Reducer 13 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -467,20 +543,20 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), (CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) (type: decimal(35,20)) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 16 + Reducer 14 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint), VALUE._col3 (type: decimal(22,2)), VALUE._col4 (type: decimal(22,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -501,24 +577,24 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int), _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) outputColumnNames: rank_window_0, _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), (CAST( _col3 AS decimal(15,4)) / CAST( _col4 AS decimal(15,4))) (type: decimal(35,20)) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 415044 Basic stats: COMPLETE Column stats: COMPLETE value expressions: rank_window_0 (type: int), _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 17 + Reducer 15 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: decimal(22,2)), VALUE._col5 (type: decimal(22,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 421848 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -538,57 +614,51 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 6453105 Data size: 873880077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1701 Data size: 421848 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <= 10) or (rank_window_1 <= 10)) (type: boolean) - Statistics: Num rows: 4302070 Data size: 582586718 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1134 Data size: 281232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'catalog' (type: string), _col1 (type: int), (CAST( _col2 AS decimal(15,4)) / CAST( _col3 AS decimal(15,4))) (type: decimal(35,20)), _col0 (type: int), rank_window_1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4302070 Data size: 582586718 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1134 Data size: 243810 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col3 (type: int), _col4 (type: int), _col1 (type: int), _col2 (type: decimal(35,20)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6453220 Data size: 875080950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2276 Data size: 489340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) - Statistics: Num rows: 6453220 Data size: 875080950 Basic stats: COMPLETE Column stats: NONE - Reducer 2 + Statistics: Num rows: 2276 Data size: 489340 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 19 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 5866775 Data size: 797711773 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 5866775 Data size: 797711773 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 21 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 23466488 Data size: 2070220435 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 23466488 Data size: 2070220435 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 22 + 0 _col1 (type: int), _col2 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col1, _col3, _col4, _col11, _col12 + Statistics: Num rows: 1673571 Data size: 122910588 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), COALESCE(_col11,0) (type: int), COALESCE(_col3,0) (type: int), COALESCE(_col12,0) (type: decimal(12,2)), COALESCE(_col4,0) (type: decimal(12,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1673571 Data size: 122910588 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1), sum(_col2), sum(_col3), sum(_col4) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) + Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -597,24 +667,24 @@ STAGE PLANS: 0 _col1 (type: int), _col2 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col1, _col3, _col4, _col11, _col12 - Statistics: Num rows: 25813137 Data size: 2277242527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 438010 Data size: 77847864 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), COALESCE(_col11,0) (type: int), COALESCE(_col3,0) (type: int), COALESCE(_col12,0) (type: decimal(12,2)), COALESCE(_col4,0) (type: decimal(12,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 25813137 Data size: 2277242527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 438010 Data size: 77847864 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 25813137 Data size: 2277242527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 25813137 Data size: 2277242527 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 23 + Reducer 20 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -622,20 +692,20 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), (CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) (type: decimal(35,20)) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 24 + Reducer 21 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint), VALUE._col3 (type: decimal(22,2)), VALUE._col4 (type: decimal(22,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -656,24 +726,24 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int), _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) outputColumnNames: rank_window_0, _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), (CAST( _col3 AS decimal(15,4)) / CAST( _col4 AS decimal(15,4))) (type: decimal(35,20)) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: rank_window_0 (type: int), _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 25 + Reducer 22 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: decimal(22,2)), VALUE._col5 (type: decimal(22,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 425072 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -693,52 +763,26 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 12906568 Data size: 1138621219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 425072 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <= 10) or (rank_window_1 <= 10)) (type: boolean) - Statistics: Num rows: 8604378 Data size: 759080753 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1142 Data size: 283216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'store' (type: string), _col1 (type: int), (CAST( _col2 AS decimal(15,4)) / CAST( _col3 AS decimal(15,4))) (type: decimal(35,20)), _col0 (type: int), rank_window_1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 8604378 Data size: 759080753 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1142 Data size: 243246 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col3 (type: int), _col4 (type: int), _col1 (type: int), _col2 (type: decimal(35,20)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11830988 Data size: 1196621228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) - Statistics: Num rows: 11830988 Data size: 1196621228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int), _col2 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col1, _col3, _col4, _col11, _col12 - Statistics: Num rows: 6453452 Data size: 877482969 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), COALESCE(_col11,0) (type: int), COALESCE(_col3,0) (type: int), COALESCE(_col12,0) (type: decimal(12,2)), COALESCE(_col4,0) (type: decimal(12,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6453452 Data size: 877482969 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1), sum(_col2), sum(_col3), sum(_col4) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6453452 Data size: 877482969 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6453452 Data size: 877482969 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -746,20 +790,20 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), (CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) (type: decimal(35,20)) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint), VALUE._col3 (type: decimal(22,2)), VALUE._col4 (type: decimal(22,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -780,24 +824,24 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int), _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) outputColumnNames: rank_window_0, _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), (CAST( _col3 AS decimal(15,4)) / CAST( _col4 AS decimal(15,4))) (type: decimal(35,20)) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 418216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: rank_window_0 (type: int), _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(22,2)), _col4 (type: decimal(22,2)) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: decimal(22,2)), VALUE._col5 (type: decimal(22,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 425072 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -817,78 +861,78 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 3226726 Data size: 438741484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1714 Data size: 425072 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <= 10) or (rank_window_1 <= 10)) (type: boolean) - Statistics: Num rows: 2151150 Data size: 292494232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1142 Data size: 283216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'web' (type: string), _col1 (type: int), (CAST( _col2 AS decimal(15,4)) / CAST( _col3 AS decimal(15,4))) (type: decimal(35,20)), _col0 (type: int), rank_window_1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2151150 Data size: 292494232 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1142 Data size: 240962 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col3 (type: int), _col4 (type: int), _col1 (type: int), _col2 (type: decimal(35,20)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6453220 Data size: 875080950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2276 Data size: 489340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) - Statistics: Num rows: 6453220 Data size: 875080950 Basic stats: COMPLETE Column stats: NONE - Reducer 7 + Statistics: Num rows: 2276 Data size: 489340 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: decimal(35,20)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3226610 Data size: 437540475 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2276 Data size: 489340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: int), _col4 (type: decimal(35,20)), _col1 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3226610 Data size: 437540475 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2276 Data size: 489340 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col3 (type: int), _col4 (type: int), _col1 (type: int), _col2 (type: decimal(35,20)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 11830988 Data size: 1196621228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(35,20)) - Statistics: Num rows: 11830988 Data size: 1196621228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 8 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: decimal(35,20)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5915494 Data size: 598310614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: int), _col4 (type: decimal(35,20)), _col1 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5915494 Data size: 598310614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col3 (type: int), _col4 (type: int) sort order: +++ - Statistics: Num rows: 5915494 Data size: 598310614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: decimal(35,20)) - Reducer 9 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: decimal(35,20)), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 5915494 Data size: 598310614 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3418 Data size: 734870 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 10100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 10100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query5.q.out b/ql/src/test/results/clientpositive/perf/spark/query5.q.out index afcd4e5aff..8539b3a40c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query5.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query5.q.out @@ -255,7 +255,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -268,14 +269,14 @@ STAGE PLANS: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -288,19 +289,44 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 23 + Map 14 + Map Operator Tree: + TableScan + alias: catalog_page + filterExpr: cp_catalog_page_sk is not null (type: boolean) + Statistics: Num rows: 46000 Data size: 4784000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cp_catalog_page_sk is not null (type: boolean) + Statistics: Num rows: 46000 Data size: 4784000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cp_catalog_page_sk (type: int), cp_catalog_page_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 46000 Data size: 4784000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 22 Map Operator Tree: TableScan alias: web_site filterExpr: web_site_sk is not null (type: boolean) - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8736 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: web_site_sk is not null (type: boolean) - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8736 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: web_site_sk (type: int), web_site_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8736 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -312,15 +338,14 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 329), Map 14 (PARTITION-LEVEL SORT, 329), Map 9 (PARTITION-LEVEL SORT, 329) - Reducer 11 <- Map 15 (PARTITION-LEVEL SORT, 362), Reducer 10 (PARTITION-LEVEL SORT, 362) - Reducer 12 <- Reducer 11 (GROUP, 398) - Reducer 17 <- Map 14 (PARTITION-LEVEL SORT, 322), Map 16 (PARTITION-LEVEL SORT, 322), Reducer 20 (PARTITION-LEVEL SORT, 322) - Reducer 18 <- Reducer 17 (GROUP, 389) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 432), Map 6 (PARTITION-LEVEL SORT, 432), Map 7 (PARTITION-LEVEL SORT, 432) - Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 164), Map 21 (PARTITION-LEVEL SORT, 164) - Reducer 3 <- Reducer 2 (GROUP, 523) - Reducer 4 <- Reducer 12 (GROUP, 1009), Reducer 18 (GROUP, 1009), Reducer 3 (GROUP, 1009) + Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 1009), Map 13 (PARTITION-LEVEL SORT, 1009), Map 9 (PARTITION-LEVEL SORT, 1009) + Reducer 11 <- Reducer 10 (GROUP, 13) + Reducer 16 <- Map 13 (PARTITION-LEVEL SORT, 992), Map 15 (PARTITION-LEVEL SORT, 992), Reducer 19 (PARTITION-LEVEL SORT, 992) + Reducer 17 <- Reducer 16 (GROUP, 2) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 38), Map 20 (PARTITION-LEVEL SORT, 38) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1009), Map 6 (PARTITION-LEVEL SORT, 1009), Map 7 (PARTITION-LEVEL SORT, 1009) + Reducer 3 <- Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 11 (GROUP, 2), Reducer 17 (GROUP, 2), Reducer 3 (GROUP, 2) Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -329,138 +354,118 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 127618581836 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 116392994012 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int), ss_sold_date_sk (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 234066890940 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633586785 Data size: 55276696920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 578964757 Data size: 258089079660 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 13 + Map 12 Map Operator Tree: TableScan alias: catalog_returns filterExpr: (cr_returned_date_sk is not null and cr_catalog_page_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6549923644 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cr_catalog_page_sk is not null and cr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28221805 Data size: 6418675356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_catalog_page_sk (type: int), cr_returned_date_sk (type: int), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)), cr_return_amount (type: decimal(7,2)), cr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28221805 Data size: 12740359676 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788717 Data size: 42056843632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 313339499 Data size: 142583032264 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 14 + Map 13 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-08-18 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-08-18 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 15 - Map Operator Tree: - TableScan - alias: catalog_page - filterExpr: cp_catalog_page_sk is not null (type: boolean) - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cp_catalog_page_sk is not null (type: boolean) - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cp_catalog_page_sk (type: int), cp_catalog_page_id (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 16 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_sold_date_sk is not null and ws_web_site_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 33404306044 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_sold_date_sk is not null and ws_web_site_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930874 Data size: 33387651996 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_web_site_sk (type: int), ws_sold_date_sk (type: int), ws_ext_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930874 Data size: 65628167772 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 302405606 Data size: 41118416712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 278747306 Data size: 126963097864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized - Map 19 + Map 18 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_web_site_sk is not null and ws_item_sk is not null and ws_order_number is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1727888024 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_order_number is not null and ws_web_site_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966669 Data size: 1727456072 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_item_sk (type: int), ws_web_site_sk (type: int), ws_order_number (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966669 Data size: 1727456072 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col2 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966669 Data size: 1727456072 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized - Map 21 + Map 20 Map Operator Tree: TableScan alias: web_returns filterExpr: (wr_returned_date_sk is not null and wr_item_sk is not null and wr_order_number is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3250157212 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (wr_item_sk is not null and wr_order_number is not null and wr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13749816 Data size: 3103737632 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_returned_date_sk (type: int), wr_item_sk (type: int), wr_order_number (type: int), wr_return_amt (type: decimal(7,2)), wr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13749816 Data size: 3103737632 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13749816 Data size: 3103737632 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)) Execution mode: vectorized Map 6 @@ -468,19 +473,19 @@ STAGE PLANS: TableScan alias: store_returns filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 12893729500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53634860 Data size: 12007980080 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_store_sk (type: int), sr_returned_date_sk (type: int), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)), sr_return_amt (type: decimal(7,2)), sr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53634860 Data size: 24022188720 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633586785 Data size: 55276696920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 578964757 Data size: 258089079660 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized Map 7 @@ -488,41 +493,43 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-08-18 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-08-18 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 9 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_sold_date_sk is not null and cs_catalog_page_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 66640923564 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_catalog_page_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117694 Data size: 65976309132 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_catalog_page_sk (type: int), cs_sold_date_sk (type: int), cs_ext_sales_price (type: decimal(7,2)), cs_net_profit (type: decimal(7,2)), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117694 Data size: 129842672588 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788717 Data size: 42056843632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 313339499 Data size: 142583032264 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized Reducer 10 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -531,36 +538,30 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348467596 Data size: 46262528997 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 348467596 Data size: 46262528997 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) + Statistics: Num rows: 34813117 Data size: 15276159576 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col5, _col9 + input vertices: + 1 Map 14 + Statistics: Num rows: 34813117 Data size: 18631879860 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col4), sum(_col3), sum(_col5) + keys: _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 2835758 Data size: 1553995384 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2835758 Data size: 1553995384 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col5, _col9 - Statistics: Num rows: 383314363 Data size: 50888782999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col4), sum(_col3), sum(_col5) - keys: _col9 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 383314363 Data size: 50888782999 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 383314363 Data size: 50888782999 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 12 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -568,25 +569,25 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 191657181 Data size: 25444391433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 21287608 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'catalog channel' (type: string), concat('catalog_page', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), (_col3 - _col4) (type: decimal(18,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 191657181 Data size: 25444391433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) - Reducer 17 + Reducer 16 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -597,7 +598,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5 - Statistics: Num rows: 332646173 Data size: 45230259363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30969803 Data size: 13851130384 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -606,21 +607,21 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9 input vertices: - 1 Map 23 - Statistics: Num rows: 365910798 Data size: 49753286377 Basic stats: COMPLETE Column stats: NONE + 1 Map 22 + Statistics: Num rows: 30969803 Data size: 16824663276 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col4), sum(_col3), sum(_col5) keys: _col9 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 365910798 Data size: 49753286377 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3498 Data size: 1916904 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 365910798 Data size: 49753286377 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3498 Data size: 1916904 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 18 + Reducer 17 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -628,24 +629,41 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 182955399 Data size: 24876643188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 29044 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'web channel' (type: string), concat('web_site', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), (_col3 - _col4) (type: decimal(18,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 182955399 Data size: 24876643188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 32595 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) + Reducer 19 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + outputColumnNames: _col1, _col3, _col6, _col7 + Statistics: Num rows: 134816432 Data size: 31136049324 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), _col3 (type: int), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 134816432 Data size: 61334930092 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 278747306 Data size: 126963097864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 2 Local Work: Map Reduce Local Work @@ -657,7 +675,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5 - Statistics: Num rows: 696945478 Data size: 60804367929 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 64325014 Data size: 17869127348 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -667,36 +685,19 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col9 input vertices: 1 Map 8 - Statistics: Num rows: 766640042 Data size: 66884806171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 64325014 Data size: 24240896424 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col4), sum(_col3), sum(_col5) keys: _col9 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 766640042 Data size: 66884806171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78090 Data size: 42793320 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 766640042 Data size: 66884806171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78090 Data size: 42793320 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 20 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col1, _col3, _col6, _col7 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col3 (type: int), 0 (type: decimal(7,2)), 0 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 302405606 Data size: 41118416712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 3 Execution mode: vectorized Reduce Operator Tree: @@ -705,22 +706,22 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 383320021 Data size: 33442403085 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 822 Data size: 450456 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'store channel' (type: string), concat('store', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), (_col3 - _col4) (type: decimal(18,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 383320021 Data size: 33442403085 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 822 Data size: 507174 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2273797803 Data size: 251290313118 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) Reducer 4 @@ -731,16 +732,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 1136898901 Data size: 125645156503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24356442 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1136898901 Data size: 125645156503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1136898901 Data size: 125645156503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(27,2)), _col3 (type: decimal(27,2)), _col4 (type: decimal(28,2)) Reducer 5 @@ -749,13 +750,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(27,2)), VALUE._col1 (type: decimal(27,2)), VALUE._col2 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1136898901 Data size: 125645156503 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 11000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 61900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 11000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 61900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query50.q.out b/ql/src/test/results/clientpositive/perf/spark/query50.q.out index 0c4528fe8d..10dc29aa35 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query50.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query50.q.out @@ -116,7 +116,8 @@ limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -124,19 +125,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 10 + Map 7 + Map Operator Tree: + TableScan + alias: d1 + filterExpr: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 292196 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 292196 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 73049 Data size: 292196 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col7 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 1400640 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 1400640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_id (type: int), s_street_number (type: string), s_street_name (type: string), s_street_type (type: string), s_suite_number (type: string), s_city (type: string), s_county (type: string), s_state (type: string), s_zip (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 1400640 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col10 (type: int) @@ -145,14 +166,37 @@ STAGE PLANS: Local Work: Map Reduce Local Work + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: d2 + filterExpr: ((d_year = 2000) and (d_moy = 9) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 9) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 36), Map 7 (PARTITION-LEVEL SORT, 36) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 436), Reducer 2 (PARTITION-LEVEL SORT, 436) - Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 438), Reducer 3 (PARTITION-LEVEL SORT, 438) - Reducer 5 <- Reducer 4 (GROUP, 529) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 77), Map 6 (PARTITION-LEVEL SORT, 77) + Reducer 3 <- Reducer 2 (GROUP, 81) + Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -160,112 +204,54 @@ STAGE PLANS: TableScan alias: store_returns filterExpr: (sr_ticket_number is not null and sr_item_sk is not null and sr_customer_sk is not null and sr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 905340432 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53632139 Data size: 843104260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_customer_sk (type: int), sr_ticket_number (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: d2 - filterExpr: ((d_year = 2000) and (d_moy = 9) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 9) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53632139 Data size: 843104260 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 5 + Statistics: Num rows: 1339446 Data size: 10715576 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) + sort order: +++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col3 (type: int) + Statistics: Num rows: 1339446 Data size: 10715576 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: vectorized - Map 8 + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_ticket_number is not null and ss_item_sk is not null and ss_customer_sk is not null and ss_store_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 11208924312 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501694138 Data size: 9763010828 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501694138 Data size: 9763010828 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) sort order: +++ Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501694138 Data size: 9763010828 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col3 (type: int) Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: d1 - filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) - sort order: +++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int), _col2 (type: int), _col3 (type: int) - 1 _col1 (type: int), _col2 (type: int), _col4 (type: int) - outputColumnNames: _col0, _col7, _col10 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col7 (type: int) - sort order: + - Map-reduce partition columns: _col7 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col10 (type: int) - Reducer 4 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -273,38 +259,48 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col7 (type: int) - 1 _col0 (type: int) + 0 _col1 (type: int), _col2 (type: int), _col3 (type: int) + 1 _col1 (type: int), _col2 (type: int), _col4 (type: int) outputColumnNames: _col0, _col7, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11945216 Data size: 42423092 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: int) + 0 _col7 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col7, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 + outputColumnNames: _col0, _col7, _col10 input vertices: - 1 Map 10 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col14 (type: string), _col15 (type: int), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: string), CASE WHEN (((_col0 - _col7) <= 30)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 30) and ((_col0 - _col7) <= 60))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 60) and ((_col0 - _col7) <= 90))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 90) and ((_col0 - _col7) <= 120))) THEN (1) ELSE (0) END (type: int), CASE WHEN (((_col0 - _col7) > 120)) THEN (1) ELSE (0) END (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14) - keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) - mode: hash + 1 Map 7 + Statistics: Num rows: 11945216 Data size: 42423092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col10 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col7, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 + input vertices: + 1 Map 8 + Statistics: Num rows: 11945216 Data size: 9813609728 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col14 (type: string), _col15 (type: int), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: string), CASE WHEN (((_col0 - _col7) <= 30)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 30) and ((_col0 - _col7) <= 60))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 60) and ((_col0 - _col7) <= 90))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col0 - _col7) > 90) and ((_col0 - _col7) <= 120))) THEN (1) ELSE (0) END (type: int), CASE WHEN (((_col0 - _col7) > 120)) THEN (1) ELSE (0) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) - sort order: ++++++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint) - Reducer 5 + Statistics: Num rows: 11945216 Data size: 9813609728 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14) + keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 11945216 Data size: 10248995280 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) + sort order: ++++++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) + Statistics: Num rows: 11945216 Data size: 10248995280 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint) + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -312,26 +308,26 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: string), KEY._col8 (type: string), KEY._col9 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11945216 Data size: 10248995280 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) sort order: ++++++++++ - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11945216 Data size: 10248995280 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: string), KEY.reducesinkkey7 (type: string), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11945216 Data size: 10248995280 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 85800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 85800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query51.q.out b/ql/src/test/results/clientpositive/perf/spark/query51.q.out index c0bb72b2bf..c5517f5c2e 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query51.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query51.q.out @@ -102,14 +102,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -127,14 +127,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -146,11 +146,11 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 437) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 303), Reducer 8 (PARTITION-LEVEL SORT, 303) - Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 241) + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 101) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 119), Reducer 8 (PARTITION-LEVEL SORT, 119) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 1009) Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 8 <- Map 7 (GROUP PARTITION-LEVEL SORT, 169) + Reducer 8 <- Map 7 (GROUP PARTITION-LEVEL SORT, 27) #### A masked pattern was here #### Vertices: Map 1 @@ -158,14 +158,14 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66112679912 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550076554 Data size: 63137692296 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550076554 Data size: 63137692296 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -175,18 +175,18 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col4 input vertices: 1 Map 6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 10061757972 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col1 (type: int), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 12834241140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 12834241140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized Local Work: @@ -196,14 +196,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 17276145620 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271850184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271850184 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -213,18 +213,18 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col4 input vertices: 1 Map 9 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 3354966720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col1 (type: int), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 3358997040 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 3358997040 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized Local Work: @@ -236,7 +236,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56414316 Data size: 11847006360 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -256,16 +256,16 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: ROWS PRECEDING(MAX)~CURRENT - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56414316 Data size: 11847006360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), sum_window_0 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56414316 Data size: 11847006360 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56414316 Data size: 11847006360 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(27,2)) Reducer 3 Reduce Operator Tree: @@ -276,19 +276,19 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111182802024 Data size: 46696776850080 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END (type: int), CASE WHEN (_col4 is not null) THEN (_col4) ELSE (_col1) END (type: string) sort order: ++ Map-reduce partition columns: CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END (type: int) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111182802024 Data size: 46696776850080 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: decimal(27,2)), _col3 (type: int), _col4 (type: string), _col5 (type: decimal(27,2)) Reducer 4 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: decimal(27,2)), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111182802024 Data size: 46696776850080 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -314,18 +314,18 @@ STAGE PLANS: name: max window function: GenericUDAFMaxEvaluator window frame: ROWS PRECEDING(MAX)~CURRENT - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111182802024 Data size: 46696776850080 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (max_window_0 > max_window_1) (type: boolean) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37060934008 Data size: 15565592283360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END (type: int), CASE WHEN (_col4 is not null) THEN (_col4) ELSE (_col1) END (type: string), _col5 (type: decimal(27,2)), _col2 (type: decimal(27,2)), max_window_0 (type: decimal(27,2)), max_window_1 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37060934008 Data size: 23570754029088 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37060934008 Data size: 23570754029088 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(27,2)), _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(27,2)) Reducer 5 @@ -334,13 +334,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(27,2)), VALUE._col1 (type: decimal(27,2)), VALUE._col2 (type: decimal(27,2)), VALUE._col3 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37060934008 Data size: 23570754029088 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 63600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 63600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -352,7 +352,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 3358997040 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -372,16 +372,16 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: ROWS PRECEDING(MAX)~CURRENT - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 3358997040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), sum_window_0 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 3358997040 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 3358997040 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(27,2)) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/perf/spark/query52.q.out b/ql/src/test/results/clientpositive/perf/spark/query52.q.out index f6c4fc8337..3e1bb0bf3f 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query52.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query52.q.out @@ -41,117 +41,112 @@ select dt.d_year limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 6 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 440), Reducer 2 (PARTITION-LEVEL SORT, 440) - Reducer 4 <- Reducer 3 (GROUP, 481) - Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 6 + Map 4 Map Operator Tree: TableScan alias: dt filterExpr: ((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: item filterExpr: ((i_manager_id = 1) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 51734956 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manager_id = 1) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 821160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand_id (type: int), i_brand (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 7333 Data size: 821228 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66112867736 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 15062131 Data size: 60248636 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col7, _col8 + input vertices: + 1 Map 5 + Statistics: Num rows: 2301098 Data size: 239314236 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col7 (type: int), _col8 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col7 (type: int), _col8 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -159,30 +154,30 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: decimal(17,2)), _col0 (type: int) sort order: -+ - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1998 (type: int), _col0 (type: int), _col1 (type: string), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query53.q.out b/ql/src/test/results/clientpositive/perf/spark/query53.q.out index ec9350e353..97d3cd2316 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query53.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query53.q.out @@ -62,19 +62,59 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 4 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 133975396 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 694 Data size: 201256 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_manufact_id (type: int) + outputColumnNames: _col0, _col4 + Statistics: Num rows: 694 Data size: 201256 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 5 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 317 Data size: 3804 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_qoy (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 317 Data size: 3804 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -86,10 +126,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 403), Map 6 (PARTITION-LEVEL SORT, 403) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438) - Reducer 4 <- Reducer 3 (GROUP PARTITION-LEVEL SORT, 529) - Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -97,123 +135,71 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 6 - Map Operator Tree: - TableScan - alias: item - filterExpr: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_manufact_id (type: int) - outputColumnNames: _col0, _col4 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_qoy (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3, _col8 + input vertices: + 1 Map 4 + Statistics: Num rows: 7595537 Data size: 30382264 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col8, _col11 + input vertices: + 1 Map 5 + Statistics: Num rows: 1318594 Data size: 10548864 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col8, _col11 + input vertices: + 1 Map 6 + Statistics: Num rows: 1318594 Data size: 10548860 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col8 (type: int), _col11 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 605 Data size: 72600 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 605 Data size: 72600 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col8 (type: int) - Reducer 3 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col8, _col11 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col8, _col11 - input vertices: - 1 Map 8 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col8 (type: int), _col11 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 4 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 72000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 69600 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -233,36 +219,36 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 69600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col2 (type: decimal(17,2)) outputColumnNames: avg_window_0, _col0, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 600 Data size: 69600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((avg_window_0 > 0)) THEN (((abs((_col2 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END (type: boolean) - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 68400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: decimal(17,2)), avg_window_0 (type: decimal(21,6)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 68400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: decimal(21,6)), _col1 (type: decimal(17,2)), _col0 (type: int) sort order: +++ - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 68400 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey2 (type: int), KEY.reducesinkkey1 (type: decimal(17,2)), KEY.reducesinkkey0 (type: decimal(21,6)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 300 Data size: 68400 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query54.q.out b/ql/src/test/results/clientpositive/perf/spark/query54.q.out index 241d6d8e1f..e840e51afd 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query54.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query54.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join JOIN[84][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Work 'Reducer 4' is a cross product -Warning: Shuffle Join JOIN[115][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 5' is a cross product -Warning: Map Join MAPJOIN[145][bigTable=?] in task 'Stage-1:MAPRED' is a cross product Warning: Map Join MAPJOIN[144][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[145][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[146][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[147][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain with my_customers as ( select distinct c_customer_sk @@ -113,628 +113,548 @@ with my_customers as ( limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 + Stage-5 is a root stage + Stage-4 depends on stages: Stage-5 + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark - Edges: - Reducer 28 <- Map 27 (GROUP, 2) - Reducer 29 <- Reducer 28 (GROUP, 1) -#### A masked pattern was here #### - Vertices: - Map 27 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (d_month_seq + 3) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 28 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 29 - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 - - Stage: Stage-3 - Spark - Edges: - Reducer 23 <- Map 22 (GROUP, 2) - Reducer 24 <- Reducer 23 (GROUP, 1) -#### A masked pattern was here #### - Vertices: - Map 22 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (d_month_seq + 1) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 23 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 24 - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 - - Stage: Stage-4 + Stage: Stage-5 Spark #### A masked pattern was here #### Vertices: Map 12 Map Operator Tree: TableScan - alias: store - filterExpr: (s_county is not null and s_state is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: ((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (s_county is not null and s_state is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + predicate: ((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 453 Data size: 84258 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_county (type: string), s_state (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + expressions: i_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 453 Data size: 86070 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: - 0 _col1 (type: string), _col2 (type: string) - 1 _col0 (type: string), _col1 (type: string) + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-4 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 654), Reducer 17 (PARTITION-LEVEL SORT, 654) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 458), Map 18 (PARTITION-LEVEL SORT, 458), Map 19 (PARTITION-LEVEL SORT, 458) - Reducer 15 <- Map 20 (PARTITION-LEVEL SORT, 505), Reducer 14 (PARTITION-LEVEL SORT, 505) - Reducer 16 <- Map 21 (PARTITION-LEVEL SORT, 1009), Reducer 15 (PARTITION-LEVEL SORT, 1009) - Reducer 17 <- Reducer 16 (GROUP, 610) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 26 <- Map 25 (GROUP, 2) - Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 772), Reducer 2 (PARTITION-LEVEL SORT, 772) - Reducer 31 <- Map 30 (GROUP, 2) - Reducer 4 <- Reducer 26 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1) - Reducer 5 <- Reducer 31 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1) - Reducer 6 <- Reducer 5 (GROUP, 1009) - Reducer 7 <- Reducer 6 (GROUP, 1009) - Reducer 8 <- Reducer 7 (SORT, 1) + Reducer 9 <- Map 10 (PARTITION-LEVEL SORT, 41), Map 11 (PARTITION-LEVEL SORT, 41), Map 8 (PARTITION-LEVEL SORT, 41) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized Map 10 - Map Operator Tree: - TableScan - alias: customer_address - filterExpr: (ca_address_sk is not null and ca_county is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ca_address_sk is not null and ca_county is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_address_sk (type: int), ca_county (type: string), ca_state (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string), _col2 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0 - input vertices: - 1 Map 12 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Map 13 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_bill_customer_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) - Execution mode: vectorized - Map 18 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null and ws_bill_customer_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1727745288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1726885332 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_item_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1726885332 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 429048824 Data size: 5136897360 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized - Map 19 + Map 11 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 20 + Map 8 Map Operator Tree: TableScan - alias: item - filterExpr: ((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_bill_customer_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 3444361236 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 285117831 Data size: 3410012028 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 285117831 Data size: 3410012028 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 429048824 Data size: 5136897360 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized - Map 21 + Reducer 9 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 11665117 Data size: 81779564 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 12 + Statistics: Num rows: 110092 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-3 + Spark + Edges: + Reducer 14 <- Map 13 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 13 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col9, _col10 + input vertices: + 0 Reducer 9 + Statistics: Num rows: 110092 Data size: 880736 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col10 (type: int), _col9 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55046 Data size: 440368 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 55046 Data size: 440368 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 + Map Operator Tree: + TableScan + alias: store + filterExpr: (s_county is not null and s_state is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 313536 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (s_county is not null and s_state is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 313536 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: s_county (type: string), s_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1704 Data size: 313536 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string), _col2 (type: string) + 1 _col0 (type: string), _col1 (type: string) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 14 Execution mode: vectorized - Map 25 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55046 Data size: 440368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55046 Data size: 440368 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + + Stage: Stage-2 + Spark + Edges: + Reducer 16 <- Map 15 (GROUP, 2) + Reducer 17 <- Reducer 16 (GROUP, 1) + Reducer 19 <- Map 15 (GROUP, 2) + Reducer 21 <- Map 20 (GROUP, 2) + Reducer 22 <- Reducer 21 (GROUP, 1) + Reducer 24 <- Map 20 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 15 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (d_month_seq + 1) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 30 + Map 20 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_moy = 3)) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 3) and (d_year = 1999)) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (d_month_seq + 3) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 9 + Map 5 Map Operator Tree: TableScan alias: date_dim filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_month_seq (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col5 - Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col5 (type: int) - sort order: + - Map-reduce partition columns: _col5 (type: int) - Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE - Reducer 14 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 522710951 Data size: 70881569741 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 522710951 Data size: 70881569741 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Map 6 + Map Operator Tree: + TableScan + alias: customer_address + filterExpr: (ca_address_sk is not null and ca_county is not null and ca_state is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 7520000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ca_address_sk is not null and ca_county is not null and ca_state is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 7520000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int), ca_county (type: string), ca_state (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 40000000 Data size: 7520000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string), _col2 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 7 + Statistics: Num rows: 39720279 Data size: 158881116 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col5 + input vertices: + 1 Reducer 14 + Statistics: Num rows: 55046 Data size: 220184 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col5 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col9, _col10 - Statistics: Num rows: 574982058 Data size: 77969728405 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col10 (type: int), _col9 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 574982058 Data size: 77969728405 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 574982058 Data size: 77969728405 Basic stats: COMPLETE Column stats: NONE - Reducer 17 Execution mode: vectorized Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int) + keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 287491029 Data size: 38984864202 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 287491029 Data size: 38984864202 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 287491029 Data size: 38984864202 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) - Reducer 26 + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 17 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int) + aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Reducer 3 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 + Reducer 19 + Execution mode: vectorized Local Work: Map Reduce Local Work Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col5 (type: int) - outputColumnNames: _col2, _col4, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator keys: 0 1 - outputColumnNames: _col2, _col4, _col10 - input vertices: - 1 Reducer 24 - Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int), _col10 (type: int) - Reducer 31 + Reducer 21 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Reducer 4 + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 22 + Execution mode: vectorized Local Work: Map Reduce Local Work Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col2, _col4, _col10, _col13 - Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col2 (type: decimal(7,2)), _col4 (type: int), _col13 (type: int) - outputColumnNames: _col0, _col4, _col11, _col13 - Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col4, _col11, _col13 - input vertices: - 1 Reducer 29 - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col4 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: decimal(7,2)), _col2 (type: int), _col3 (type: int) - Reducer 5 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 58108714324214428 Data size: 9223372036854775807 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: _col2 BETWEEN _col3 AND _col4 (type: boolean) - Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: decimal(7,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 6 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 + Reducer 24 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66009206448 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 525327388 Data size: 60202615996 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 525327388 Data size: 60202615996 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4 + input vertices: + 1 Map 5 + Statistics: Num rows: 525327388 Data size: 60297172284 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col5 (type: int) + outputColumnNames: _col2, _col4, _col10 + input vertices: + 1 Map 6 + Statistics: Num rows: 8989304 Data size: 71914544 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col2, _col4, _col10 + input vertices: + 1 Reducer 17 + Statistics: Num rows: 8989304 Data size: 71914544 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col2, _col4, _col10, _col13 + input vertices: + 1 Reducer 19 + Statistics: Num rows: 224732600 Data size: 26860040464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col10 (type: int), _col2 (type: decimal(7,2)), _col4 (type: int), _col13 (type: int) + outputColumnNames: _col0, _col4, _col11, _col13 + Statistics: Num rows: 224732600 Data size: 26860040464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col4, _col11, _col13 + input vertices: + 1 Reducer 22 + Statistics: Num rows: 224732600 Data size: 26860040464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col4 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 224732600 Data size: 26860040464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + input vertices: + 1 Reducer 24 + Statistics: Num rows: 5618315000 Data size: 718137518064 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 BETWEEN _col3 AND _col4 (type: boolean) + Statistics: Num rows: 624257222 Data size: 79793057584 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: decimal(7,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 624257222 Data size: 79793057584 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 312 Data size: 36192 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 312 Data size: 36192 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 2 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -742,24 +662,24 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3228261906900801 Data size: 512409557603043008 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger((_col1 / 50)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3228261906900801 Data size: 512409557603043008 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3228261906900801 Data size: 512409557603043008 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3228261906900801 Data size: 512409557603043008 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 7 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -767,30 +687,30 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1614130953450400 Data size: 256204778801521408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), (_col0 * 50) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1614130953450400 Data size: 256204778801521408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: bigint) sort order: ++ - Statistics: Num rows: 1614130953450400 Data size: 256204778801521408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: int) - Reducer 8 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1614130953450400 Data size: 256204778801521408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 15800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 15800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query55.q.out b/ql/src/test/results/clientpositive/perf/spark/query55.q.out index afcd67c203..6ab1f855bc 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query55.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query55.q.out @@ -25,117 +25,112 @@ select i_brand_id brand_id, i_brand brand, limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 6 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 440), Reducer 2 (PARTITION-LEVEL SORT, 440) - Reducer 4 <- Reducer 3 (GROUP, 481) - Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 6 + Map 4 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: item filterExpr: ((i_manager_id = 36) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 51734956 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manager_id = 36) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 821160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand_id (type: int), i_brand (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 7333 Data size: 821228 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66112867736 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 15062131 Data size: 60248636 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col7, _col8 + input vertices: + 1 Map 5 + Statistics: Num rows: 2301098 Data size: 239314236 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col7 (type: int), _col8 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col7 (type: int), _col8 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -143,30 +138,30 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401322 Data size: 86685544 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: decimal(17,2)), _col0 (type: int) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401322 Data size: 88290824 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: decimal(17,2)), _col3 (type: int) sort order: -+ - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401322 Data size: 88290824 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 401322 Data size: 88290824 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 22000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query56.q.out b/ql/src/test/results/clientpositive/perf/spark/query56.q.out index e03574f4ab..59a049dfed 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query56.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query56.q.out @@ -133,31 +133,66 @@ where i_color in ('orchid','chiffon','lace')) limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-6 + Stage-7 depends on stages: Stage-5 + Stage-9 depends on stages: Stage-7 + Stage-8 depends on stages: Stage-9 + Stage-10 depends on stages: Stage-8 + Stage-1 depends on stages: Stage-10 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark Edges: - Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 11 <- Map 13 (PARTITION-LEVEL SORT, 596), Reducer 10 (PARTITION-LEVEL SORT, 596) - Reducer 15 <- Map 1 (PARTITION-LEVEL SORT, 8), Reducer 19 (PARTITION-LEVEL SORT, 8) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 375), Reducer 22 (PARTITION-LEVEL SORT, 375) - Reducer 17 <- Reducer 16 (GROUP, 406) - Reducer 19 <- Map 18 (GROUP, 6) - Reducer 21 <- Map 12 (PARTITION-LEVEL SORT, 305), Map 20 (PARTITION-LEVEL SORT, 305) - Reducer 22 <- Map 13 (PARTITION-LEVEL SORT, 494), Reducer 21 (PARTITION-LEVEL SORT, 494) - Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 8), Reducer 30 (PARTITION-LEVEL SORT, 8) - Reducer 27 <- Reducer 26 (PARTITION-LEVEL SORT, 191), Reducer 33 (PARTITION-LEVEL SORT, 191) - Reducer 28 <- Reducer 27 (GROUP, 204) - Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 487), Reducer 15 (PARTITION-LEVEL SORT, 487) - Reducer 30 <- Map 18 (GROUP, 6) - Reducer 32 <- Map 31 (PARTITION-LEVEL SORT, 154), Map 34 (PARTITION-LEVEL SORT, 154) - Reducer 33 <- Map 35 (PARTITION-LEVEL SORT, 327), Reducer 32 (PARTITION-LEVEL SORT, 327) - Reducer 4 <- Reducer 3 (GROUP, 529) - Reducer 5 <- Reducer 17 (GROUP, 569), Reducer 28 (GROUP, 569), Reducer 4 (GROUP, 569) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 3 <- Map 2 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 2 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_color) IN ('orchid', 'chiffon', 'lace') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 87318000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_color) IN ('orchid', 'chiffon', 'lace') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 23100 Data size: 4365900 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_id (type: string) + outputColumnNames: i_item_id + Statistics: Num rows: 23100 Data size: 4365900 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: i_item_id (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 3 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-2 + Spark #### A masked pattern was here #### Vertices: Map 1 @@ -165,276 +200,453 @@ STAGE PLANS: TableScan alias: item filterExpr: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 3 + Statistics: Num rows: 17170 Data size: 1785680 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and (d_moy = 1) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark + Edges: + Reducer 13 <- Map 12 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 12 Map Operator Tree: TableScan - alias: customer_address - filterExpr: ((ca_gmt_offset = -8) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: ((i_color) IN ('orchid', 'chiffon', 'lace') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 87318000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ca_gmt_offset = -8) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + predicate: ((i_color) IN ('orchid', 'chiffon', 'lace') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 23100 Data size: 4365900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ca_address_sk (type: int) + expressions: i_item_id (type: string) + outputColumnNames: i_item_id + Statistics: Num rows: 23100 Data size: 4365900 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: i_item_id (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 13 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 + Map Operator Tree: + TableScan + alias: item + filterExpr: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_item_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 13 + Statistics: Num rows: 17170 Data size: 1785680 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 17 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2000) and (d_moy = 1) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 18 + Local Work: + Map Reduce Local Work + + Stage: Stage-9 + Spark + Edges: + Reducer 21 <- Map 20 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 20 Map Operator Tree: TableScan alias: item filterExpr: ((i_color) IN ('orchid', 'chiffon', 'lace') and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 87318000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_color) IN ('orchid', 'chiffon', 'lace') and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 23100 Data size: 4365900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_id (type: string) outputColumnNames: i_item_id - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 23100 Data size: 4365900 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: i_item_id (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 20 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: (cs_sold_date_sk is not null and cs_bill_addr_sk is not null and cs_item_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 21 Execution mode: vectorized - Map 25 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 11550 Data size: 1155000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 19 Map Operator Tree: TableScan alias: item filterExpr: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 21 + Statistics: Num rows: 17170 Data size: 1785680 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) Execution mode: vectorized - Map 31 + Local Work: + Map Reduce Local Work + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 25 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null and ws_item_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2000) and (d_moy = 1) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_moy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 34 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 15 <- Map 10 (PARTITION-LEVEL SORT, 14), Map 14 (PARTITION-LEVEL SORT, 14) + Reducer 16 <- Reducer 15 (GROUP, 2) + Reducer 23 <- Map 22 (PARTITION-LEVEL SORT, 11), Map 26 (PARTITION-LEVEL SORT, 11) + Reducer 24 <- Reducer 23 (GROUP, 2) + Reducer 5 <- Map 10 (PARTITION-LEVEL SORT, 8), Map 4 (PARTITION-LEVEL SORT, 8) + Reducer 6 <- Reducer 5 (GROUP, 2) + Reducer 7 <- Reducer 16 (GROUP, 2), Reducer 24 (GROUP, 2), Reducer 6 (GROUP, 2) + Reducer 8 <- Reducer 7 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 2000) and (d_moy = 1) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: customer_address + filterExpr: ((ca_gmt_offset = -8) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_moy = 1) and (d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + predicate: ((ca_gmt_offset = -8) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) + expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Map 14 + Map Operator Tree: + TableScan + alias: catalog_sales + filterExpr: (cs_sold_date_sk is not null and cs_bill_addr_sk is not null and cs_item_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 35538021432 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 285117733 Data size: 35183603168 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 285117733 Data size: 35183603168 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 17 + Statistics: Num rows: 7751872 Data size: 764931900 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 7751872 Data size: 764931900 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 22 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null and ws_item_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17852019388 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143931246 Data size: 17843165220 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 143931246 Data size: 17843165220 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 25 + Statistics: Num rows: 3941109 Data size: 468766936 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 3941109 Data size: 468766936 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 35 + Local Work: + Map Reduce Local Work + Map 26 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_gmt_offset = -8) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_gmt_offset = -8) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 9 + Map 4 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_addr_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313188164 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327191 Data size: 62303901444 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525327191 Data size: 62303901444 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 14384447 Data size: 57537904 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 14384447 Data size: 57537904 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 11 + Local Work: + Map Reduce Local Work + Reducer 15 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1550375 Data size: 20250108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - outputColumnNames: _col3, _col5 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col4, _col5 + Statistics: Num rows: 1550375 Data size: 20250108 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 11 + Statistics: Num rows: 373066 Data size: 37306712 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col4 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 17 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -442,107 +654,58 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(27,2)) - Reducer 19 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reducer 21 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - Reducer 22 + Reducer 23 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col3 + Statistics: Num rows: 788222 Data size: 87410040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - outputColumnNames: _col4, _col5 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 26 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 27 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col3 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 28 + expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col3, _col5 + Statistics: Num rows: 788222 Data size: 87410040 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 19 + Statistics: Num rows: 189670 Data size: 36186328 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 24 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -550,71 +713,22 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 95833781 Data size: 13030622757 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(27,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col3 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 30 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reducer 32 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 33 + Reducer 5 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -623,18 +737,34 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2876890 Data size: 11507672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: decimal(7,2)) outputColumnNames: _col3, _col5 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 4 + Statistics: Num rows: 2876890 Data size: 11507672 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 1 + Statistics: Num rows: 692265 Data size: 69226612 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -642,20 +772,20 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(27,2)) - Reducer 5 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -663,26 +793,26 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: decimal(27,2)) sort order: + - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) - Reducer 6 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: decimal(27,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 430 Data size: 91160 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query57.q.out b/ql/src/test/results/clientpositive/perf/spark/query57.q.out index 51e644a87b..217a489d29 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query57.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query57.q.out @@ -104,19 +104,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 7 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: call_center filterExpr: (cc_call_center_sk is not null and cc_name is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cc_call_center_sk is not null and cc_name is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cc_call_center_sk (type: int), cc_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -129,19 +149,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 18 + Map 15 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 16 Map Operator Tree: TableScan alias: call_center filterExpr: (cc_call_center_sk is not null and cc_name is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cc_call_center_sk is not null and cc_name is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cc_call_center_sk (type: int), cc_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -154,19 +194,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 26 + Map 22 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 752 Data size: 9024 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 23 Map Operator Tree: TableScan alias: call_center filterExpr: (cc_call_center_sk is not null and cc_name is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cc_call_center_sk is not null and cc_name is not null) (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cc_call_center_sk (type: int), cc_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -178,21 +238,18 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 306), Map 17 (PARTITION-LEVEL SORT, 306) - Reducer 13 <- Map 19 (PARTITION-LEVEL SORT, 374), Reducer 12 (PARTITION-LEVEL SORT, 374) - Reducer 14 <- Reducer 13 (GROUP, 406) - Reducer 15 <- Reducer 14 (PARTITION-LEVEL SORT, 203) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 203) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 8 (PARTITION-LEVEL SORT, 306) - Reducer 21 <- Map 20 (PARTITION-LEVEL SORT, 306), Map 25 (PARTITION-LEVEL SORT, 306) - Reducer 22 <- Map 27 (PARTITION-LEVEL SORT, 374), Reducer 21 (PARTITION-LEVEL SORT, 374) - Reducer 23 <- Reducer 22 (GROUP, 406) - Reducer 24 <- Reducer 23 (PARTITION-LEVEL SORT, 203) - Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 374), Reducer 2 (PARTITION-LEVEL SORT, 374) - Reducer 4 <- Reducer 3 (GROUP, 406) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 203) - Reducer 6 <- Reducer 16 (PARTITION-LEVEL SORT, 423), Reducer 24 (PARTITION-LEVEL SORT, 423), Reducer 5 (PARTITION-LEVEL SORT, 423) - Reducer 7 <- Reducer 6 (SORT, 1) + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 202), Map 17 (PARTITION-LEVEL SORT, 202) + Reducer 12 <- Reducer 11 (GROUP, 372) + Reducer 13 <- Reducer 12 (PARTITION-LEVEL SORT, 372) + Reducer 14 <- Reducer 13 (PARTITION-LEVEL SORT, 372) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 202), Map 24 (PARTITION-LEVEL SORT, 202) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 202), Map 9 (PARTITION-LEVEL SORT, 202) + Reducer 20 <- Reducer 19 (GROUP, 372) + Reducer 21 <- Reducer 20 (PARTITION-LEVEL SORT, 372) + Reducer 3 <- Reducer 2 (GROUP, 372) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 372) + Reducer 5 <- Reducer 14 (PARTITION-LEVEL SORT, 737), Reducer 21 (PARTITION-LEVEL SORT, 737), Reducer 4 (PARTITION-LEVEL SORT, 737) + Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -200,210 +257,188 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_call_center_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 35538018952 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117980 Data size: 35183631184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_call_center_sk (type: int), cs_item_sk (type: int), cs_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 285117980 Data size: 35183631184 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 + input vertices: + 1 Map 7 + Statistics: Num rows: 116588247 Data size: 14758000268 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col5, _col6, _col8 + input vertices: + 1 Map 8 + Statistics: Num rows: 116588247 Data size: 25722993858 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 116588247 Data size: 25722993858 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 10 - Map Operator Tree: - TableScan - alias: item - filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) - Execution mode: vectorized - Map 11 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_call_center_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 35538018952 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117980 Data size: 35183631184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_call_center_sk (type: int), cs_item_sk (type: int), cs_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 285117980 Data size: 35183631184 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 + input vertices: + 1 Map 15 + Statistics: Num rows: 116588247 Data size: 14758000268 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col5, _col6, _col8 + input vertices: + 1 Map 16 + Statistics: Num rows: 116588247 Data size: 25722993858 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 116588247 Data size: 25722993858 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 17 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) - Execution mode: vectorized - Map 19 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 20 + Map 18 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_call_center_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 35538018952 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117980 Data size: 35183631184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_call_center_sk (type: int), cs_item_sk (type: int), cs_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 25 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 285117980 Data size: 35183631184 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6 + input vertices: + 1 Map 22 + Statistics: Num rows: 116588247 Data size: 14758000268 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col5, _col6, _col8 + input vertices: + 1 Map 23 + Statistics: Num rows: 116588247 Data size: 25722993858 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 116588247 Data size: 25722993858 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string) Execution mode: vectorized - Map 27 + Local Work: + Map Reduce Local Work + Map 24 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 8 + Map 9 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE + predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int) + expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 462000 Data size: 89628000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Reducer 12 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col5, _col6, _col8 - input vertices: - 1 Map 18 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string) - Reducer 13 + Reducer 11 Reduce Operator Tree: Join Operator condition map: @@ -412,20 +447,20 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col5, _col6, _col8, _col10, _col11 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47408407800 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col10 (type: string), _col11 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) sort order: +++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) - Reducer 14 + Reducer 12 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -433,20 +468,20 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int) sort order: ++++ Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col5 (type: decimal(17,2)) - Reducer 15 + Reducer 13 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey3 (type: int), VALUE._col0 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -466,23 +501,23 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: decimal(17,2)) outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int), _col1 (type: int) sort order: +++++ Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE value expressions: avg_window_0 (type: decimal(21,6)), _col5 (type: decimal(17,2)) - Reducer 16 + Reducer 14 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: decimal(21,6)), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 60625888440 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -503,84 +538,50 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 60625888440 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 > 0) and (_col1 = 2000) and rank_window_1 is not null) (type: boolean) - Statistics: Num rows: 31942874 Data size: 4325706828 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 346989 Data size: 180434280 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_1 (type: int), _col0 (type: decimal(21,6)), _col1 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)) outputColumnNames: rank_window_1, _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 31942874 Data size: 4325706828 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 346989 Data size: 180434280 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col0 > 0)) THEN (((abs((_col6 - _col0)) / _col0) > 0.1)) ELSE (null) END (type: boolean) - Statistics: Num rows: 15971437 Data size: 2162853414 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 173494 Data size: 90910856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: string), _col4 (type: string), _col3 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: decimal(17,2)), _col0 (type: decimal(21,6)), rank_window_1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 15971437 Data size: 2162853414 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 173494 Data size: 90910856 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col7 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col7 (type: int) - Statistics: Num rows: 15971437 Data size: 2162853414 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 173494 Data size: 90910856 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col4 (type: int), _col5 (type: decimal(17,2)), _col6 (type: decimal(21,6)) - Reducer 2 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col5, _col6, _col8 - input vertices: - 1 Map 9 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string) - Reducer 21 - Local Work: - Map Reduce Local Work + Reducer 19 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col5, _col6, _col8 - input vertices: - 1 Map 26 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col3, _col5, _col6, _col8, _col10, _col11 + Statistics: Num rows: 116588247 Data size: 47408407800 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col10 (type: string), _col11 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string) - Reducer 22 + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) + sort order: +++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col5 (type: decimal(17,2)) + Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -589,20 +590,20 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col5, _col6, _col8, _col10, _col11 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47408407800 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col10 (type: string), _col11 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) sort order: +++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) - Reducer 23 + Reducer 20 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -610,19 +611,19 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int), _col1 (type: int) sort order: +++++ Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) - Reducer 24 + Reducer 21 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -643,43 +644,21 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: rank_window_0 is not null (type: boolean) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col5 (type: decimal(17,2)), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47101651788 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), (_col4 - 1) (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), (_col4 - 1) (type: int) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47101651788 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: decimal(17,2)) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col5, _col6, _col8, _col10, _col11 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col5 (type: int), _col6 (type: int), _col8 (type: string), _col10 (type: string), _col11 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) - sort order: +++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -687,19 +666,19 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int), _col1 (type: int) sort order: +++++ Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) - Reducer 5 + Reducer 4 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -720,21 +699,21 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: rank_window_0 is not null (type: boolean) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47568004776 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col5 (type: decimal(17,2)), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47101651788 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), (_col4 + 1) (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), (_col4 + 1) (type: int) - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116588247 Data size: 47101651788 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: decimal(17,2)) - Reducer 6 + Reducer 5 Reduce Operator Tree: Join Operator condition map: @@ -745,30 +724,30 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string), _col2 (type: string), _col7 (type: int) 2 _col0 (type: string), _col1 (type: string), _col2 (type: string), (_col4 - 1) (type: int) outputColumnNames: _col3, _col5, _col6, _col8, _col9, _col10, _col11, _col16 - Statistics: Num rows: 421645952 Data size: 57099332264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 173494 Data size: 112077124 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: string), _col6 (type: string), _col8 (type: int), _col9 (type: int), _col11 (type: decimal(21,6)), _col10 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col16 (type: decimal(17,2)), (_col10 - _col11) (type: decimal(22,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 421645952 Data size: 57099332264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 173494 Data size: 131508452 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col8 (type: decimal(22,6)), _col2 (type: int) sort order: ++ - Statistics: Num rows: 421645952 Data size: 57099332264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 173494 Data size: 131508452 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int), _col4 (type: decimal(21,6)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) - Reducer 7 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: decimal(21,6)), VALUE._col4 (type: decimal(17,2)), VALUE._col5 (type: decimal(17,2)), VALUE._col6 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 421645952 Data size: 57099332264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 173494 Data size: 131508452 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 75800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 75800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query58.q.out b/ql/src/test/results/clientpositive/perf/spark/query58.q.out index 59213cbbe2..ac3c35a7d4 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query58.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query58.q.out @@ -1,6 +1,6 @@ -Warning: Map Join MAPJOIN[183][bigTable=?] in task 'Stage-1:MAPRED' is a cross product -Warning: Map Join MAPJOIN[184][bigTable=?] in task 'Stage-1:MAPRED' is a cross product -Warning: Map Join MAPJOIN[185][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[191][bigTable=?] in task 'Stage-13:MAPRED' is a cross product +Warning: Map Join MAPJOIN[187][bigTable=?] in task 'Stage-5:MAPRED' is a cross product +Warning: Map Join MAPJOIN[195][bigTable=?] in task 'Stage-9:MAPRED' is a cross product PREHOOK: query: explain with ss_items as (select i_item_id item_id @@ -130,88 +130,76 @@ with ss_items as limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 + Stage-6 is a root stage + Stage-5 depends on stages: Stage-6 + Stage-4 depends on stages: Stage-5 + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3, Stage-7 + Stage-14 depends on stages: Stage-2 + Stage-13 depends on stages: Stage-14 + Stage-12 depends on stages: Stage-13 + Stage-11 depends on stages: Stage-12 + Stage-1 depends on stages: Stage-11 + Stage-10 is a root stage + Stage-9 depends on stages: Stage-10 + Stage-8 depends on stages: Stage-9 + Stage-7 depends on stages: Stage-8 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-6 Spark - Edges: - Reducer 11 <- Map 10 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 10 + Map 8 Map Operator Tree: TableScan alias: date_dim - filterExpr: (d_date = '1998-02-19') (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + filterExpr: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date = '1998-02-19') (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reducer 11 + expressions: d_week_seq (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 - Stage: Stage-3 + Stage: Stage-5 Spark Edges: - Reducer 24 <- Map 23 (GROUP, 1) + Reducer 7 <- Map 6 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 23 + Map 6 Map Operator Tree: TableScan alias: date_dim filterExpr: (d_date = '1998-02-19') (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 6866606 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date = '1998-02-19') (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized - Reducer 24 + Reducer 7 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -220,595 +208,534 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: 0 1 + outputColumnNames: _col1 + input vertices: + 1 Map 8 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) Stage: Stage-4 Spark Edges: - Reducer 37 <- Map 36 (GROUP, 1) + Reducer 10 <- Map 9 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 36 + Map 9 Map Operator Tree: TableScan alias: date_dim - filterExpr: (d_date = '1998-02-19') (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date = '1998-02-19') (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: (d_date is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + expressions: d_date (type: string), d_week_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Reducer 7 + Statistics: Num rows: 5 Data size: 470 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Reducer 37 + Local Work: + Map Reduce Local Work + Reducer 10 Execution mode: vectorized Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 2), Map 15 (PARTITION-LEVEL SORT, 2) - Reducer 14 <- Reducer 13 (GROUP, 2) - Reducer 17 <- Map 16 (PARTITION-LEVEL SORT, 403), Map 20 (PARTITION-LEVEL SORT, 403) - Reducer 18 <- Reducer 17 (PARTITION-LEVEL SORT, 438), Reducer 22 (PARTITION-LEVEL SORT, 438) - Reducer 19 <- Reducer 18 (GROUP, 481) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 310), Map 7 (PARTITION-LEVEL SORT, 310) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 2), Reducer 27 (PARTITION-LEVEL SORT, 2) - Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 2), Map 28 (PARTITION-LEVEL SORT, 2) - Reducer 27 <- Reducer 26 (GROUP, 2) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 336), Reducer 9 (PARTITION-LEVEL SORT, 336) - Reducer 30 <- Map 29 (PARTITION-LEVEL SORT, 159), Map 33 (PARTITION-LEVEL SORT, 159) - Reducer 31 <- Reducer 30 (PARTITION-LEVEL SORT, 169), Reducer 35 (PARTITION-LEVEL SORT, 169) - Reducer 32 <- Reducer 31 (GROUP, 186) - Reducer 35 <- Map 34 (PARTITION-LEVEL SORT, 2), Reducer 40 (PARTITION-LEVEL SORT, 2) - Reducer 39 <- Map 38 (PARTITION-LEVEL SORT, 2), Map 41 (PARTITION-LEVEL SORT, 2) - Reducer 4 <- Reducer 3 (GROUP, 369) - Reducer 40 <- Reducer 39 (GROUP, 2) - Reducer 5 <- Reducer 19 (PARTITION-LEVEL SORT, 518), Reducer 32 (PARTITION-LEVEL SORT, 518), Reducer 4 (PARTITION-LEVEL SORT, 518) - Reducer 6 <- Reducer 5 (SORT, 1) - Reducer 9 <- Map 8 (PARTITION-LEVEL SORT, 2), Reducer 14 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 12 + Map 5 Map Operator Tree: TableScan alias: date_dim - filterExpr: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_week_seq (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col1 + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 input vertices: - 0 Reducer 11 - Statistics: Num rows: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 10 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 15 + + Stage: Stage-2 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 268), Map 4 (PARTITION-LEVEL SORT, 268) + Reducer 23 <- Map 22 (PARTITION-LEVEL SORT, 136), Map 25 (PARTITION-LEVEL SORT, 136) + Reducer 24 <- Reducer 23 (GROUP, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 34391818848 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 286549727 Data size: 34219840636 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date (type: string), d_week_seq (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 286549727 Data size: 34219840636 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Statistics: Num rows: 286549727 Data size: 34219840636 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) Execution mode: vectorized - Map 16 + Map 22 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17276151220 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143966864 Data size: 17271855784 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271855784 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271855784 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) Execution mode: vectorized - Map 20 + Map 25 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 21 + Map 4 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int), d_date (type: string) + expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: vectorized - Map 25 + Reducer 2 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4 + Statistics: Num rows: 286549727 Data size: 61728614428 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + input vertices: + 1 Map 5 + Statistics: Num rows: 62327 Data size: 6232812 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 68 Data size: 14416 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 68 Data size: 14416 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 23 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4 + Statistics: Num rows: 143966864 Data size: 31092674728 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + input vertices: + 1 Map 26 + Statistics: Num rows: 31537 Data size: 3153812 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 69 Data size: 14628 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 69 Data size: 14628 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 24 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 69 Data size: 14628 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + Reducer 3 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 68 Data size: 14416 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + + Stage: Stage-14 + Spark +#### A masked pattern was here #### + Vertices: + Map 19 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_week_seq (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator keys: 0 1 - outputColumnNames: _col1 - input vertices: - 0 Reducer 24 - Statistics: Num rows: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-13 + Spark + Edges: + Reducer 18 <- Map 17 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 17 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_date = '1998-02-19') (type: boolean) + Statistics: Num rows: 73049 Data size: 6866606 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date = '1998-02-19') (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized + Reducer 18 Execution mode: vectorized Local Work: Map Reduce Local Work - Map 28 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1 + input vertices: + 1 Map 19 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + + Stage: Stage-12 + Spark + Edges: + Reducer 21 <- Map 20 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 20 Map Operator Tree: TableScan alias: date_dim filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date (type: string), d_week_seq (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Reducer 18 + Statistics: Num rows: 5 Data size: 470 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 29 + Local Work: + Map Reduce Local Work + Reducer 21 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-11 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 33 - Map Operator Tree: - TableScan - alias: item - filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_item_id (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 34 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Execution mode: vectorized - Map 38 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_week_seq (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col1 + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 input vertices: - 0 Reducer 37 - Statistics: Num rows: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 21 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 41 + + Stage: Stage-1 + Spark + Edges: + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 494), Map 15 (PARTITION-LEVEL SORT, 494) + Reducer 13 <- Reducer 12 (GROUP, 2) + Reducer 14 <- Reducer 13 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 11 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66112867736 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date (type: string), d_week_seq (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) Execution mode: vectorized - Map 7 + Map 15 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 8 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_date (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Execution mode: vectorized - Reducer 13 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col2 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col2 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 14 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reducer 17 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: string) - Reducer 18 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 19 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: string) - Reducer 22 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 26 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col2 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col2 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 27 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 30 + Reducer 12 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -817,170 +744,257 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: string) - Reducer 31 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 32 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 35 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 39 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col2 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col2 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 4 + Statistics: Num rows: 550076554 Data size: 115945220792 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + input vertices: + 1 Map 16 + Statistics: Num rows: 120498 Data size: 12049912 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 69 Data size: 14628 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 69 Data size: 14628 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 13 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 40 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reducer 5 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3, _col5 - Statistics: Num rows: 766650239 Data size: 67634106674 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) (type: boolean) - Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: decimal(17,2)), (((_col3 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), _col1 (type: decimal(17,2)), (((_col1 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), _col5 (type: decimal(17,2)), (((_col5 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), (((_col3 + _col1) + _col5) / 3) (type: decimal(23,6)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: decimal(17,2)) - sort order: ++ - Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: decimal(38,17)), _col3 (type: decimal(17,2)), _col4 (type: decimal(38,17)), _col5 (type: decimal(17,2)), _col6 (type: decimal(38,17)), _col7 (type: decimal(23,6)) - Reducer 6 + Statistics: Num rows: 69 Data size: 14628 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5 + input vertices: + 0 Reducer 3 + 2 Reducer 24 + Statistics: Num rows: 68 Data size: 29648 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) (type: boolean) + Statistics: Num rows: 1 Data size: 436 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col3 (type: decimal(17,2)), (((_col3 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), _col1 (type: decimal(17,2)), (((_col1 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), _col5 (type: decimal(17,2)), (((_col5 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), (((_col3 + _col1) + _col5) / 3) (type: decimal(23,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: decimal(17,2)) + sort order: ++ + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(38,17)), _col3 (type: decimal(17,2)), _col4 (type: decimal(38,17)), _col5 (type: decimal(17,2)), _col6 (type: decimal(38,17)), _col7 (type: decimal(23,6)) + Reducer 14 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: decimal(17,2)), VALUE._col0 (type: decimal(38,17)), VALUE._col1 (type: decimal(17,2)), VALUE._col2 (type: decimal(38,17)), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: decimal(38,17)), VALUE._col5 (type: decimal(23,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 29 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_week_seq (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-9 + Spark + Edges: + Reducer 28 <- Map 27 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 27 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_date = '1998-02-19') (type: boolean) + Statistics: Num rows: 73049 Data size: 6866606 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date = '1998-02-19') (type: boolean) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized + Reducer 28 + Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1 + input vertices: + 1 Map 29 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + + Stage: Stage-8 + Spark + Edges: + Reducer 31 <- Map 30 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 30 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date (type: string), d_week_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Reducer 28 + Statistics: Num rows: 5 Data size: 470 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 31 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 26 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Reducer 31 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query59.q.out b/ql/src/test/results/clientpositive/perf/spark/query59.q.out index 1224ab68a6..4f0dc492d4 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query59.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query59.q.out @@ -87,7 +87,9 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -95,19 +97,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 6 + Map Operator Tree: + TableScan + alias: d + filterExpr: (d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_week_seq (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store filterExpr: (s_store_sk is not null and s_store_id is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_store_id is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_id (type: string), s_store_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 327168 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -120,301 +142,228 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 16 + Map 5 Map Operator Tree: TableScan - alias: store - filterExpr: (s_store_sk is not null and s_store_id is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (s_store_id is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int), s_store_id (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + expressions: d_date_sk (type: int), d_week_seq (type: int), d_day_name (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-4 Spark - Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 398), Map 14 (PARTITION-LEVEL SORT, 398) - Reducer 12 <- Reducer 11 (GROUP, 437) - Reducer 13 <- Map 15 (PARTITION-LEVEL SORT, 219), Reducer 12 (PARTITION-LEVEL SORT, 219) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Reducer 2 (GROUP, 437) - Reducer 4 <- Map 8 (PARTITION-LEVEL SORT, 219), Reducer 3 (PARTITION-LEVEL SORT, 219) - Reducer 5 <- Reducer 13 (PARTITION-LEVEL SORT, 529), Reducer 4 (PARTITION-LEVEL SORT, 529) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 11 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: d + filterExpr: (d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + expressions: d_week_seq (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + Map 12 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: (s_store_sk is not null and s_store_id is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (s_store_id is not null and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + expressions: s_store_sk (type: int), s_store_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan alias: date_dim filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_week_seq (type: int), d_day_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string) - Execution mode: vectorized - Map 15 - Map Operator Tree: - TableScan - alias: d - filterExpr: (d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_week_seq (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7231851 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 1009) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 10), Reducer 9 (PARTITION-LEVEL SORT, 10) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 9 <- Map 8 (GROUP, 1009) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66009029132 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 525329897 Data size: 60202741740 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int), d_week_seq (type: int), d_day_name (type: string) + expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 525329897 Data size: 60202741740 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4, _col5 + input vertices: + 1 Map 5 + Statistics: Num rows: 525329897 Data size: 108102319107 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col4 (type: int), _col1 (type: int), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Tuesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 525329897 Data size: 108102319107 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7), sum(_col8) + keys: _col0 (type: int), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 262664948 Data size: 207983372096 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 262664948 Data size: 207983372096 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 8 Map Operator Tree: TableScan - alias: d - filterExpr: (d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66009029132 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 525329897 Data size: 60202741740 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_week_seq (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col4 (type: int), _col1 (type: int), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col7, _col8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3), sum(_col5), sum(_col6), sum(_col7), sum(_col8) - keys: _col0 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) - Reducer 12 + expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 525329897 Data size: 60202741740 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4, _col5 + input vertices: + 1 Map 10 + Statistics: Num rows: 525329897 Data size: 108102319107 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col4 (type: int), _col1 (type: int), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col7, _col8 + Statistics: Num rows: 525329897 Data size: 108102319107 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col5), sum(_col6), sum(_col7), sum(_col8) + keys: _col0 (type: int), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 262664948 Data size: 178564897920 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 262664948 Data size: 178564897920 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) - Reducer 13 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col11 - input vertices: - 1 Map 16 - Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col11 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), (_col0 - 52) (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), (_col0 - 52) (type: int) - Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col4 (type: int), _col1 (type: int), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Tuesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7), sum(_col8) - keys: _col0 (type: int), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) - Reducer 3 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) - Reducer 4 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1104768 Data size: 874777456 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13 + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 input vertices: - 1 Map 9 - Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col12 (type: string), _col0 (type: int) - sort order: ++ - Map-reduce partition columns: _col12 (type: string), _col0 (type: int) - Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)), _col13 (type: string) - Reducer 5 + 1 Map 6 + Statistics: Num rows: 681744 Data size: 539742448 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13 + input vertices: + 1 Map 7 + Statistics: Num rows: 681744 Data size: 665382144 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col12 (type: string), _col0 (type: int) + sort order: ++ + Map-reduce partition columns: _col12 (type: string), _col0 (type: int) + Statistics: Num rows: 681744 Data size: 665382144 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)), _col13 (type: string) + Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -423,34 +372,75 @@ STAGE PLANS: 0 _col12 (type: string), _col0 (type: int) 1 _col1 (type: string), (_col0 - 52) (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514700865 Data size: 848227025520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col13 (type: string), _col12 (type: string), _col0 (type: int), (_col2 / _col16) (type: decimal(37,20)), (_col3 / _col17) (type: decimal(37,20)), (_col4 / _col4) (type: decimal(37,20)), (_col5 / _col18) (type: decimal(37,20)), (_col6 / _col19) (type: decimal(37,20)), (_col7 / _col20) (type: decimal(37,20)), (_col8 / _col21) (type: decimal(37,20)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514700865 Data size: 502348044240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: +++ - Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514700865 Data size: 502348044240 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(37,20)), _col4 (type: decimal(37,20)), _col5 (type: decimal(37,20)), _col6 (type: decimal(37,20)), _col7 (type: decimal(37,20)), _col8 (type: decimal(37,20)), _col9 (type: decimal(37,20)) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: decimal(37,20)), VALUE._col1 (type: decimal(37,20)), VALUE._col2 (type: decimal(37,20)), VALUE._col3 (type: decimal(37,20)), VALUE._col4 (type: decimal(37,20)), VALUE._col5 (type: decimal(37,20)), VALUE._col6 (type: decimal(37,20)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514700865 Data size: 502348044240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 97600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 97600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1104768 Data size: 751043440 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 11 + Statistics: Num rows: 681744 Data size: 463387120 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col11 + input vertices: + 1 Map 12 + Statistics: Num rows: 681744 Data size: 529033344 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col11 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 681744 Data size: 529033344 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), (_col0 - 52) (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), (_col0 - 52) (type: int) + Statistics: Num rows: 681744 Data size: 529033344 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query6.q.out b/ql/src/test/results/clientpositive/perf/spark/query6.q.out index fe3741f80c..685e539195 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query6.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query6.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[85][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[89][bigTable=?] in task 'Stage-5:MAPRED' is a cross product PREHOOK: query: explain select a.ca_state state, count(*) cnt from customer_address a @@ -50,62 +50,181 @@ select a.ca_state state, count(*) cnt limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3 + Stage-6 depends on stages: Stage-2 + Stage-5 depends on stages: Stage-6 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-4 + Spark + Edges: + Reducer 3 <- Map 2 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 2 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2000) and (d_moy = 2) and d_month_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 2) and (d_year = 2000) and d_month_seq is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_month_seq (type: int) + outputColumnNames: d_month_seq + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: d_month_seq (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 3 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: d + filterExpr: (d_date_sk is not null and d_month_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date_sk is not null and d_month_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_month_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + input vertices: + 1 Reducer 3 + Statistics: Num rows: 52 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-2 Spark +#### A masked pattern was here #### + Vertices: + Map 4 + Map Operator Tree: + TableScan + alias: s + filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6704610012 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 525327388 Data size: 6114829788 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 525327388 Data size: 6114829788 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5 + input vertices: + 0 Map 1 + Statistics: Num rows: 575379 Data size: 2301520 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col5 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark Edges: - Reducer 18 <- Map 17 (GROUP, 2) - Reducer 19 <- Reducer 18 (GROUP, 1) + Reducer 14 <- Map 13 (GROUP, 2) + Reducer 15 <- Reducer 14 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 17 + Map 13 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and (d_moy = 2)) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 2) and (d_year = 2000)) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_month_seq (type: int) outputColumnNames: d_month_seq - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: d_month_seq (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Reducer 18 + Reducer 14 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 19 + Reducer 15 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -114,248 +233,165 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sq_count_check(_col0) <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 1 - Stage: Stage-1 + Stage: Stage-5 Spark Edges: - Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 855), Map 13 (PARTITION-LEVEL SORT, 855) - Reducer 15 <- Map 14 (GROUP, 6) - Reducer 16 <- Map 20 (PARTITION-LEVEL SORT, 8), Reducer 15 (PARTITION-LEVEL SORT, 8) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 9 (PARTITION-LEVEL SORT, 2) - Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 398), Reducer 2 (PARTITION-LEVEL SORT, 398) - Reducer 4 <- Reducer 12 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009) - Reducer 5 <- Reducer 16 (PARTITION-LEVEL SORT, 483), Reducer 4 (PARTITION-LEVEL SORT, 483) - Reducer 6 <- Reducer 5 (GROUP, 529) - Reducer 7 <- Reducer 6 (SORT, 1) - Reducer 9 <- Map 8 (GROUP, 2) + Reducer 12 <- Map 11 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: d - filterExpr: (d_date_sk is not null and d_month_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (d_date_sk is not null and d_month_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_month_seq (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Execution mode: vectorized - Map 10 + Map 11 Map Operator Tree: TableScan - alias: s - filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: j + filterExpr: i_category is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 93193408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int) + predicate: i_category is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 93193408 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(i_current_price), count(i_current_price) + keys: i_category (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 10 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: c - filterExpr: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Reducer 12 Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 2100 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (_col1 / _col2) (type: decimal(37,22)), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 2020 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 15 + Statistics: Num rows: 10 Data size: 2020 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col2 (type: string) + + Stage: Stage-1 + Spark + Edges: + Reducer 6 <- Map 10 (PARTITION-LEVEL SORT, 34), Map 5 (PARTITION-LEVEL SORT, 34) + Reducer 7 <- Map 16 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) + Reducer 8 <- Reducer 7 (GROUP, 2) + Reducer 9 <- Reducer 8 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan alias: a filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 14 - Map Operator Tree: - TableScan - alias: j - filterExpr: i_category is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: i_category is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(i_current_price), count(i_current_price) - keys: i_category (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) - Execution mode: vectorized - Map 20 + Map 16 Map Operator Tree: TableScan alias: i filterExpr: (i_item_sk is not null and i_category is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 95041408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_category is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 95041408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_current_price (type: decimal(7,2)), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: decimal(7,2)) + Statistics: Num rows: 462000 Data size: 95041408 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col2 (type: string) + outputColumnNames: _col0, _col3, _col4 + input vertices: + 0 Reducer 12 + Statistics: Num rows: 462000 Data size: 105205408 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col4 > (1.2 * CAST( _col0 AS decimal(16,6)))) (type: boolean) + Statistics: Num rows: 154000 Data size: 35068544 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 154000 Data size: 35068544 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 154000 Data size: 35068544 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 8 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 2000) and (d_moy = 2) and d_month_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: c + filterExpr: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_moy = 2) and (d_year = 2000) and d_month_seq is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_month_seq (type: int) - outputColumnNames: d_month_seq - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: d_month_seq (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 12 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string) - Reducer 15 + expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: vectorized + Reducer 6 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (_col1 / _col2) (type: decimal(37,22)), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - input vertices: - 1 Reducer 19 - Statistics: Num rows: 231000 Data size: 333859228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 231000 Data size: 333859228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(37,22)) - Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col2 (type: string) - outputColumnNames: _col0, _col3, _col4 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col4 > (1.2 * CAST( _col0 AS decimal(16,6)))) (type: boolean) - Statistics: Num rows: 169400 Data size: 243305506 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 169400 Data size: 243305506 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 169400 Data size: 243305506 Basic stats: COMPLETE Column stats: NONE - Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -363,46 +399,25 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col5 (type: int) - sort order: + - Map-reduce partition columns: _col5 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int) - Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col5 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col9 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col9 (type: string) - Reducer 5 + outputColumnNames: _col0, _col3 + Statistics: Num rows: 80000000 Data size: 7200000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col5 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col9 + input vertices: + 0 Map 4 + Statistics: Num rows: 575379 Data size: 51784110 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col4 (type: int) + sort order: + + Map-reduce partition columns: _col4 (type: int) + Statistics: Num rows: 575379 Data size: 51784110 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col9 (type: string) + Reducer 7 Reduce Operator Tree: Join Operator condition map: @@ -411,20 +426,20 @@ STAGE PLANS: 0 _col4 (type: int) 1 _col0 (type: int) outputColumnNames: _col9 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2236 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col9 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 6 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -432,46 +447,33 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 >= 10L) (type: boolean) - Statistics: Num rows: 127775039 Data size: 11272351038 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + - Statistics: Num rows: 127775039 Data size: 11272351038 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string) - Reducer 7 + Reducer 9 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 127775039 Data size: 11272351038 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query60.q.out b/ql/src/test/results/clientpositive/perf/spark/query60.q.out index f4f61e21d0..11eee4ac2e 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query60.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query60.q.out @@ -153,31 +153,66 @@ where i_category in ('Children')) limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-6 + Stage-7 depends on stages: Stage-5 + Stage-9 depends on stages: Stage-7 + Stage-8 depends on stages: Stage-9 + Stage-10 depends on stages: Stage-8 + Stage-1 depends on stages: Stage-10 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark Edges: - Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 11 <- Map 13 (PARTITION-LEVEL SORT, 596), Reducer 10 (PARTITION-LEVEL SORT, 596) - Reducer 15 <- Map 1 (PARTITION-LEVEL SORT, 7), Reducer 19 (PARTITION-LEVEL SORT, 7) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 375), Reducer 22 (PARTITION-LEVEL SORT, 375) - Reducer 17 <- Reducer 16 (GROUP, 406) - Reducer 19 <- Map 18 (GROUP, 3) - Reducer 21 <- Map 12 (PARTITION-LEVEL SORT, 305), Map 20 (PARTITION-LEVEL SORT, 305) - Reducer 22 <- Map 13 (PARTITION-LEVEL SORT, 494), Reducer 21 (PARTITION-LEVEL SORT, 494) - Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 7), Reducer 30 (PARTITION-LEVEL SORT, 7) - Reducer 27 <- Reducer 26 (PARTITION-LEVEL SORT, 191), Reducer 33 (PARTITION-LEVEL SORT, 191) - Reducer 28 <- Reducer 27 (GROUP, 204) - Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 487), Reducer 15 (PARTITION-LEVEL SORT, 487) - Reducer 30 <- Map 18 (GROUP, 3) - Reducer 32 <- Map 31 (PARTITION-LEVEL SORT, 154), Map 34 (PARTITION-LEVEL SORT, 154) - Reducer 33 <- Map 35 (PARTITION-LEVEL SORT, 327), Reducer 32 (PARTITION-LEVEL SORT, 327) - Reducer 4 <- Reducer 3 (GROUP, 529) - Reducer 5 <- Reducer 17 (GROUP, 569), Reducer 28 (GROUP, 569), Reducer 4 (GROUP, 569) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 3 <- Map 2 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 2 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_category = 'Children') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 87780000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_category = 'Children') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 46200 Data size: 8778000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_id (type: string) + outputColumnNames: i_item_id + Statistics: Num rows: 46200 Data size: 8778000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: i_item_id (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 3 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-2 + Spark #### A masked pattern was here #### Vertices: Map 1 @@ -185,276 +220,453 @@ STAGE PLANS: TableScan alias: item filterExpr: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 3 + Statistics: Num rows: 34340 Data size: 3571360 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_moy = 9) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark + Edges: + Reducer 13 <- Map 12 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 12 Map Operator Tree: TableScan - alias: customer_address - filterExpr: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: ((i_category = 'Children') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 87780000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + predicate: ((i_category = 'Children') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 46200 Data size: 8778000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ca_address_sk (type: int) + expressions: i_item_id (type: string) + outputColumnNames: i_item_id + Statistics: Num rows: 46200 Data size: 8778000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: i_item_id (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 13 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 + Map Operator Tree: + TableScan + alias: item + filterExpr: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_item_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 13 + Statistics: Num rows: 34340 Data size: 3571360 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 17 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 9) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 18 + Local Work: + Map Reduce Local Work + + Stage: Stage-9 + Spark + Edges: + Reducer 21 <- Map 20 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 20 Map Operator Tree: TableScan alias: item filterExpr: ((i_category = 'Children') and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 87780000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_category = 'Children') and i_item_id is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46200 Data size: 8778000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_id (type: string) outputColumnNames: i_item_id - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46200 Data size: 8778000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: i_item_id (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 20 - Map Operator Tree: - TableScan - alias: catalog_sales - filterExpr: (cs_sold_date_sk is not null and cs_bill_addr_sk is not null and cs_item_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 21 Execution mode: vectorized - Map 25 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 23100 Data size: 2310000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 19 Map Operator Tree: TableScan alias: item filterExpr: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 21 + Statistics: Num rows: 34340 Data size: 3571360 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) Execution mode: vectorized - Map 31 + Local Work: + Map Reduce Local Work + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 25 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null and ws_item_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 9) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 34 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 15 <- Map 10 (PARTITION-LEVEL SORT, 14), Map 14 (PARTITION-LEVEL SORT, 14) + Reducer 16 <- Reducer 15 (GROUP, 2) + Reducer 23 <- Map 22 (PARTITION-LEVEL SORT, 11), Map 26 (PARTITION-LEVEL SORT, 11) + Reducer 24 <- Reducer 23 (GROUP, 2) + Reducer 5 <- Map 10 (PARTITION-LEVEL SORT, 8), Map 4 (PARTITION-LEVEL SORT, 8) + Reducer 6 <- Reducer 5 (GROUP, 2) + Reducer 7 <- Reducer 16 (GROUP, 2), Reducer 24 (GROUP, 2), Reducer 6 (GROUP, 2) + Reducer 8 <- Reducer 7 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 9) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: customer_address + filterExpr: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) + expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 35 + Map 14 + Map Operator Tree: + TableScan + alias: catalog_sales + filterExpr: (cs_sold_date_sk is not null and cs_bill_addr_sk is not null and cs_item_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 35538021432 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 285117733 Data size: 35183603168 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 285117733 Data size: 35183603168 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 17 + Statistics: Num rows: 7751872 Data size: 764931900 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 7751872 Data size: 764931900 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 22 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_sold_date_sk is not null and ws_bill_addr_sk is not null and ws_item_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17852019388 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143931246 Data size: 17843165220 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 143931246 Data size: 17843165220 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 25 + Statistics: Num rows: 3941109 Data size: 468766936 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 3941109 Data size: 468766936 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 26 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 9 + Map 4 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_addr_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313188164 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327191 Data size: 62303901444 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525327191 Data size: 62303901444 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 14384447 Data size: 57537904 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 14384447 Data size: 57537904 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 11 + Local Work: + Map Reduce Local Work + Reducer 15 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col3 + Statistics: Num rows: 1550375 Data size: 20250108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - outputColumnNames: _col3, _col5 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col4, _col5 + Statistics: Num rows: 1550375 Data size: 20250108 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 11 + Statistics: Num rows: 746132 Data size: 74613312 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col4 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 17 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -462,108 +674,59 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(27,2)) - Reducer 19 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reducer 21 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - Reducer 22 + Reducer 23 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col3 + Statistics: Num rows: 788222 Data size: 87410040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col2 (type: int), _col3 (type: decimal(7,2)) - outputColumnNames: _col4, _col5 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 26 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 27 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col3 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 28 + expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col3, _col5 + Statistics: Num rows: 788222 Data size: 87410040 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 19 + Statistics: Num rows: 379339 Data size: 76396156 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 24 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -571,72 +734,23 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 95833781 Data size: 13030622757 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(27,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col3 (type: int) - outputColumnNames: _col1, _col8 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 30 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE - Reducer 32 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 33 + Reducer 5 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -645,18 +759,34 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2876890 Data size: 11507672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col3 (type: decimal(7,2)) outputColumnNames: _col3, _col5 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) - Reducer 4 + Statistics: Num rows: 2876890 Data size: 11507672 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + input vertices: + 0 Map 1 + Statistics: Num rows: 1384530 Data size: 138453112 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -664,21 +794,21 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(27,2)) - Reducer 5 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -686,25 +816,25 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: decimal(27,2)) sort order: ++ - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 6 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: decimal(27,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1717 Data size: 364004 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 21200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query61.q.out b/ql/src/test/results/clientpositive/perf/spark/query61.q.out index c178b5acb9..37b81bc1cc 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query61.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query61.q.out @@ -86,34 +86,139 @@ order by promotions, total limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage + Stage-5 is a root stage + Stage-4 depends on stages: Stage-5 + Stage-3 depends on stages: Stage-4 Stage-2 depends on stages: Stage-3 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 + Stage-9 depends on stages: Stage-2 + Stage-8 depends on stages: Stage-9 + Stage-7 depends on stages: Stage-8 + Stage-6 depends on stages: Stage-7 + Stage-1 depends on stages: Stage-6 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 11) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 17 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_category = 'Electronics') and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_category = 'Electronics') and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 46200 Data size: 4342800 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 46200 Data size: 4573800 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 15 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_store_sk is not null and ss_sold_date_sk is not null and ss_customer_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 70513520748 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501694138 Data size: 61417514116 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 501694138 Data size: 61417514116 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 16 + Statistics: Num rows: 13737330 Data size: 54949440 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4 + input vertices: + 1 Map 17 + Statistics: Num rows: 13222427 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 24 + Map 18 Map Operator Tree: TableScan alias: store filterExpr: ((s_gmt_offset = -7) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 196768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_gmt_offset = -7) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 39444 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 341 Data size: 39556 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: 0 _col3 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + input vertices: + 0 Map 15 + Statistics: Num rows: 2646038 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col2 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -121,244 +226,251 @@ STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 697), Map 18 (PARTITION-LEVEL SORT, 697) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 1009), Reducer 21 (PARTITION-LEVEL SORT, 1009) - Reducer 17 <- Reducer 16 (GROUP, 1) - Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 398), Map 22 (PARTITION-LEVEL SORT, 398) - Reducer 21 <- Map 23 (PARTITION-LEVEL SORT, 440), Reducer 20 (PARTITION-LEVEL SORT, 440) + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 13), Map 14 (PARTITION-LEVEL SORT, 13) + Reducer 13 <- Reducer 12 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 14 + Map 11 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized - Map 18 + Map 14 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_gmt_offset = -7) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_gmt_offset = -7) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 19 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_store_sk is not null and ss_sold_date_sk is not null and ss_customer_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Reducer 12 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 16000001 Data size: 64000004 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col8 + input vertices: + 1 Map 18 + Statistics: Num rows: 529208 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(17,2)) + Reducer 13 Execution mode: vectorized - Map 22 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-9 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and (d_moy = 11) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 23 + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: item filterExpr: ((i_category = 'Electronics') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_category = 'Electronics') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46200 Data size: 4342800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col8 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col8) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(17,2)) - Reducer 17 + Statistics: Num rows: 46200 Data size: 4573800 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 - Reducer 20 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 21 + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_store_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_customer_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 72713838164 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 479120970 Data size: 60484355364 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_promo_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 479120970 Data size: 60484355364 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 7 + Statistics: Num rows: 13119234 Data size: 52477060 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col5 + input vertices: + 1 Map 8 + Statistics: Num rows: 12627499 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - input vertices: - 1 Map 24 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)) - Stage: Stage-4 + Stage: Stage-7 Spark #### A masked pattern was here #### Vertices: - Map 12 + Map 9 Map Operator Tree: TableScan alias: store filterExpr: ((s_gmt_offset = -7) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 196768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_gmt_offset = -7) and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 341 Data size: 39444 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 341 Data size: 39556 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: 0 _col3 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2, _col4, _col5 + input vertices: + 0 Map 6 + Statistics: Num rows: 2526982 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 13 + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 10 Map Operator Tree: TableScan alias: promotion filterExpr: (((p_channel_dmail = 'Y') or (p_channel_email = 'Y') or (p_channel_tv = 'Y')) and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 595700 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((p_channel_dmail = 'Y') or (p_channel_email = 'Y') or (p_channel_tv = 'Y')) and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 595700 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_promo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 2300 Data size: 595700 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: 0 _col4 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2, _col5 + input vertices: + 0 Map 9 + Statistics: Num rows: 2526982 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col2 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -366,12 +478,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 697), Map 6 (PARTITION-LEVEL SORT, 697) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1009), Reducer 9 (PARTITION-LEVEL SORT, 1009) - Reducer 4 <- Reducer 3 (GROUP, 1) - Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 8 <- Map 10 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 440), Reducer 8 (PARTITION-LEVEL SORT, 440) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 13), Map 5 (PARTITION-LEVEL SORT, 13) + Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -379,99 +488,43 @@ STAGE PLANS: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 640000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized - Map 10 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 11) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: item - filterExpr: ((i_category = 'Electronics') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((i_category = 'Electronics') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 6 + Map 5 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_gmt_offset = -7) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_gmt_offset = -7) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: (ss_store_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_customer_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_promo_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)) + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 2 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -480,32 +533,27 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16000001 Data size: 64000004 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col9 + input vertices: + 1 Map 10 + Statistics: Num rows: 505397 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col9) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(17,2)) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col9 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col9) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -514,7 +562,7 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -523,89 +571,35 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 input vertices: - 1 Reducer 17 - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 13 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: decimal(17,2)), _col1 (type: decimal(17,2)), ((CAST( _col0 AS decimal(15,4)) / CAST( _col1 AS decimal(15,4))) * 100) (type: decimal(38,19)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(17,2)), _col1 (type: decimal(17,2)) sort order: ++ - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(38,19)) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(17,2)), KEY.reducesinkkey1 (type: decimal(17,2)), VALUE._col0 (type: decimal(38,19)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 225 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 8 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)) - Reducer 9 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col5 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col5 - input vertices: - 1 Map 12 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col5 - input vertices: - 1 Map 13 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query63.q.out b/ql/src/test/results/clientpositive/perf/spark/query63.q.out index 0b1614ff5e..6b26f71f38 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query63.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query63.q.out @@ -64,19 +64,59 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 4 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 133975508 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 694 Data size: 201256 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_manager_id (type: int) + outputColumnNames: _col0, _col4 + Statistics: Num rows: 694 Data size: 201256 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 5 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 317 Data size: 3804 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_moy (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 317 Data size: 3804 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -88,10 +128,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 403), Map 6 (PARTITION-LEVEL SORT, 403) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438) - Reducer 4 <- Reducer 3 (GROUP PARTITION-LEVEL SORT, 529) - Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -99,123 +137,71 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 6 - Map Operator Tree: - TableScan - alias: item - filterExpr: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_manager_id (type: int) - outputColumnNames: _col0, _col4 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_moy (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3, _col8 + input vertices: + 1 Map 4 + Statistics: Num rows: 7595537 Data size: 30382264 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col8, _col11 + input vertices: + 1 Map 5 + Statistics: Num rows: 1318594 Data size: 10548864 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col8, _col11 + input vertices: + 1 Map 6 + Statistics: Num rows: 1318594 Data size: 10548860 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col8 (type: int), _col11 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 156 Data size: 18720 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 156 Data size: 18720 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3, _col8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col8 (type: int) - Reducer 3 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col8, _col11 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col8, _col11 - input vertices: - 1 Map 8 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col8 (type: int), _col11 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 4 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143 Data size: 17160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143 Data size: 16588 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -235,36 +221,36 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143 Data size: 16588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col2 (type: decimal(17,2)) outputColumnNames: avg_window_0, _col0, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143 Data size: 16588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((avg_window_0 > 0)) THEN (((abs((_col2 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END (type: boolean) - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71 Data size: 16188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: decimal(17,2)), avg_window_0 (type: decimal(21,6)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71 Data size: 16188 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: decimal(21,6)), _col1 (type: decimal(17,2)) sort order: +++ - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71 Data size: 16188 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey2 (type: decimal(17,2)), KEY.reducesinkkey1 (type: decimal(21,6)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71 Data size: 16188 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71 Data size: 16188 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71 Data size: 16188 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query65.q.out b/ql/src/test/results/clientpositive/perf/spark/query65.q.out index 4afa1a6666..622df10898 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query65.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query65.q.out @@ -55,13 +55,15 @@ select limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3, Stage-5 + Stage-1 depends on stages: Stage-2 + Stage-5 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-4 Spark #### A masked pattern was here #### Vertices: @@ -70,14 +72,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -88,52 +90,23 @@ STAGE PLANS: Stage: Stage-3 Spark -#### A masked pattern was here #### - Vertices: - Map 9 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark Edges: - Reducer 2 <- Map 1 (GROUP, 437) - Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 328), Reducer 2 (PARTITION-LEVEL SORT, 328), Reducer 8 (PARTITION-LEVEL SORT, 328) - Reducer 4 <- Map 11 (PARTITION-LEVEL SORT, 166), Reducer 3 (PARTITION-LEVEL SORT, 166) - Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 8 <- Map 7 (GROUP PARTITION-LEVEL SORT, 437) + Reducer 5 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 4 Map Operator Tree: TableScan alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -143,75 +116,93 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Map 6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365993 Data size: 4261630000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col2 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1299837 Data size: 153875140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1299837 Data size: 153875140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 10 + Map 7 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: item - filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_item_desc (type: string), i_current_price (type: decimal(7,2)), i_wholesale_cost (type: decimal(7,2)), i_brand (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: string) + Local Work: + Map Reduce Local Work + Reducer 5 Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 76461 Data size: 9051484 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 76461 Data size: 9051484 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), count(_col2) + keys: _col1 (type: int) + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 11 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(38,13)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11 Data size: 1264 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + + Stage: Stage-2 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -220,125 +211,139 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3 input vertices: - 1 Map 9 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + 1 Map 3 + Statistics: Num rows: 58365993 Data size: 4261630000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col2 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1185580 Data size: 140349360 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1185580 Data size: 140349360 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)) Execution mode: vectorized Local Work: Map Reduce Local Work Reducer 2 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(17,2)) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4, _col6 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 <= (0.1 * _col4)) (type: boolean) - Statistics: Num rows: 232318249 Data size: 20495183367 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 232318249 Data size: 20495183367 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)), _col6 (type: string) - Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col6, _col8, _col9, _col10, _col11 - Statistics: Num rows: 255550079 Data size: 22544702192 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: string), _col8 (type: string), _col2 (type: decimal(17,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)), _col11 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 255550079 Data size: 22544702192 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Statistics: Num rows: 255550079 Data size: 22544702192 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: string) - Reducer 5 + Statistics: Num rows: 69740 Data size: 8255848 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4, _col6 + input vertices: + 1 Reducer 5 + 2 Map 7 + Statistics: Num rows: 76714 Data size: 24241624 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col2 <= (0.1 * _col4)) (type: boolean) + Statistics: Num rows: 25571 Data size: 8080436 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 9 <- Map 8 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 8 + Map Operator Tree: + TableScan + alias: item + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 236288080 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 236288080 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_item_desc (type: string), i_current_price (type: decimal(7,2)), i_wholesale_cost (type: decimal(7,2)), i_brand (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 462000 Data size: 236288080 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col6, _col8, _col9, _col10, _col11 + input vertices: + 0 Reducer 2 + Statistics: Num rows: 25571 Data size: 17848348 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: string), _col8 (type: string), _col2 (type: decimal(17,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 25571 Data size: 17848348 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 25571 Data size: 17848348 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: string) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 9 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(7,2)), VALUE._col2 (type: decimal(7,2)), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 255550079 Data size: 22544702192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25571 Data size: 17848348 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 70016 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 70016 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 8 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: decimal(17,2)) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), count(_col2) - keys: _col1 (type: int) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158398803 Data size: 13973988377 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 3 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(38,13)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 158398803 Data size: 13973988377 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158398803 Data size: 13973988377 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(38,13)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query66.q.out b/ql/src/test/results/clientpositive/perf/spark/query66.q.out index 1533d451a1..f2c0a3356c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query66.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query66.q.out @@ -443,9 +443,7 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-5 depends on stages: Stage-4 - Stage-1 depends on stages: Stage-5 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -453,19 +451,59 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 5 + Map Operator Tree: + TableScan + alias: time_dim + filterExpr: (t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 86400 Data size: 691200 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_moy (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: ship_mode filterExpr: ((sm_carrier) IN ('DIAMOND', 'AIRBORNE') and sm_ship_mode_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((sm_carrier) IN ('DIAMOND', 'AIRBORNE') and sm_ship_mode_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sm_ship_mode_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -473,19 +511,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 9 + Map 8 Map Operator Tree: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 13014 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 13014 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string), w_warehouse_sq_ft (type: int), w_city (type: string), w_county (type: string), w_state (type: string), w_country (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 13014 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -498,19 +536,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 6 + Map 11 Map Operator Tree: TableScan alias: time_dim filterExpr: (t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 691200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -518,24 +556,39 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - - Stage: Stage-4 - Spark -#### A masked pattern was here #### - Vertices: - Map 15 + Map 12 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_moy (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 13 Map Operator Tree: TableScan alias: ship_mode filterExpr: ((sm_carrier) IN ('DIAMOND', 'AIRBORNE') and sm_ship_mode_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((sm_carrier) IN ('DIAMOND', 'AIRBORNE') and sm_ship_mode_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sm_ship_mode_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -543,19 +596,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 16 + Map 14 Map Operator Tree: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 13014 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 13014 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string), w_warehouse_sq_ft (type: int), w_city (type: string), w_county (type: string), w_state (type: string), w_country (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 13014 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -564,40 +617,13 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-5 - Spark -#### A masked pattern was here #### - Vertices: - Map 13 - Map Operator Tree: - TableScan - alias: time_dim - filterExpr: (t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: t_time_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Stage: Stage-1 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 336), Map 14 (PARTITION-LEVEL SORT, 336) - Reducer 12 <- Reducer 11 (GROUP, 447) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 169), Map 7 (PARTITION-LEVEL SORT, 169) - Reducer 3 <- Reducer 2 (GROUP, 224) - Reducer 4 <- Reducer 12 (GROUP, 336), Reducer 3 (GROUP, 336) - Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 10 <- Map 9 (GROUP, 138) + Reducer 2 <- Map 1 (GROUP, 71) + Reducer 3 <- Reducer 10 (GROUP, 178), Reducer 2 (GROUP, 178) + Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -605,14 +631,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_warehouse_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null and ws_ship_mode_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 35127858780 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_ship_mode_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null and ws_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143859154 Data size: 35092850148 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_sold_time_sk (type: int), ws_ship_mode_sk (type: int), ws_warehouse_sk (type: int), ws_quantity (type: int), ws_sales_price (type: decimal(7,2)), ws_net_paid_inc_tax (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143859154 Data size: 35092850148 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -621,30 +647,70 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6 input vertices: - 1 Map 6 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + 1 Map 5 + Statistics: Num rows: 15984351 Data size: 3827604812 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col11 + input vertices: + 1 Map 6 + Statistics: Num rows: 5707369 Data size: 1361272200 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4, _col5, _col6, _col11 + input vertices: + 1 Map 7 + Statistics: Num rows: 2853684 Data size: 665116124 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5, _col6, _col11, _col15, _col16, _col17, _col18, _col19, _col20 + input vertices: + 1 Map 8 + Statistics: Num rows: 2853684 Data size: 2017905892 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col15 (type: string), _col16 (type: int), _col17 (type: string), _col18 (type: string), _col19 (type: string), _col20 (type: string), CASE WHEN ((_col11 = 1)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 1)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 + Statistics: Num rows: 2853684 Data size: 2017905892 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col6), sum(_col7), sum(_col8), sum(_col9), sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14), sum(_col15), sum(_col16), sum(_col17), sum(_col18), sum(_col19), sum(_col20), sum(_col21), sum(_col22), sum(_col23), sum(_col24), sum(_col25), sum(_col26), sum(_col27), sum(_col28), sum(_col29) + keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 + Statistics: Num rows: 2853684 Data size: 9034763544 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 2853684 Data size: 9034763544 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col6 (type: decimal(28,2)), _col7 (type: decimal(28,2)), _col8 (type: decimal(28,2)), _col9 (type: decimal(28,2)), _col10 (type: decimal(28,2)), _col11 (type: decimal(28,2)), _col12 (type: decimal(28,2)), _col13 (type: decimal(28,2)), _col14 (type: decimal(28,2)), _col15 (type: decimal(28,2)), _col16 (type: decimal(28,2)), _col17 (type: decimal(28,2)), _col18 (type: decimal(28,2)), _col19 (type: decimal(28,2)), _col20 (type: decimal(28,2)), _col21 (type: decimal(28,2)), _col22 (type: decimal(28,2)), _col23 (type: decimal(28,2)), _col24 (type: decimal(28,2)), _col25 (type: decimal(28,2)), _col26 (type: decimal(28,2)), _col27 (type: decimal(28,2)), _col28 (type: decimal(28,2)), _col29 (type: decimal(28,2)) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 10 + Map 9 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_warehouse_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null and cs_ship_mode_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 70079519076 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_ship_mode_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null and cs_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 282272460 Data size: 68688251380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_sold_time_sk (type: int), cs_ship_mode_sk (type: int), cs_warehouse_sk (type: int), cs_quantity (type: int), cs_ext_sales_price (type: decimal(7,2)), cs_net_paid_inc_ship_tax (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 282272460 Data size: 68688251380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -653,106 +719,58 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6 input vertices: - 1 Map 13 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + 1 Map 11 + Statistics: Num rows: 31363607 Data size: 7346682388 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col11 + input vertices: + 1 Map 12 + Statistics: Num rows: 11119518 Data size: 2493747100 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4, _col5, _col6, _col11 + input vertices: + 1 Map 13 + Statistics: Num rows: 5559759 Data size: 1142808544 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5, _col6, _col11, _col15, _col16, _col17, _col18, _col19, _col20 + input vertices: + 1 Map 14 + Statistics: Num rows: 5559759 Data size: 3783784334 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col15 (type: string), _col16 (type: int), _col17 (type: string), _col18 (type: string), _col19 (type: string), _col20 (type: string), CASE WHEN ((_col11 = 1)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 1)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 + Statistics: Num rows: 5559759 Data size: 3783784334 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col6), sum(_col7), sum(_col8), sum(_col9), sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14), sum(_col15), sum(_col16), sum(_col17), sum(_col18), sum(_col19), sum(_col20), sum(_col21), sum(_col22), sum(_col23), sum(_col24), sum(_col25), sum(_col26), sum(_col27), sum(_col28), sum(_col29) + keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 + Statistics: Num rows: 5559759 Data size: 17602196994 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 5559759 Data size: 17602196994 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col6 (type: decimal(28,2)), _col7 (type: decimal(28,2)), _col8 (type: decimal(28,2)), _col9 (type: decimal(28,2)), _col10 (type: decimal(28,2)), _col11 (type: decimal(28,2)), _col12 (type: decimal(28,2)), _col13 (type: decimal(28,2)), _col14 (type: decimal(28,2)), _col15 (type: decimal(28,2)), _col16 (type: decimal(28,2)), _col17 (type: decimal(28,2)), _col18 (type: decimal(28,2)), _col19 (type: decimal(28,2)), _col20 (type: decimal(28,2)), _col21 (type: decimal(28,2)), _col22 (type: decimal(28,2)), _col23 (type: decimal(28,2)), _col24 (type: decimal(28,2)), _col25 (type: decimal(28,2)), _col26 (type: decimal(28,2)), _col27 (type: decimal(28,2)), _col28 (type: decimal(28,2)), _col29 (type: decimal(28,2)) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 14 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_moy (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_moy (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) - Execution mode: vectorized - Reducer 11 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col11 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col4, _col5, _col6, _col11 - input vertices: - 1 Map 15 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: PARTIAL Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col5, _col6, _col11, _col15, _col16, _col17, _col18, _col19, _col20 - input vertices: - 1 Map 16 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col15 (type: string), _col16 (type: int), _col17 (type: string), _col18 (type: string), _col19 (type: string), _col20 (type: string), CASE WHEN ((_col11 = 1)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 1)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: sum(_col6), sum(_col7), sum(_col8), sum(_col9), sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14), sum(_col15), sum(_col16), sum(_col17), sum(_col18), sum(_col19), sum(_col20), sum(_col21), sum(_col22), sum(_col23), sum(_col24), sum(_col25), sum(_col26), sum(_col27), sum(_col28), sum(_col29) - keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - sort order: ++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - value expressions: _col6 (type: decimal(28,2)), _col7 (type: decimal(28,2)), _col8 (type: decimal(28,2)), _col9 (type: decimal(28,2)), _col10 (type: decimal(28,2)), _col11 (type: decimal(28,2)), _col12 (type: decimal(28,2)), _col13 (type: decimal(28,2)), _col14 (type: decimal(28,2)), _col15 (type: decimal(28,2)), _col16 (type: decimal(28,2)), _col17 (type: decimal(28,2)), _col18 (type: decimal(28,2)), _col19 (type: decimal(28,2)), _col20 (type: decimal(28,2)), _col21 (type: decimal(28,2)), _col22 (type: decimal(28,2)), _col23 (type: decimal(28,2)), _col24 (type: decimal(28,2)), _col25 (type: decimal(28,2)), _col26 (type: decimal(28,2)), _col27 (type: decimal(28,2)), _col28 (type: decimal(28,2)), _col29 (type: decimal(28,2)) - Reducer 12 + Reducer 10 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -760,73 +778,25 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2513700 Data size: 7958374200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(28,2)), _col7 (type: decimal(28,2)), _col8 (type: decimal(28,2)), _col9 (type: decimal(28,2)), _col10 (type: decimal(28,2)), _col11 (type: decimal(28,2)), _col12 (type: decimal(28,2)), _col13 (type: decimal(28,2)), _col14 (type: decimal(28,2)), _col15 (type: decimal(28,2)), _col16 (type: decimal(28,2)), _col17 (type: decimal(28,2)), (_col6 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col7 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col8 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col9 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col10 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col11 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col12 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col13 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col14 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col15 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col16 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col17 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), _col18 (type: decimal(28,2)), _col19 (type: decimal(28,2)), _col20 (type: decimal(28,2)), _col21 (type: decimal(28,2)), _col22 (type: decimal(28,2)), _col23 (type: decimal(28,2)), _col24 (type: decimal(28,2)), _col25 (type: decimal(28,2)), _col26 (type: decimal(28,2)), _col27 (type: decimal(28,2)), _col28 (type: decimal(28,2)), _col29 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41 - Statistics: Num rows: 316240137 Data size: 42883351482 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5027400 Data size: 15916748400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col7), sum(_col8), sum(_col9), sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14), sum(_col15), sum(_col16), sum(_col17), sum(_col18), sum(_col19), sum(_col20), sum(_col21), sum(_col22), sum(_col23), sum(_col24), sum(_col25), sum(_col26), sum(_col27), sum(_col28), sum(_col29), sum(_col30), sum(_col31), sum(_col32), sum(_col33), sum(_col34), sum(_col35), sum(_col36), sum(_col37), sum(_col38), sum(_col39), sum(_col40), sum(_col41) keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41 - Statistics: Num rows: 316240137 Data size: 42883351482 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5027400 Data size: 22673573996 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 316240137 Data size: 42883351482 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5027400 Data size: 22673573996 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col6 (type: decimal(38,2)), _col7 (type: decimal(38,2)), _col8 (type: decimal(38,2)), _col9 (type: decimal(38,2)), _col10 (type: decimal(38,2)), _col11 (type: decimal(38,2)), _col12 (type: decimal(38,2)), _col13 (type: decimal(38,2)), _col14 (type: decimal(38,2)), _col15 (type: decimal(38,2)), _col16 (type: decimal(38,2)), _col17 (type: decimal(38,2)), _col18 (type: decimal(38,12)), _col19 (type: decimal(38,12)), _col20 (type: decimal(38,12)), _col21 (type: decimal(38,12)), _col22 (type: decimal(38,12)), _col23 (type: decimal(38,12)), _col24 (type: decimal(38,12)), _col25 (type: decimal(38,12)), _col26 (type: decimal(38,12)), _col27 (type: decimal(38,12)), _col28 (type: decimal(38,12)), _col29 (type: decimal(38,12)), _col30 (type: decimal(38,2)), _col31 (type: decimal(38,2)), _col32 (type: decimal(38,2)), _col33 (type: decimal(38,2)), _col34 (type: decimal(38,2)), _col35 (type: decimal(38,2)), _col36 (type: decimal(38,2)), _col37 (type: decimal(38,2)), _col38 (type: decimal(38,2)), _col39 (type: decimal(38,2)), _col40 (type: decimal(38,2)), _col41 (type: decimal(38,2)) Reducer 2 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col11 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col4, _col5, _col6, _col11 - input vertices: - 1 Map 8 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: PARTIAL Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col5, _col6, _col11, _col15, _col16, _col17, _col18, _col19, _col20 - input vertices: - 1 Map 9 - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col15 (type: string), _col16 (type: int), _col17 (type: string), _col18 (type: string), _col19 (type: string), _col20 (type: string), CASE WHEN ((_col11 = 1)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col5 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 1)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 2)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 3)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 4)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 5)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 6)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 7)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 8)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 9)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 10)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 11)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)), CASE WHEN ((_col11 = 12)) THEN ((_col6 * CAST( _col4 AS decimal(10,0)))) ELSE (0) END (type: decimal(18,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: sum(_col6), sum(_col7), sum(_col8), sum(_col9), sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14), sum(_col15), sum(_col16), sum(_col17), sum(_col18), sum(_col19), sum(_col20), sum(_col21), sum(_col22), sum(_col23), sum(_col24), sum(_col25), sum(_col26), sum(_col27), sum(_col28), sum(_col29) - keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - sort order: ++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: PARTIAL Column stats: NONE - value expressions: _col6 (type: decimal(28,2)), _col7 (type: decimal(28,2)), _col8 (type: decimal(28,2)), _col9 (type: decimal(28,2)), _col10 (type: decimal(28,2)), _col11 (type: decimal(28,2)), _col12 (type: decimal(28,2)), _col13 (type: decimal(28,2)), _col14 (type: decimal(28,2)), _col15 (type: decimal(28,2)), _col16 (type: decimal(28,2)), _col17 (type: decimal(28,2)), _col18 (type: decimal(28,2)), _col19 (type: decimal(28,2)), _col20 (type: decimal(28,2)), _col21 (type: decimal(28,2)), _col22 (type: decimal(28,2)), _col23 (type: decimal(28,2)), _col24 (type: decimal(28,2)), _col25 (type: decimal(28,2)), _col26 (type: decimal(28,2)), _col27 (type: decimal(28,2)), _col28 (type: decimal(28,2)), _col29 (type: decimal(28,2)) - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -834,25 +804,25 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29 - Statistics: Num rows: 105417161 Data size: 14333685343 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2513700 Data size: 7958374200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(28,2)), _col7 (type: decimal(28,2)), _col8 (type: decimal(28,2)), _col9 (type: decimal(28,2)), _col10 (type: decimal(28,2)), _col11 (type: decimal(28,2)), _col12 (type: decimal(28,2)), _col13 (type: decimal(28,2)), _col14 (type: decimal(28,2)), _col15 (type: decimal(28,2)), _col16 (type: decimal(28,2)), _col17 (type: decimal(28,2)), (_col6 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col7 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col8 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col9 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col10 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col11 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col12 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col13 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col14 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col15 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col16 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), (_col17 / CAST( _col1 AS decimal(10,0))) (type: decimal(38,12)), _col18 (type: decimal(28,2)), _col19 (type: decimal(28,2)), _col20 (type: decimal(28,2)), _col21 (type: decimal(28,2)), _col22 (type: decimal(28,2)), _col23 (type: decimal(28,2)), _col24 (type: decimal(28,2)), _col25 (type: decimal(28,2)), _col26 (type: decimal(28,2)), _col27 (type: decimal(28,2)), _col28 (type: decimal(28,2)), _col29 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41 - Statistics: Num rows: 316240137 Data size: 42883351482 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5027400 Data size: 15916748400 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col7), sum(_col8), sum(_col9), sum(_col10), sum(_col11), sum(_col12), sum(_col13), sum(_col14), sum(_col15), sum(_col16), sum(_col17), sum(_col18), sum(_col19), sum(_col20), sum(_col21), sum(_col22), sum(_col23), sum(_col24), sum(_col25), sum(_col26), sum(_col27), sum(_col28), sum(_col29), sum(_col30), sum(_col31), sum(_col32), sum(_col33), sum(_col34), sum(_col35), sum(_col36), sum(_col37), sum(_col38), sum(_col39), sum(_col40), sum(_col41) keys: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41 - Statistics: Num rows: 316240137 Data size: 42883351482 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5027400 Data size: 22673573996 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 316240137 Data size: 42883351482 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5027400 Data size: 22673573996 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col6 (type: decimal(38,2)), _col7 (type: decimal(38,2)), _col8 (type: decimal(38,2)), _col9 (type: decimal(38,2)), _col10 (type: decimal(38,2)), _col11 (type: decimal(38,2)), _col12 (type: decimal(38,2)), _col13 (type: decimal(38,2)), _col14 (type: decimal(38,2)), _col15 (type: decimal(38,2)), _col16 (type: decimal(38,2)), _col17 (type: decimal(38,2)), _col18 (type: decimal(38,12)), _col19 (type: decimal(38,12)), _col20 (type: decimal(38,12)), _col21 (type: decimal(38,12)), _col22 (type: decimal(38,12)), _col23 (type: decimal(38,12)), _col24 (type: decimal(38,12)), _col25 (type: decimal(38,12)), _col26 (type: decimal(38,12)), _col27 (type: decimal(38,12)), _col28 (type: decimal(38,12)), _col29 (type: decimal(38,12)), _col30 (type: decimal(38,2)), _col31 (type: decimal(38,2)), _col32 (type: decimal(38,2)), _col33 (type: decimal(38,2)), _col34 (type: decimal(38,2)), _col35 (type: decimal(38,2)), _col36 (type: decimal(38,2)), _col37 (type: decimal(38,2)), _col38 (type: decimal(38,2)), _col39 (type: decimal(38,2)), _col40 (type: decimal(38,2)), _col41 (type: decimal(38,2)) - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -860,30 +830,30 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41 - Statistics: Num rows: 158120068 Data size: 21441675673 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2513700 Data size: 11336787000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 158120068 Data size: 21441675673 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2513700 Data size: 11336787000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(38,2)), _col7 (type: decimal(38,2)), _col8 (type: decimal(38,2)), _col9 (type: decimal(38,2)), _col10 (type: decimal(38,2)), _col11 (type: decimal(38,2)), _col12 (type: decimal(38,2)), _col13 (type: decimal(38,2)), _col14 (type: decimal(38,2)), _col15 (type: decimal(38,2)), _col16 (type: decimal(38,2)), _col17 (type: decimal(38,2)), _col18 (type: decimal(38,12)), _col19 (type: decimal(38,12)), _col20 (type: decimal(38,12)), _col21 (type: decimal(38,12)), _col22 (type: decimal(38,12)), _col23 (type: decimal(38,12)), _col24 (type: decimal(38,12)), _col25 (type: decimal(38,12)), _col26 (type: decimal(38,12)), _col27 (type: decimal(38,12)), _col28 (type: decimal(38,12)), _col29 (type: decimal(38,12)), _col30 (type: decimal(38,2)), _col31 (type: decimal(38,2)), _col32 (type: decimal(38,2)), _col33 (type: decimal(38,2)), _col34 (type: decimal(38,2)), _col35 (type: decimal(38,2)), _col36 (type: decimal(38,2)), _col37 (type: decimal(38,2)), _col38 (type: decimal(38,2)), _col39 (type: decimal(38,2)), _col40 (type: decimal(38,2)), _col41 (type: decimal(38,2)) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: decimal(38,2)), VALUE._col6 (type: decimal(38,2)), VALUE._col7 (type: decimal(38,2)), VALUE._col8 (type: decimal(38,2)), VALUE._col9 (type: decimal(38,2)), VALUE._col10 (type: decimal(38,2)), VALUE._col11 (type: decimal(38,2)), VALUE._col12 (type: decimal(38,2)), VALUE._col13 (type: decimal(38,2)), VALUE._col14 (type: decimal(38,2)), VALUE._col15 (type: decimal(38,2)), VALUE._col16 (type: decimal(38,2)), VALUE._col17 (type: decimal(38,12)), VALUE._col18 (type: decimal(38,12)), VALUE._col19 (type: decimal(38,12)), VALUE._col20 (type: decimal(38,12)), VALUE._col21 (type: decimal(38,12)), VALUE._col22 (type: decimal(38,12)), VALUE._col23 (type: decimal(38,12)), VALUE._col24 (type: decimal(38,12)), VALUE._col25 (type: decimal(38,12)), VALUE._col26 (type: decimal(38,12)), VALUE._col27 (type: decimal(38,12)), VALUE._col28 (type: decimal(38,12)), VALUE._col29 (type: decimal(38,2)), VALUE._col30 (type: decimal(38,2)), VALUE._col31 (type: decimal(38,2)), VALUE._col32 (type: decimal(38,2)), VALUE._col33 (type: decimal(38,2)), VALUE._col34 (type: decimal(38,2)), VALUE._col35 (type: decimal(38,2)), VALUE._col36 (type: decimal(38,2)), VALUE._col37 (type: decimal(38,2)), VALUE._col38 (type: decimal(38,2)), VALUE._col39 (type: decimal(38,2)), VALUE._col40 (type: decimal(38,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41 - Statistics: Num rows: 158120068 Data size: 21441675673 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2513700 Data size: 11336787000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 451000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), 'DIAMOND,AIRBORNE' (type: string), 2002 (type: int), _col6 (type: decimal(38,2)), _col7 (type: decimal(38,2)), _col8 (type: decimal(38,2)), _col9 (type: decimal(38,2)), _col10 (type: decimal(38,2)), _col11 (type: decimal(38,2)), _col12 (type: decimal(38,2)), _col13 (type: decimal(38,2)), _col14 (type: decimal(38,2)), _col15 (type: decimal(38,2)), _col16 (type: decimal(38,2)), _col17 (type: decimal(38,2)), _col18 (type: decimal(38,12)), _col19 (type: decimal(38,12)), _col20 (type: decimal(38,12)), _col21 (type: decimal(38,12)), _col22 (type: decimal(38,12)), _col23 (type: decimal(38,12)), _col24 (type: decimal(38,12)), _col25 (type: decimal(38,12)), _col26 (type: decimal(38,12)), _col27 (type: decimal(38,12)), _col28 (type: decimal(38,12)), _col29 (type: decimal(38,12)), _col30 (type: decimal(38,2)), _col31 (type: decimal(38,2)), _col32 (type: decimal(38,2)), _col33 (type: decimal(38,2)), _col34 (type: decimal(38,2)), _col35 (type: decimal(38,2)), _col36 (type: decimal(38,2)), _col37 (type: decimal(38,2)), _col38 (type: decimal(38,2)), _col39 (type: decimal(38,2)), _col40 (type: decimal(38,2)), _col41 (type: decimal(38,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43 - Statistics: Num rows: 100 Data size: 13500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 461400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 461400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query67.q.out b/ql/src/test/results/clientpositive/perf/spark/query67.q.out index db91e67fdc..0b8061d391 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query67.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query67.q.out @@ -94,19 +94,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 1460980 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 162320 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int), d_qoy (type: int) + outputColumnNames: _col0, _col2, _col3, _col4 + Statistics: Num rows: 8116 Data size: 162320 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -118,11 +138,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 486), Reducer 2 (PARTITION-LEVEL SORT, 486) - Reducer 4 <- Reducer 3 (GROUP, 1009) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 1009) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 86), Map 8 (PARTITION-LEVEL SORT, 86) + Reducer 3 <- Reducer 2 (GROUP, 1009) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 1009) + Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -130,90 +149,64 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70513332076 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 64310837112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int), d_qoy (type: int) - outputColumnNames: _col0, _col2, _col3, _col4 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int) + Statistics: Num rows: 525329897 Data size: 64310837112 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col7, _col8, _col9 + input vertices: + 1 Map 6 + Statistics: Num rows: 58365993 Data size: 5100942084 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col7, _col8, _col9, _col11 + input vertices: + 1 Map 7 + Statistics: Num rows: 58365993 Data size: 10798610860 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 58365993 Data size: 10798610860 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col11 (type: string) Execution mode: vectorized - Map 9 + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand (type: string), i_class (type: string), i_category (type: string), i_product_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 181566000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) Execution mode: vectorized Reducer 2 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col7, _col8, _col9 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col7, _col8, _col9, _col11 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col11 (type: string) - Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -222,24 +215,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col4, _col7, _col8, _col9, _col11, _col13, _col14, _col15, _col16 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365993 Data size: 33269518165 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col15 (type: string), _col14 (type: string), _col13 (type: string), _col16 (type: string), _col7 (type: int), _col9 (type: int), _col8 (type: int), _col11 (type: string), COALESCE((_col4 * CAST( _col3 AS decimal(10,0))),0) (type: decimal(18,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365993 Data size: 33269518165 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col8) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 6899852151 Data size: 608706960084 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525293937 Data size: 326207534877 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col8 (type: bigint) sort order: +++++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col8 (type: bigint) - Statistics: Num rows: 6899852151 Data size: 608706960084 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525293937 Data size: 326207534877 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col9 (type: decimal(28,2)) - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -247,26 +240,26 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY._col5 (type: int), KEY._col6 (type: int), KEY._col7 (type: string), KEY._col8 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9 - Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525293937 Data size: 326207534877 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col9 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525293937 Data size: 322005183381 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col8 (type: decimal(28,2)) sort order: +- Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525293937 Data size: 322005183381 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: string), KEY.reducesinkkey1 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525293937 Data size: 322005183381 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -287,32 +280,32 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525293937 Data size: 322005183381 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (rank_window_0 <= 100) (type: boolean) - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 175097979 Data size: 107335061127 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col8 (type: decimal(28,2)), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 175097979 Data size: 108035453043 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col8 (type: decimal(28,2)), _col9 (type: int) sort order: ++++++++++ - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 175097979 Data size: 108035453043 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: string), KEY.reducesinkkey8 (type: decimal(28,2)), KEY.reducesinkkey9 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 175097979 Data size: 108035453043 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 61700 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 61700 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query68.q.out b/ql/src/test/results/clientpositive/perf/spark/query68.q.out index f2e676381f..8a2b59089e 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query68.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query68.q.out @@ -90,19 +90,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 11 + Map 10 Map Operator Tree: TableScan alias: store filterExpr: ((s_city) IN ('Cedar Grove', 'Wildwood') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 165288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_city) IN ('Cedar Grove', 'Wildwood') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 8245 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 8245 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col4 (type: int) @@ -110,19 +110,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 12 + Map 11 Map Operator Tree: TableScan alias: household_demographics filterExpr: (((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1855 Data size: 22260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1855 Data size: 22260 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -130,16 +130,35 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work + Map 9 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (1998, 1999, 2000) and d_dom BETWEEN 1 AND 2 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year) IN (1998, 1999, 2000) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) (type: boolean) + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 5 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 882), Reducer 9 (PARTITION-LEVEL SORT, 882) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 148), Map 5 (PARTITION-LEVEL SORT, 148) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 231), Reducer 8 (PARTITION-LEVEL SORT, 231) Reducer 4 <- Reducer 3 (SORT, 1) - Reducer 7 <- Map 10 (PARTITION-LEVEL SORT, 398), Map 6 (PARTITION-LEVEL SORT, 398) - Reducer 8 <- Map 13 (PARTITION-LEVEL SORT, 846), Reducer 7 (PARTITION-LEVEL SORT, 846) - Reducer 9 <- Reducer 8 (GROUP, 582) + Reducer 7 <- Map 12 (PARTITION-LEVEL SORT, 31), Map 6 (PARTITION-LEVEL SORT, 31) + Reducer 8 <- Reducer 7 (GROUP, 58) #### A masked pattern was here #### Vertices: Map 1 @@ -147,58 +166,39 @@ STAGE PLANS: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 15040000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string) Execution mode: vectorized - Map 10 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year) IN (1998, 1999, 2000) and d_dom BETWEEN 1 AND 2 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year) IN (1998, 1999, 2000) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 13 + Map 12 Map Operator Tree: TableScan alias: customer_address filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_city (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 5 @@ -206,19 +206,19 @@ STAGE PLANS: TableScan alias: current_addr filterExpr: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ca_address_sk is not null (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_city (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 6 @@ -226,21 +226,53 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_hdemo_sk is not null and ss_addr_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 198131908360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 457565061 Data size: 157393968356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_hdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)), ss_ext_tax (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) + Statistics: Num rows: 457565061 Data size: 157393968356 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + input vertices: + 1 Map 9 + Statistics: Num rows: 163378059 Data size: 50915494812 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7, _col8 + input vertices: + 1 Map 10 + Statistics: Num rows: 65777178 Data size: 15988811588 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col8 + input vertices: + 1 Map 11 + Statistics: Num rows: 16946760 Data size: 67787384 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 16946760 Data size: 67787384 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -250,12 +282,12 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col5 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22160000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22160000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string), _col3 (type: string), _col5 (type: string) Reducer 3 Reduce Operator Tree: @@ -266,18 +298,18 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col2, _col3, _col5, _col6, _col8, _col9, _col10, _col11 - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 11964412560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col5 <> _col8) (type: boolean) - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 11964412560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col2 (type: string), _col5 (type: string), _col8 (type: string), _col6 (type: int), _col9 (type: decimal(17,2)), _col11 (type: decimal(17,2)), _col10 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 11964412560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col4 (type: int) sort order: ++ - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 11964412560 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) Reducer 4 @@ -286,56 +318,18 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey1 (type: int), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: decimal(17,2)), VALUE._col5 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 11964412560 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 70600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 70600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 7 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7, _col8 - input vertices: - 1 Map 11 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col8 - input vertices: - 1 Map 12 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) - Reducer 8 Reduce Operator Tree: Join Operator condition map: @@ -344,20 +338,20 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col8, _col18 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 1643836064 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col7), sum(_col8) keys: _col1 (type: int), _col18 (type: string), _col3 (type: int), _col5 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 7337947088 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 7337947088 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) - Reducer 9 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -365,16 +359,16 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 7337947088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col0 (type: int), _col1 (type: string), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 7337947084 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16946760 Data size: 7337947084 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/perf/spark/query69.q.out b/ql/src/test/results/clientpositive/perf/spark/query69.q.out index e17832c8e8..ff2b54d1ce 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query69.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query69.q.out @@ -91,80 +91,31 @@ select limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4, Stage-5 + Stage-1 depends on stages: Stage-2 + Stage-4 is a root stage + Stage-5 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Spark -#### A masked pattern was here #### - Vertices: - Map 11 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 14 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-4 - Spark -#### A masked pattern was here #### - Vertices: - Map 17 + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -173,52 +124,26 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 13 <- Map 12 (GROUP, 169) - Reducer 16 <- Map 15 (GROUP, 336) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 8 (PARTITION-LEVEL SORT, 855) - Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 597), Reducer 2 (PARTITION-LEVEL SORT, 597) - Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 1009), Reducer 13 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009) - Reducer 5 <- Reducer 16 (PARTITION-LEVEL SORT, 648), Reducer 4 (PARTITION-LEVEL SORT, 648) - Reducer 6 <- Reducer 5 (GROUP, 265) - Reducer 7 <- Reducer 6 (SORT, 1) + Reducer 11 <- Map 10 (GROUP, 2) + Reducer 14 <- Map 13 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: c - filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int) - Execution mode: vectorized Map 10 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 1151734616 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -227,38 +152,34 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 11 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) + 1 Map 12 + Statistics: Num rows: 17104380 Data size: 68274076 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: int) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 168231 Data size: 671516 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 168231 Data size: 671516 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work - Map 12 + Map 13 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + filterExpr: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 2292391500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 285115246 Data size: 2269509840 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) + expressions: cs_sold_date_sk (type: int), cs_ship_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285115246 Data size: 2269509840 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -267,34 +188,34 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 14 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + 1 Map 15 + Statistics: Num rows: 33642830 Data size: 128862124 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167041 Data size: 639820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167041 Data size: 639820 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work - Map 15 + Map 8 Map Operator Tree: TableScan - alias: catalog_sales - filterExpr: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 4400627472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: cs_sold_date_sk (type: int), cs_ship_customer_sk (type: int) + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -303,96 +224,131 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 17 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col1 (type: int) - mode: hash + 1 Map 9 + Statistics: Num rows: 62428523 Data size: 155171512 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62428523 Data size: 155171512 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 168231 Data size: 418156 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 8 + Reducer 11 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 168231 Data size: 671516 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 168231 Data size: 1344440 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + Reducer 14 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 167041 Data size: 639820 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 167041 Data size: 1307984 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 9), Map 6 (PARTITION-LEVEL SORT, 9) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 6), Reducer 2 (PARTITION-LEVEL SORT, 6) + Reducer 4 <- Reducer 3 (GROUP, 2) + Reducer 5 <- Reducer 4 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 948805540 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 77201384 Data size: 915613760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int) + Execution mode: vectorized + Map 6 Map Operator Tree: TableScan alias: ca filterExpr: ((ca_state) IN ('CO', 'IL', 'MN') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_state) IN ('CO', 'IL', 'MN') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2352941 Data size: 211764690 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2352941 Data size: 211764690 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2352941 Data size: 211764690 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 9 + Map 7 Map Operator Tree: TableScan alias: customer_demographics filterExpr: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 675833400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 675833400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int), cd_gender (type: string), cd_marital_status (type: string), cd_education_status (type: string), cd_purchase_estimate (type: int), cd_credit_rating (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 675833400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 675833400 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string) Execution mode: vectorized - Reducer 13 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) - Reducer 16 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) Reducer 2 Reduce Operator Tree: Join Operator @@ -402,14 +358,16 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4541258 Data size: 25527216 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4541258 Data size: 25527216 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reducer 3 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -418,69 +376,58 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - value expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + Statistics: Num rows: 4605476 Data size: 1671787788 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + Left Outer Join 0 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10, _col12 + input vertices: + 1 Map 8 + 2 Reducer 11 + Statistics: Num rows: 9896 Data size: 3631832 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col12 is null (type: boolean) + Statistics: Num rows: 1 Data size: 367 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 1 Data size: 367 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col6, _col7, _col8, _col9, _col10, _col14 + input vertices: + 1 Reducer 14 + Statistics: Num rows: 844 Data size: 306372 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col14 is null (type: boolean) + Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + outputColumnNames: _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 367 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) + sort order: +++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) + Statistics: Num rows: 1 Data size: 367 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col5 (type: bigint) Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - Left Outer Join 0 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 1393909496 Data size: 122971100382 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col12 is null (type: boolean) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) - outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) - Reducer 5 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col6, _col7, _col8, _col9, _col10, _col14 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col14 is null (type: boolean) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) - outputColumnNames: _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) - sort order: +++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col5 (type: bigint) - Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -488,35 +435,85 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 367 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col5 (type: bigint), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 383 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: int), _col6 (type: string) sort order: +++++ - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 383 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint) - Reducer 7 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: bigint), KEY.reducesinkkey3 (type: int), VALUE._col0 (type: bigint), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 383 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 383 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 383 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 12 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 15 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and d_moy BETWEEN 1 AND 3 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 217 Data size: 2604 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-0 Fetch Operator limit: 100 diff --git a/ql/src/test/results/clientpositive/perf/spark/query7.q.out b/ql/src/test/results/clientpositive/perf/spark/query7.q.out index e11fee6a13..d46c0f9aa2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query7.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query7.q.out @@ -39,28 +39,69 @@ select i_item_id, limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 2 + Map Operator Tree: + TableScan + alias: customer_demographics + filterExpr: ((cd_gender = 'F') and (cd_marital_status = 'W') and (cd_education_status = 'Primary') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1861800 Data size: 498962400 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 14776 Data size: 3959968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14776 Data size: 3915640 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 3 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 4 Map Operator Tree: TableScan alias: promotion filterExpr: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 400200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 400200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_promo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 400200 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -69,14 +110,8 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438) - Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 534), Reducer 3 (PARTITION-LEVEL SORT, 534) - Reducer 5 <- Reducer 4 (GROUP, 582) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -84,147 +119,99 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_item_sk is not null and ss_promo_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 195930958348 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_cdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501686735 Data size: 170654006468 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_cdemo_sk (type: int), ss_promo_sk (type: int), ss_quantity (type: int), ss_list_price (type: decimal(7,2)), ss_sales_price (type: decimal(7,2)), ss_coupon_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Statistics: Num rows: 501686735 Data size: 170654006468 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 2 + Statistics: Num rows: 4037893 Data size: 16151920 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 3 + Statistics: Num rows: 1441769 Data size: 5767420 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 4 + Statistics: Num rows: 1441769 Data size: 5767416 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 6 <- Map 5 (GROUP, 2) + Reducer 7 <- Reducer 6 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 5 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: customer_demographics - filterExpr: ((cd_gender = 'F') and (cd_marital_status = 'W') and (cd_education_status = 'Primary') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 8 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5, _col6, _col7, _col18 + input vertices: + 0 Map 1 + Statistics: Num rows: 1441769 Data size: 144177240 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col4), count(_col4), sum(_col5), count(_col5), sum(_col7), count(_col7), sum(_col6), count(_col6) + keys: _col18 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 310774 Data size: 147928424 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 310774 Data size: 147928424 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(17,2)), _col8 (type: bigint) Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Reducer 3 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col5, _col6, _col7 - input vertices: - 1 Map 9 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col5, _col6, _col7, _col18 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col4), count(_col4), sum(_col5), count(_col5), sum(_col7), count(_col7), sum(_col6), count(_col6) - keys: _col18 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(17,2)), _col8 (type: bigint) - Reducer 5 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -232,30 +219,30 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 147928424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (UDFToDouble(_col1) / _col2) (type: double), (_col3 / _col4) (type: decimal(37,22)), (_col5 / _col6) (type: decimal(37,22)), (_col7 / _col8) (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 137983656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 137983656 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double), _col2 (type: decimal(37,22)), _col3 (type: decimal(37,22)), _col4 (type: decimal(37,22)) - Reducer 6 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double), VALUE._col1 (type: decimal(37,22)), VALUE._col2 (type: decimal(37,22)), VALUE._col3 (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 310774 Data size: 137983656 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 44400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 44400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query70.q.out b/ql/src/test/results/clientpositive/perf/spark/query70.q.out index 4222b5262d..b311875a88 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query70.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query70.q.out @@ -73,54 +73,49 @@ select limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 10 Map Operator Tree: TableScan - alias: store - filterExpr: (s_state is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (s_state is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int), s_county (type: string), s_state (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - - Stage: Stage-3 - Spark -#### A masked pattern was here #### - Vertices: - Map 14 + Map 11 Map Operator Tree: TableScan alias: store filterExpr: (s_store_sk is not null and s_state is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_state is not null and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 153360 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -129,132 +124,102 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 11 <- Reducer 10 (GROUP, 481) - Reducer 12 <- Reducer 11 (PARTITION-LEVEL SORT, 241) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 561), Reducer 2 (PARTITION-LEVEL SORT, 561) - Reducer 4 <- Reducer 3 (GROUP, 1009) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 793) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 8 <- Map 7 (GROUP, 2) + Reducer 9 <- Reducer 8 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 5 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_net_profit (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 13 - Map Operator Tree: - TableScan - alias: date_dim + alias: d1 filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan - alias: d1 - filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: (s_state is not null and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 320352 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + predicate: (s_state is not null and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 320352 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int), s_county (type: string), s_state (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1704 Data size: 320352 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 9 + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_store_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66010002860 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 60203629900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + Statistics: Num rows: 525329897 Data size: 60203629900 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 10 + Statistics: Num rows: 58365993 Data size: 4029054188 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col6 + input vertices: + 1 Map 11 + Statistics: Num rows: 58365993 Data size: 8909599062 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col6 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1715 Data size: 339570 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1715 Data size: 339570 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)) Execution mode: vectorized - Reducer 10 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col6 - input vertices: - 1 Map 14 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)) - Reducer 11 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -262,20 +227,22 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 49 Data size: 9702 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: decimal(17,2)) sort order: +- Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 49 Data size: 9702 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 12 + Reducer 9 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: decimal(17,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 49 Data size: 9702 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -296,74 +263,90 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 49 Data size: 9702 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (rank_window_0 <= 5) (type: boolean) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 3168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE - Reducer 2 + Statistics: Num rows: 16 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col7 (type: string) + 1 _col0 (type: string) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 66010002860 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 525329897 Data size: 60203629900 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_net_profit (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 525329897 Data size: 60203629900 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 5 + Statistics: Num rows: 58365993 Data size: 4029054188 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col6, _col7 + input vertices: + 1 Map 6 + Statistics: Num rows: 58365993 Data size: 14629466376 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col7 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col2, _col6, _col7 + input vertices: + 1 Reducer 9 + Statistics: Num rows: 19058283 Data size: 3506724184 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col7 (type: string), _col6 (type: string), _col2 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 19058283 Data size: 3506724184 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 10080 Data size: 3064320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) + Statistics: Num rows: 10080 Data size: 3064320 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: decimal(17,2)) + Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col6, _col7 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col7 (type: string) - sort order: + - Map-reduce partition columns: _col7 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col6 (type: string) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col7 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2, _col6, _col7 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: string), _col6 (type: string), _col2 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(17,2)) - Reducer 4 + Reducer 2 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -371,24 +354,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 72960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(17,2)), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 72960 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (grouping(_col3, 1) + grouping(_col3, 0)) (type: bigint), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string), _col2 (type: decimal(17,2)) sort order: ++- Map-reduce partition columns: (grouping(_col3, 1) + grouping(_col3, 0)) (type: bigint), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string) - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 72960 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: decimal(17,2)), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 72960 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -409,30 +392,30 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 72960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: decimal(17,2)), _col0 (type: string), _col1 (type: string), (grouping(_col3, 1) + grouping(_col3, 0)) (type: bigint), rank_window_0 (type: int), CASE WHEN (((grouping(_col3, 1) + grouping(_col3, 0)) = 0)) THEN (_col0) ELSE (null) END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 118080 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: bigint), _col5 (type: string), _col4 (type: int) sort order: -++ - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 118080 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: decimal(17,2)), _col1 (type: string), _col2 (type: string) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 118080 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query71.q.out b/ql/src/test/results/clientpositive/perf/spark/query71.q.out index eded78cbe7..b3527f4f94 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query71.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query71.q.out @@ -75,195 +75,253 @@ select i_brand_id brand_id, i_brand brand,t_hour,t_minute, order by ext_price desc, i_brand_id POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 13 (PARTITION-LEVEL SORT, 398) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 10 (PARTITION-LEVEL SORT, 154) - Reducer 3 <- Map 14 (PARTITION-LEVEL SORT, 943), Reducer 12 (PARTITION-LEVEL SORT, 943), Reducer 2 (PARTITION-LEVEL SORT, 943), Reducer 9 (PARTITION-LEVEL SORT, 943) - Reducer 4 <- Map 15 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009) - Reducer 5 <- Reducer 4 (GROUP, 1009) - Reducer 6 <- Reducer 5 (SORT, 1) - Reducer 9 <- Map 10 (PARTITION-LEVEL SORT, 305), Map 8 (PARTITION-LEVEL SORT, 305) #### A masked pattern was here #### Vertices: - Map 1 + Map 11 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_sold_date_sk is not null and ws_item_sk is not null and ws_sold_time_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: time_dim + filterExpr: ((t_meal_time) IN ('breakfast', 'dinner') and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 86400 Data size: 8553600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_item_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: ((t_meal_time) IN ('breakfast', 'dinner') and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 43200 Data size: 4276800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_sold_time_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + expressions: t_time_sk (type: int), t_hour (type: int), t_minute (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 43200 Data size: 4276800 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 11 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null and ss_sold_time_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_sold_time_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_date_sk (type: int), ss_sold_time_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 11), Map 10 (PARTITION-LEVEL SORT, 11), Map 6 (PARTITION-LEVEL SORT, 11), Map 8 (PARTITION-LEVEL SORT, 11) + Reducer 3 <- Reducer 2 (GROUP, 4) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_sold_date_sk is not null and ws_item_sk is not null and ws_sold_time_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17852017748 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_item_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null) (type: boolean) + Statistics: Num rows: 143930836 Data size: 17843112740 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_sold_time_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 143930836 Data size: 17843112740 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 5 + Statistics: Num rows: 3941098 Data size: 468763976 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 3941098 Data size: 468763976 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 26077346 Data size: 1291228396 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(7,2)), _col2 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 10 Map Operator Tree: TableScan alias: item filterExpr: ((i_manager_id = 1) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 51734956 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manager_id = 1) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 821160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand_id (type: int), i_brand (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 821228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7333 Data size: 821228 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: string) Execution mode: vectorized - Map 15 + Map 6 Map Operator Tree: TableScan - alias: time_dim - filterExpr: ((t_meal_time) IN ('breakfast', 'dinner') and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + filterExpr: (cs_sold_date_sk is not null and cs_item_sk is not null and cs_sold_time_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 35538018272 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((t_meal_time) IN ('breakfast', 'dinner') and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null) (type: boolean) + Statistics: Num rows: 285116947 Data size: 35183503056 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: t_time_sk (type: int), t_hour (type: int), t_minute (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + expressions: cs_sold_date_sk (type: int), cs_sold_time_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 285116947 Data size: 35183503056 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 7 + Statistics: Num rows: 7751851 Data size: 764926716 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 7751851 Data size: 764926716 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 26077346 Data size: 1291228396 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(7,2)), _col2 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 8 Map Operator Tree: TableScan - alias: catalog_sales - filterExpr: (cs_sold_date_sk is not null and cs_item_sk is not null and cs_sold_time_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_sold_date_sk is not null and ss_item_sk is not null and ss_sold_time_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 68313180432 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_sold_time_sk is not null) (type: boolean) + Statistics: Num rows: 525325345 Data size: 62303675448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: cs_sold_date_sk (type: int), cs_sold_time_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + expressions: ss_sold_date_sk (type: int), ss_sold_time_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 525325345 Data size: 62303675448 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 14384397 Data size: 57537704 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 14384397 Data size: 57537704 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 26077346 Data size: 1291228396 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(7,2)), _col2 (type: int) Execution mode: vectorized - Reducer 12 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1108786976 Data size: 120333742785 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(7,2)), _col2 (type: int) + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1108786976 Data size: 120333742785 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(7,2)), _col2 (type: int) - Reducer 3 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -272,36 +330,30 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col4, _col5 - Statistics: Num rows: 1219665700 Data size: 132367119932 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1219665700 Data size: 132367119932 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(7,2)), _col4 (type: int), _col5 (type: string) - Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col4, _col5, _col8, _col9 - Statistics: Num rows: 1341632299 Data size: 145603835081 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - keys: _col4 (type: int), _col8 (type: int), _col9 (type: int), _col5 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1341632299 Data size: 145603835081 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) - sort order: ++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) - Statistics: Num rows: 1341632299 Data size: 145603835081 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(17,2)) - Reducer 5 + Statistics: Num rows: 3983933 Data size: 414329080 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col4, _col5, _col8, _col9 + input vertices: + 1 Map 11 + Statistics: Num rows: 1991967 Data size: 223100348 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0) + keys: _col4 (type: int), _col8 (type: int), _col9 (type: int), _col5 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1991967 Data size: 446200540 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + sort order: ++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + Statistics: Num rows: 1991967 Data size: 446200540 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: decimal(17,2)) + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -309,47 +361,30 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1991967 Data size: 446200540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col1 (type: int), _col2 (type: int), _col4 (type: decimal(17,2)), _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1991967 Data size: 454168340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: decimal(17,2)), _col5 (type: int) sort order: -+ - Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1991967 Data size: 454168340 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: int) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: int), KEY.reducesinkkey0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1991967 Data size: 446200540 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1991967 Data size: 446200540 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1108786976 Data size: 120333742785 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(7,2)), _col2 (type: int) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query72.q.out b/ql/src/test/results/clientpositive/perf/spark/query72.q.out index 37cf70413e..729c77577c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query72.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query72.q.out @@ -61,7 +61,10 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-5 + Stage-1 depends on stages: Stage-6 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -69,19 +72,44 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 7 + Map 16 + Map Operator Tree: + TableScan + alias: d2 + filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_week_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int), _col20 (type: int) + 1 _col0 (type: int), _col1 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 Map Operator Tree: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -90,23 +118,48 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-3 + Stage: Stage-4 Spark #### A masked pattern was here #### Vertices: Map 15 + Map Operator Tree: + TableScan + alias: d3 + filterExpr: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 12 Map Operator Tree: TableScan alias: household_demographics filterExpr: ((hd_buy_potential = '1001-5000') and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 691200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((hd_buy_potential = '1001-5000') and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1440 Data size: 138240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1440 Data size: 139680 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -114,15 +167,15 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 16 + Map 13 Map Operator Tree: TableScan alias: promotion - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_promo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col5 (type: int) @@ -131,18 +184,40 @@ STAGE PLANS: Local Work: Map Reduce Local Work + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 10 + Map Operator Tree: + TableScan + alias: d1 + filterExpr: ((d_year = 2001) and d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7743194 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and d_date_sk is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 69112 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string), d_week_seq (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 652 Data size: 69112 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 14 (PARTITION-LEVEL SORT, 338), Reducer 9 (PARTITION-LEVEL SORT, 338) - Reducer 11 <- Map 17 (PARTITION-LEVEL SORT, 452), Reducer 10 (PARTITION-LEVEL SORT, 452) - Reducer 12 <- Map 18 (PARTITION-LEVEL SORT, 492), Reducer 11 (PARTITION-LEVEL SORT, 492) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 186), Reducer 12 (PARTITION-LEVEL SORT, 186) - Reducer 3 <- Map 19 (PARTITION-LEVEL SORT, 67), Reducer 2 (PARTITION-LEVEL SORT, 67) - Reducer 4 <- Map 20 (PARTITION-LEVEL SORT, 97), Reducer 3 (PARTITION-LEVEL SORT, 97) - Reducer 5 <- Reducer 4 (GROUP, 80) - Reducer 6 <- Reducer 5 (SORT, 1) - Reducer 9 <- Map 13 (PARTITION-LEVEL SORT, 306), Map 8 (PARTITION-LEVEL SORT, 306) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 42), Reducer 9 (PARTITION-LEVEL SORT, 42) + Reducer 3 <- Map 17 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009) + Reducer 4 <- Reducer 3 (GROUP, 1009) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 8 <- Map 11 (PARTITION-LEVEL SORT, 99), Map 7 (PARTITION-LEVEL SORT, 99) + Reducer 9 <- Map 14 (PARTITION-LEVEL SORT, 9), Reducer 8 (PARTITION-LEVEL SORT, 9) #### A masked pattern was here #### Vertices: Map 1 @@ -150,14 +225,14 @@ STAGE PLANS: TableScan alias: inventory filterExpr: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 593821108 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -166,232 +241,110 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col5 input vertices: - 1 Map 7 - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + 1 Map 6 + Statistics: Num rows: 37584000 Data size: 4201885108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 4201885108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col3 (type: int), _col5 (type: string) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 13 - Map Operator Tree: - TableScan - alias: d1 - filterExpr: ((d_year = 2001) and d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_date (type: string), d_week_seq (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: int) - Execution mode: vectorized - Map 14 + Map 11 Map Operator Tree: TableScan alias: customer_demographics filterExpr: ((cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 165700200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 23671419 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 23671419 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 23671419 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 17 + Map 14 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_desc (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 18 - Map Operator Tree: - TableScan - alias: d3 - filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_date (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 86856000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 19 - Map Operator Tree: - TableScan - alias: d2 - filterExpr: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_week_seq (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 20 + Map 17 Map Operator Tree: TableScan alias: catalog_returns filterExpr: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 230391048 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 230391048 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_item_sk (type: int), cr_order_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 230391048 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 230391048 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 8 + Map 7 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_sold_date_sk is not null and cs_ship_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 9181123640 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 282274763 Data size: 8998926960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_ship_date_sk (type: int), cs_bill_cdemo_sk (type: int), cs_bill_hdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_order_number (type: int), cs_quantity (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int) + Statistics: Num rows: 282274763 Data size: 8998926960 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9, _col10 + input vertices: + 1 Map 10 + Statistics: Num rows: 100076475 Data size: 12581416510 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 100076475 Data size: 12581416510 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int) Execution mode: vectorized - Reducer 10 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col9, _col10 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col5, _col6, _col7, _col9, _col10 - input vertices: - 1 Map 15 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col5 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10, _col16 - input vertices: - 1 Map 16 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int) - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10, _col16, _col18 - Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int), _col18 (type: string) - Reducer 12 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col16, _col18, _col20 - Statistics: Num rows: 510191624 Data size: 69090195216 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col20) > (UDFToDouble(_col9) + 5.0D)) (type: boolean) - Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col18 (type: string), _col4 (type: int), _col6 (type: int), _col7 (type: int), _col10 (type: int), _col16 (type: int) - outputColumnNames: _col3, _col8, _col10, _col11, _col14, _col20 - Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col8 (type: int) - sort order: + - Map-reduce partition columns: _col8 (type: int) - Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string), _col10 (type: int), _col11 (type: int), _col14 (type: int), _col20 (type: int) Reducer 2 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -400,37 +353,31 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col8 (type: int) outputColumnNames: _col0, _col3, _col5, _col9, _col14, _col16, _col17, _col20, _col26 - Statistics: Num rows: 187070265 Data size: 25333072028 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1637843460 Data size: 510997755348 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 < _col17) (type: boolean) - Statistics: Num rows: 62356755 Data size: 8444357342 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col20 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col20 (type: int) - Statistics: Num rows: 62356755 Data size: 8444357342 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: string), _col9 (type: string), _col14 (type: int), _col16 (type: int), _col26 (type: int) + Statistics: Num rows: 545947820 Data size: 170332585120 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col20 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col5, _col9, _col14, _col16, _col20, _col26 + input vertices: + 1 Map 16 + Statistics: Num rows: 610435044 Data size: 183130513200 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col14 (type: int), _col16 (type: int), _col5 (type: string), _col9 (type: string), _col20 (type: int), _col26 (type: int) + outputColumnNames: _col4, _col6, _col13, _col15, _col22, _col28 + Statistics: Num rows: 610435044 Data size: 183130513200 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col4 (type: int), _col6 (type: int) + sort order: ++ + Map-reduce partition columns: _col4 (type: int), _col6 (type: int) + Statistics: Num rows: 610435044 Data size: 183130513200 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col13 (type: string), _col15 (type: string), _col22 (type: int), _col28 (type: int) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col20 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col5, _col9, _col14, _col16, _col20, _col26 - Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col14 (type: int), _col16 (type: int), _col5 (type: string), _col9 (type: string), _col20 (type: int), _col26 (type: int) - outputColumnNames: _col4, _col6, _col13, _col15, _col22, _col28 - Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int), _col6 (type: int) - sort order: ++ - Map-reduce partition columns: _col4 (type: int), _col6 (type: int) - Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE - value expressions: _col13 (type: string), _col15 (type: string), _col22 (type: int), _col28 (type: int) - Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -439,24 +386,24 @@ STAGE PLANS: 0 _col4 (type: int), _col6 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col13, _col15, _col22, _col28 - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 963870346 Data size: 281450141032 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col15 (type: string), _col13 (type: string), _col22 (type: int), CASE WHEN (_col28 is null) THEN (1) ELSE (0) END (type: int), CASE WHEN (_col28 is not null) THEN (1) ELSE (0) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 963870346 Data size: 281450141032 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col3), count(_col4), count() keys: _col0 (type: string), _col1 (type: string), _col2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 963870346 Data size: 300727547952 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 963870346 Data size: 300727547952 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -464,46 +411,103 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71169210 Data size: 22204793520 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: -+++ - Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71169210 Data size: 22204793520 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: bigint) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 71169210 Data size: 22204793520 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 31200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 31200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 8 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col9, _col10 + Statistics: Num rows: 40895108 Data size: 4966629896 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col4, _col5, _col6, _col7, _col9, _col10 + input vertices: + 1 Map 12 + Statistics: Num rows: 8179022 Data size: 948189328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col5 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10, _col16 + input vertices: + 1 Map 13 + Statistics: Num rows: 8179022 Data size: 953835612 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col4 (type: int) + sort order: + + Map-reduce partition columns: _col4 (type: int) + Statistics: Num rows: 8179022 Data size: 953835612 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int) Reducer 9 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col4 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9, _col10 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int) + outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10, _col16, _col18 + Statistics: Num rows: 8179022 Data size: 2458775660 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col16, _col18, _col20 + input vertices: + 1 Map 15 + Statistics: Num rows: 8179022 Data size: 3200532772 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(_col20) > (UDFToDouble(_col9) + 5.0D)) (type: boolean) + Statistics: Num rows: 2726340 Data size: 1066844000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col18 (type: string), _col4 (type: int), _col6 (type: int), _col7 (type: int), _col10 (type: int), _col16 (type: int) + outputColumnNames: _col3, _col8, _col10, _col11, _col14, _col20 + Statistics: Num rows: 2726340 Data size: 1066844000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col8 (type: int) + sort order: + + Map-reduce partition columns: _col8 (type: int) + Statistics: Num rows: 2726340 Data size: 1066844000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: string), _col10 (type: int), _col11 (type: int), _col14 (type: int), _col20 (type: int) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query73.q.out b/ql/src/test/results/clientpositive/perf/spark/query73.q.out index ddaca3d4a1..693e15b9b4 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query73.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query73.q.out @@ -53,28 +53,49 @@ select c_last_name order by cnt desc POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 5 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (2000, 2001, 2002) and d_dom BETWEEN 1 AND 2 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year) IN (2000, 2001, 2002) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) (type: boolean) + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan alias: household_demographics filterExpr: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 748800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 480 Data size: 49920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 480 Data size: 49920 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -82,19 +103,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 9 + Map 7 Map Operator Tree: TableScan alias: store filterExpr: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 173808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 8670 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 8670 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -103,173 +124,148 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 567), Reducer 6 (PARTITION-LEVEL SORT, 567) - Reducer 3 <- Reducer 2 (SORT, 1) - Reducer 5 <- Map 4 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 6 <- Reducer 5 (GROUP, 529) + Reducer 4 <- Map 3 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: customer - filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c_customer_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) - Execution mode: vectorized - Map 4 + Map 3 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_hdemo_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 11105263900 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 479121995 Data size: 9237528672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + Statistics: Num rows: 479121995 Data size: 9237528672 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 5 + Statistics: Num rows: 171075172 Data size: 2478531076 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4 + input vertices: + 1 Map 6 + Statistics: Num rows: 11405013 Data size: 45620060 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col4 + input vertices: + 1 Map 7 + Statistics: Num rows: 4591740 Data size: 18366964 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col1 (type: int), _col4 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4591740 Data size: 55100884 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 4591740 Data size: 55100884 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + Reducer 4 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4591740 Data size: 55100884 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4591740 Data size: 55100884 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 BETWEEN 1 AND 5 (type: boolean) + Statistics: Num rows: 510193 Data size: 6122320 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year) IN (2000, 2001, 2002) and d_dom BETWEEN 1 AND 2 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: customer + filterExpr: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 28480000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_year) IN (2000, 2001, 2002) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + predicate: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 28480000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + expressions: c_customer_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 80000000 Data size: 28480000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7 + input vertices: + 1 Reducer 4 + Statistics: Num rows: 510193 Data size: 185710252 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: string), _col2 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: int), _col7 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 510193 Data size: 185710252 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col5 (type: bigint) + sort order: - + Statistics: Num rows: 510193 Data size: 185710252 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: string), _col2 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: int), _col7 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col5 (type: bigint) - sort order: - - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int) - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: int), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 510193 Data size: 185710252 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 510193 Data size: 185710252 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 5 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col4 - input vertices: - 1 Map 9 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col1 (type: int), _col4 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) - Reducer 6 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 BETWEEN 1 AND 5 (type: boolean) - Statistics: Num rows: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: bigint) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query74.q.out b/ql/src/test/results/clientpositive/perf/spark/query74.q.out index e73a19f791..dbb32fcba3 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query74.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query74.q.out @@ -119,308 +119,338 @@ with year_total as ( limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-1 depends on stages: Stage-5 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) - Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 975), Reducer 10 (PARTITION-LEVEL SORT, 975) - Reducer 12 <- Reducer 11 (GROUP, 481) - Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 154), Map 19 (PARTITION-LEVEL SORT, 154) - Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 706), Reducer 16 (PARTITION-LEVEL SORT, 706) - Reducer 18 <- Reducer 17 (GROUP, 186) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 7 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 398), Map 25 (PARTITION-LEVEL SORT, 398) - Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 975), Reducer 22 (PARTITION-LEVEL SORT, 975) - Reducer 24 <- Reducer 23 (GROUP, 481) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 706), Reducer 2 (PARTITION-LEVEL SORT, 706) - Reducer 4 <- Reducer 3 (GROUP, 186) - Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 444), Reducer 18 (PARTITION-LEVEL SORT, 444), Reducer 24 (PARTITION-LEVEL SORT, 444), Reducer 4 (PARTITION-LEVEL SORT, 444) - Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 6 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year) IN (2001, 2002) and (d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_net_paid (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + expressions: d_date_sk (type: int), 2002 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year) IN (2001, 2002) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), 2001 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (2001, 2002) and (d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), 2001 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 21 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (2001, 2002) and (d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), 2002 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Reducer 9 (GROUP, 581) + Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 226), Map 17 (PARTITION-LEVEL SORT, 226) + Reducer 15 <- Reducer 14 (GROUP, 159) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 332), Map 22 (PARTITION-LEVEL SORT, 332) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 226), Map 7 (PARTITION-LEVEL SORT, 226) + Reducer 20 <- Reducer 19 (GROUP, 581) + Reducer 3 <- Reducer 2 (GROUP, 159) + Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 792), Reducer 15 (PARTITION-LEVEL SORT, 792), Reducer 20 (PARTITION-LEVEL SORT, 792), Reducer 3 (PARTITION-LEVEL SORT, 792) + Reducer 5 <- Reducer 4 (SORT, 1) + Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 332), Map 8 (PARTITION-LEVEL SORT, 332) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17276024392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 143930993 Data size: 17267425552 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_net_paid (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 143930993 Data size: 17267425552 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4 + input vertices: + 1 Map 6 + Statistics: Num rows: 51391963 Data size: 6162885092 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 51391963 Data size: 6162885092 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 12 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized - Map 15 + Map 13 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 17276024392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 17267425552 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + Statistics: Num rows: 143930993 Data size: 17267425552 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4 + input vertices: + 1 Map 16 + Statistics: Num rows: 51391963 Data size: 6162885092 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 51391963 Data size: 6162885092 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) Execution mode: vectorized - Map 19 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year) IN (2001, 2002) and (d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), 2001 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Execution mode: vectorized - Map 20 + Local Work: + Map Reduce Local Work + Map 17 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized - Map 21 + Map 18 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66009192560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 60202603340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 25 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year) IN (2001, 2002) and (d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), 2002 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Statistics: Num rows: 525327388 Data size: 60202603340 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4 + input vertices: + 1 Map 21 + Statistics: Num rows: 187573258 Data size: 19766664028 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 187573258 Data size: 19766664028 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) Execution mode: vectorized - Map 26 + Local Work: + Map Reduce Local Work + Map 22 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year) IN (2001, 2002) and (d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), 2002 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Execution mode: vectorized - Map 8 Map Operator Tree: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_customer_id is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_customer_id is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_customer_id (type: string), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 22720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Execution mode: vectorized - Map 9 + Map 8 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66009192560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 60202603340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + Statistics: Num rows: 525327388 Data size: 60202603340 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4 + input vertices: + 1 Map 11 + Statistics: Num rows: 187573258 Data size: 19766664028 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 187573258 Data size: 19766664028 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col6, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col2) - keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - sort order: ++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)) - Reducer 12 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -428,41 +458,25 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 74279010168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col4 (type: decimal(7,2)) outputColumnNames: _col0, _col4 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 39765530696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col4 > 0) (type: boolean) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col4 (type: decimal(7,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62524419 Data size: 13255176828 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(7,2)) - Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) - Reducer 17 + Reducer 14 Reduce Operator Tree: Join Operator condition map: @@ -471,20 +485,20 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col4, _col6, _col7, _col8 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20347210324 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col2) keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20351217348 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20351217348 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(7,2)) - Reducer 18 + Reducer 15 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -492,57 +506,47 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20351217348 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col4 (type: decimal(7,2)) outputColumnNames: _col0, _col4 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col4 > 0) (type: boolean) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col4 (type: decimal(7,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 17130654 Data size: 3631698648 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(7,2)) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) - Reducer 22 + Reducer 19 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) - Reducer 23 + outputColumnNames: _col2, _col4, _col6, _col7, _col8 + Statistics: Num rows: 187573258 Data size: 71631425816 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(_col2) + keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 187573258 Data size: 74279010168 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) + sort order: ++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) + Statistics: Num rows: 187573258 Data size: 74279010168 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: decimal(7,2)) + Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -551,20 +555,20 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col4, _col6, _col7, _col8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20347210324 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col2) keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20351217348 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20351217348 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(7,2)) - Reducer 24 + Reducer 20 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -572,40 +576,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 74279010168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 73528717136 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 73528717136 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col6, _col7, _col8 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col2) - keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - sort order: ++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -613,18 +595,18 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 20351217348 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col4 (type: decimal(7,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51391963 Data size: 10895096156 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(7,2)) - Reducer 5 + Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -637,36 +619,58 @@ STAGE PLANS: 2 _col0 (type: string) 3 _col0 (type: string) outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1149975359 Data size: 101451160012 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 187573258 Data size: 136553331824 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col9 / _col3))) ELSE ((null > (_col9 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END (type: boolean) - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 68276665912 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 26260256120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 26260256120 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 93786629 Data size: 26260256120 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4, _col6, _col7, _col8 + Statistics: Num rows: 187573258 Data size: 71631425816 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(_col2) + keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col4 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 187573258 Data size: 74279010168 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) + sort order: ++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int) + Statistics: Num rows: 187573258 Data size: 74279010168 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: decimal(7,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query75.q.out b/ql/src/test/results/clientpositive/perf/spark/query75.q.out index 54c3c695aa..471cbc4448 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query75.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query75.q.out @@ -137,752 +137,878 @@ WITH all_sales AS ( limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-6 + Stage-1 depends on stages: Stage-7 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 398), Map 16 (PARTITION-LEVEL SORT, 398) - Reducer 14 <- Map 10 (PARTITION-LEVEL SORT, 440), Reducer 13 (PARTITION-LEVEL SORT, 440) - Reducer 15 <- Map 18 (PARTITION-LEVEL SORT, 516), Reducer 14 (PARTITION-LEVEL SORT, 516) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 16 (PARTITION-LEVEL SORT, 306) - Reducer 20 <- Map 16 (PARTITION-LEVEL SORT, 154), Map 19 (PARTITION-LEVEL SORT, 154) - Reducer 21 <- Map 10 (PARTITION-LEVEL SORT, 171), Reducer 20 (PARTITION-LEVEL SORT, 171) - Reducer 22 <- Map 25 (PARTITION-LEVEL SORT, 196), Reducer 21 (PARTITION-LEVEL SORT, 196) - Reducer 27 <- Map 26 (PARTITION-LEVEL SORT, 306), Map 32 (PARTITION-LEVEL SORT, 306) - Reducer 28 <- Map 33 (PARTITION-LEVEL SORT, 338), Reducer 27 (PARTITION-LEVEL SORT, 338) - Reducer 29 <- Map 34 (PARTITION-LEVEL SORT, 393), Reducer 28 (PARTITION-LEVEL SORT, 393) - Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 338), Reducer 2 (PARTITION-LEVEL SORT, 338) - Reducer 30 <- Reducer 29 (GROUP, 934), Reducer 38 (GROUP, 934) - Reducer 31 <- Reducer 30 (GROUP PARTITION-LEVEL SORT, 671), Reducer 45 (GROUP PARTITION-LEVEL SORT, 671) - Reducer 36 <- Map 32 (PARTITION-LEVEL SORT, 398), Map 35 (PARTITION-LEVEL SORT, 398) - Reducer 37 <- Map 33 (PARTITION-LEVEL SORT, 440), Reducer 36 (PARTITION-LEVEL SORT, 440) - Reducer 38 <- Map 41 (PARTITION-LEVEL SORT, 516), Reducer 37 (PARTITION-LEVEL SORT, 516) - Reducer 4 <- Map 11 (PARTITION-LEVEL SORT, 393), Reducer 3 (PARTITION-LEVEL SORT, 393) - Reducer 43 <- Map 32 (PARTITION-LEVEL SORT, 154), Map 42 (PARTITION-LEVEL SORT, 154) - Reducer 44 <- Map 33 (PARTITION-LEVEL SORT, 171), Reducer 43 (PARTITION-LEVEL SORT, 171) - Reducer 45 <- Map 48 (PARTITION-LEVEL SORT, 196), Reducer 44 (PARTITION-LEVEL SORT, 196) - Reducer 5 <- Reducer 15 (GROUP, 934), Reducer 4 (GROUP, 934) - Reducer 6 <- Reducer 22 (GROUP PARTITION-LEVEL SORT, 671), Reducer 5 (GROUP PARTITION-LEVEL SORT, 671) - Reducer 7 <- Reducer 31 (PARTITION-LEVEL SORT, 336), Reducer 6 (PARTITION-LEVEL SORT, 336) - Reducer 8 <- Reducer 7 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 7 Map Operator Tree: TableScan - alias: catalog_sales - filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_order_number (type: int), cs_quantity (type: int), cs_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + Map 8 Map Operator Tree: TableScan alias: item filterExpr: ((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 50801820 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_brand_id (type: int), i_class_id (type: int), i_category_id (type: int), i_manufact_id (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: int) + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 11 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 12 Map Operator Tree: TableScan - alias: catalog_returns - filterExpr: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: cr_item_sk (type: int), cr_order_number (type: int), cr_return_quantity (type: int), cr_return_amount (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + Map 13 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: ((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 50801820 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + expressions: i_item_sk (type: int), i_brand_id (type: int), i_class_id (type: int), i_category_id (type: int), i_manufact_id (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 16 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 17 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 18 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 50801820 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_brand_id (type: int), i_class_id (type: int), i_category_id (type: int), i_manufact_id (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 24 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 25 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 50801820 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_brand_id (type: int), i_class_id (type: int), i_category_id (type: int), i_manufact_id (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 29 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 30 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 50801820 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_brand_id (type: int), i_class_id (type: int), i_category_id (type: int), i_manufact_id (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 34 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 35 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 50801820 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_brand_id (type: int), i_class_id (type: int), i_category_id (type: int), i_manufact_id (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 45745 Data size: 5030162 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 237), Map 14 (PARTITION-LEVEL SORT, 237) + Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 67), Map 19 (PARTITION-LEVEL SORT, 67) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 132), Map 9 (PARTITION-LEVEL SORT, 132) + Reducer 21 <- Map 20 (PARTITION-LEVEL SORT, 132), Map 26 (PARTITION-LEVEL SORT, 132) + Reducer 22 <- Reducer 21 (GROUP, 476), Reducer 28 (GROUP, 476) + Reducer 23 <- Reducer 22 (GROUP PARTITION-LEVEL SORT, 567), Reducer 33 (GROUP PARTITION-LEVEL SORT, 567) + Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 237), Map 31 (PARTITION-LEVEL SORT, 237) + Reducer 3 <- Reducer 11 (GROUP, 476), Reducer 2 (GROUP, 476) + Reducer 33 <- Map 32 (PARTITION-LEVEL SORT, 67), Map 36 (PARTITION-LEVEL SORT, 67) + Reducer 4 <- Reducer 16 (GROUP PARTITION-LEVEL SORT, 567), Reducer 3 (GROUP PARTITION-LEVEL SORT, 567) + Reducer 5 <- Reducer 23 (PARTITION-LEVEL SORT, 19), Reducer 4 (PARTITION-LEVEL SORT, 19) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: catalog_sales + filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 36689979416 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 286549727 Data size: 36506509124 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_order_number (type: int), cs_quantity (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 286549727 Data size: 36506509124 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 7 + Statistics: Num rows: 101592102 Data size: 12431296344 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 + input vertices: + 1 Map 8 + Statistics: Num rows: 96821196 Data size: 13388841348 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 96821196 Data size: 13388841348 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 10 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 70617170680 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 550076554 Data size: 67439486572 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 550076554 Data size: 67439486572 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 12 + Statistics: Num rows: 196410188 Data size: 21483561988 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 + input vertices: + 1 Map 13 + Statistics: Num rows: 187186493 Data size: 23334805908 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 187186493 Data size: 23334805908 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 14 Map Operator Tree: TableScan alias: store_returns filterExpr: sr_item_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: sr_item_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_item_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int), sr_return_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 19 + Map 15 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 18428028352 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 18423446520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Statistics: Num rows: 143966864 Data size: 18423446520 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 17 + Statistics: Num rows: 51404771 Data size: 6370022708 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 + input vertices: + 1 Map 18 + Statistics: Num rows: 48990732 Data size: 6854531796 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 48990732 Data size: 6854531796 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) Execution mode: vectorized - Map 25 + Local Work: + Map Reduce Local Work + Map 19 Map Operator Tree: TableScan alias: web_returns filterExpr: wr_item_sk is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wr_item_sk is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_item_sk (type: int), wr_order_number (type: int), wr_return_quantity (type: int), wr_return_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 26 + Map 20 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 36689979416 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 36506509124 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_order_number (type: int), cs_quantity (type: int), cs_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Execution mode: vectorized - Map 32 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 36506509124 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 24 + Statistics: Num rows: 101592102 Data size: 12431296344 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 + input vertices: + 1 Map 25 + Statistics: Num rows: 96821196 Data size: 13388841348 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 96821196 Data size: 13388841348 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) Execution mode: vectorized - Map 33 - Map Operator Tree: - TableScan - alias: item - filterExpr: ((i_category = 'Sports') and i_item_sk is not null and i_brand_id is not null and i_class_id is not null and i_category_id is not null and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_brand_id (type: int), i_class_id (type: int), i_category_id (type: int), i_manufact_id (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: int) - Execution mode: vectorized - Map 34 + Local Work: + Map Reduce Local Work + Map 26 Map Operator Tree: TableScan alias: catalog_returns filterExpr: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_item_sk (type: int), cr_order_number (type: int), cr_return_quantity (type: int), cr_return_amount (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 35 + Map 27 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70617170680 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550076554 Data size: 67439486572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Statistics: Num rows: 550076554 Data size: 67439486572 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 29 + Statistics: Num rows: 196410188 Data size: 21483561988 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 + input vertices: + 1 Map 30 + Statistics: Num rows: 187186493 Data size: 23334805908 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 187186493 Data size: 23334805908 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) Execution mode: vectorized - Map 41 + Local Work: + Map Reduce Local Work + Map 31 Map Operator Tree: TableScan alias: store_returns filterExpr: sr_item_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: sr_item_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_item_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int), sr_return_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 6907548224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 42 + Map 32 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 18428028352 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 18423446520 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Statistics: Num rows: 143966864 Data size: 18423446520 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + input vertices: + 1 Map 34 + Statistics: Num rows: 51404771 Data size: 6370022708 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 + input vertices: + 1 Map 35 + Statistics: Num rows: 48990732 Data size: 6854531796 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 48990732 Data size: 6854531796 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) Execution mode: vectorized - Map 48 + Local Work: + Map Reduce Local Work + Map 36 Map Operator Tree: TableScan alias: web_returns filterExpr: wr_item_sk is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wr_item_sk is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_item_sk (type: int), wr_order_number (type: int), wr_return_quantity (type: int), wr_return_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 1710225720 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Reducer 13 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 14 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) - Reducer 15 + Map 9 + Map Operator Tree: + TableScan + alias: catalog_returns + filterExpr: cr_item_sk is not null (type: boolean) + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cr_item_sk is not null (type: boolean) + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cr_item_sk (type: int), cr_order_number (type: int), cr_return_quantity (type: int), cr_return_amount (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 28798881 Data size: 3504192752 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + Execution mode: vectorized + Reducer 11 Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 outputColumnNames: _col3, _col4, _col8, _col9, _col10, _col12, _col15, _col16 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 308615818 Data size: 73431665376 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int), (_col3 - COALESCE(_col15,0)) (type: int), (_col4 - COALESCE(_col16,0)) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 308615818 Data size: 40737286188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 20 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 21 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) - Reducer 22 + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 16 Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 outputColumnNames: _col3, _col4, _col8, _col9, _col10, _col12, _col15, _col16 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 88085997 Data size: 21765972384 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int), (_col3 - COALESCE(_col15,0)) (type: int), (_col4 - COALESCE(_col16,0)) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 88085997 Data size: 11627349816 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE - Reducer 27 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 28 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) - Reducer 29 + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 2 Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 outputColumnNames: _col3, _col4, _col8, _col9, _col10, _col12, _col15, _col16 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 152879623 Data size: 37681151920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int), (_col3 - COALESCE(_col15,0)) (type: int), (_col4 - COALESCE(_col16,0)) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 152879623 Data size: 20180108448 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE - Reducer 3 + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 21 Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) - Reducer 30 + Left Outer Join 0 to 1 + outputColumnNames: _col3, _col4, _col8, _col9, _col10, _col12, _col15, _col16 + Statistics: Num rows: 152879623 Data size: 37681151920 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int), (_col3 - COALESCE(_col15,0)) (type: int), (_col4 - COALESCE(_col16,0)) (type: decimal(8,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 152879623 Data size: 20180108448 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 22 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: decimal(8,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 574982367 Data size: 59771294782 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE - Reducer 31 + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 23 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: decimal(8,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383324964 Data size: 42916270092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col5) keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191662482 Data size: 21458135046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8520960 Data size: 1158850384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 191662482 Data size: 21458135046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8520960 Data size: 1158850384 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: bigint), _col5 (type: decimal(18,2)) - Reducer 36 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 37 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) - Reducer 38 + Reducer 28 Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 outputColumnNames: _col3, _col4, _col8, _col9, _col10, _col12, _col15, _col16 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 308615818 Data size: 73431665376 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int), (_col3 - COALESCE(_col15,0)) (type: int), (_col4 - COALESCE(_col16,0)) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 308615818 Data size: 40737286188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE - Reducer 4 + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - outputColumnNames: _col3, _col4, _col8, _col9, _col10, _col12, _col15, _col16 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int), (_col3 - COALESCE(_col15,0)) (type: int), (_col4 - COALESCE(_col16,0)) (type: decimal(8,2)) + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: decimal(8,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 461495441 Data size: 60917392816 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - sort order: ++++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - Statistics: Num rows: 1149964734 Data size: 119542589565 Basic stats: COMPLETE Column stats: NONE - Reducer 43 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) - Reducer 44 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col12 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int) - Reducer 45 + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 33 Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 outputColumnNames: _col3, _col4, _col8, _col9, _col10, _col12, _col15, _col16 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 88085997 Data size: 21765972384 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: int), (_col3 - COALESCE(_col15,0)) (type: int), (_col4 - COALESCE(_col16,0)) (type: decimal(8,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 88085997 Data size: 11627349816 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) sort order: ++++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE - Reducer 5 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: decimal(8,2)) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 574982367 Data size: 59771294782 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(8,2)) - sort order: ++++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 766649929 Data size: 85832540296 Basic stats: COMPLETE Column stats: NONE - Reducer 6 + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: decimal(8,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383324964 Data size: 42916270092 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 549581438 Data size: 72544737204 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col5) keys: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 191662482 Data size: 21458135046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8520960 Data size: 1158850384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 191662482 Data size: 21458135046 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8520960 Data size: 1158850384 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: bigint), _col5 (type: decimal(18,2)) - Reducer 7 + Reducer 5 Reduce Operator Tree: Join Operator condition map: @@ -891,37 +1017,37 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col10, _col11 - Statistics: Num rows: 210828734 Data size: 23603949062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 114702621361 Data size: 29363871068240 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((CAST( _col10 AS decimal(17,2)) / CAST( _col4 AS decimal(17,2))) < 0.9) (type: boolean) - Statistics: Num rows: 70276244 Data size: 7867982946 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38234207120 Data size: 9787957022672 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: bigint), _col10 (type: bigint), (_col10 - _col4) (type: bigint), (_col11 - _col5) (type: decimal(19,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 70276244 Data size: 7867982946 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38234207120 Data size: 5811599482192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col6 (type: bigint) sort order: + - Statistics: Num rows: 70276244 Data size: 7867982946 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38234207120 Data size: 5811599482192 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: bigint), _col5 (type: bigint), _col7 (type: decimal(19,2)) - Reducer 8 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: bigint), VALUE._col5 (type: bigint), KEY.reducesinkkey0 (type: bigint), VALUE._col6 (type: decimal(19,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 70276244 Data size: 7867982946 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38234207120 Data size: 5811599482192 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 11100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 15200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 2001 (type: int), 2002 (type: int), _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: decimal(19,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 100 Data size: 11100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 11100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query76.q.out b/ql/src/test/results/clientpositive/perf/spark/query76.q.out index 05ec505099..abfb2c5753 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query76.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query76.q.out @@ -45,308 +45,323 @@ ORDER BY channel, col_name, d_year, d_qoy, i_category limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 85), Reducer 9 (PARTITION-LEVEL SORT, 85) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 158), Map 16 (PARTITION-LEVEL SORT, 158) - Reducer 15 <- Map 17 (PARTITION-LEVEL SORT, 169), Reducer 14 (PARTITION-LEVEL SORT, 169) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 204), Map 6 (PARTITION-LEVEL SORT, 204) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 219), Reducer 2 (PARTITION-LEVEL SORT, 219) - Reducer 4 <- Reducer 10 (GROUP, 518), Reducer 15 (GROUP, 518), Reducer 3 (GROUP, 518) - Reducer 5 <- Reducer 4 (SORT, 1) - Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 82), Map 8 (PARTITION-LEVEL SORT, 82) #### A masked pattern was here #### Vertices: - Map 1 + Map 6 Map Operator Tree: TableScan - alias: item - filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int), i_category (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 11 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 Map Operator Tree: TableScan - alias: item - filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + filterExpr: (ws_web_page_sk is null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 17852018948 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_item_sk is not null and ws_sold_date_sk is not null and ws_web_page_sk is null) (type: boolean) + Statistics: Num rows: 35728 Data size: 4429312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int), i_category (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 35728 Data size: 4286436 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + Map 9 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 13 Map Operator Tree: TableScan alias: date_dim filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 2), Map 12 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 23), Map 5 (PARTITION-LEVEL SORT, 23) + Reducer 3 <- Map 8 (GROUP, 2), Reducer 11 (GROUP, 2), Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: item + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_category (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: vectorized - Map 13 + Map 10 Map Operator Tree: TableScan alias: catalog_sales filterExpr: (cs_warehouse_sk is null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 35538013728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is null) (type: boolean) - Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1433911 Data size: 176945112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1433911 Data size: 171238168 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1433911 Data size: 171238168 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 16 + Map 12 Map Operator Tree: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_category (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 17 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) - Execution mode: vectorized - Map 6 + Map 5 Map Operator Tree: TableScan alias: store_sales filterExpr: (ss_addr_sk is null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313188164 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_addr_sk is null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24749363 Data size: 2935279164 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24749363 Data size: 2840735864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24749363 Data size: 2840735864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_year (type: int), d_qoy (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int) - Execution mode: vectorized Map 8 Map Operator Tree: TableScan - alias: web_sales - filterExpr: (ws_web_page_sk is null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ws_item_sk is not null and ws_sold_date_sk is not null and ws_web_page_sk is null) (type: boolean) - Statistics: Num rows: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col3 (type: decimal(7,2)) + expressions: i_item_sk (type: int), i_category (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 43428000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col3, _col5 + input vertices: + 0 Map 7 + Statistics: Num rows: 35728 Data size: 7359040 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col5, _col7, _col8 + input vertices: + 1 Map 9 + Statistics: Num rows: 35728 Data size: 7501984 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'web' (type: string), 'ws_web_page_sk' (type: string), _col7 (type: int), _col8 (type: int), _col5 (type: string), _col3 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 35728 Data size: 14111664 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), sum(_col5) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 224000 Data size: 91392000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + sort order: +++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + Statistics: Num rows: 224000 Data size: 91392000 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2)) Execution mode: vectorized - Reducer 10 + Local Work: + Map Reduce Local Work + Reducer 11 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - outputColumnNames: _col3, _col5, _col7, _col8 - Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 'web' (type: string), 'ws_web_page_sk' (type: string), _col7 (type: int), _col8 (type: int), _col5 (type: string), _col3 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col5) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 609832848 Data size: 66183559909 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - sort order: +++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - Statistics: Num rows: 609832848 Data size: 66183559909 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2)) - Reducer 14 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) outputColumnNames: _col0, _col3, _col5 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col5 (type: string) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col3, _col5, _col7, _col8 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 'catalog' (type: string), 'cs_warehouse_sk' (type: string), _col7 (type: int), _col8 (type: int), _col5 (type: string), _col3 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col5) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 609832848 Data size: 66183559909 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - sort order: +++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - Statistics: Num rows: 609832848 Data size: 66183559909 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2)) + Statistics: Num rows: 1433911 Data size: 294554510 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col5, _col7, _col8 + input vertices: + 1 Map 13 + Statistics: Num rows: 1433911 Data size: 300318830 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'catalog' (type: string), 'cs_warehouse_sk' (type: string), _col7 (type: int), _col8 (type: int), _col5 (type: string), _col3 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1433911 Data size: 572761920 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), sum(_col5) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 224000 Data size: 91392000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + sort order: +++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + Statistics: Num rows: 224000 Data size: 91392000 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2)) Reducer 2 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col1 (type: int) outputColumnNames: _col1, _col2, _col5 - Statistics: Num rows: 316797605 Data size: 27947976704 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 316797605 Data size: 27947976704 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col5 (type: decimal(7,2)) + Statistics: Num rows: 24749363 Data size: 4969181078 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col5, _col7, _col8 + input vertices: + 1 Map 6 + Statistics: Num rows: 24749363 Data size: 5072633286 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'store' (type: string), 'ss_addr_sk' (type: string), _col7 (type: int), _col8 (type: int), _col1 (type: string), _col5 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 24749363 Data size: 9601766715 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), sum(_col5) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 224000 Data size: 91392000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + sort order: +++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) + Statistics: Num rows: 224000 Data size: 91392000 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2)) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - outputColumnNames: _col1, _col5, _col7, _col8 - Statistics: Num rows: 348477373 Data size: 30742775040 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 'store' (type: string), 'ss_addr_sk' (type: string), _col7 (type: int), _col8 (type: int), _col1 (type: string), _col5 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348477373 Data size: 30742775040 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col5) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 609832848 Data size: 66183559909 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - sort order: +++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) - Statistics: Num rows: 609832848 Data size: 66183559909 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2)) - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -354,46 +369,30 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 304916424 Data size: 33091779954 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5600 Data size: 2284800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: string) sort order: +++++ - Statistics: Num rows: 304916424 Data size: 33091779954 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5600 Data size: 2284800 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col5 (type: bigint), _col6 (type: decimal(17,2)) - Reducer 5 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 304916424 Data size: 33091779954 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5600 Data size: 2284800 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 40800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 40800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3, _col5 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col5 (type: string) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query77.q.out b/ql/src/test/results/clientpositive/perf/spark/query77.q.out index ea80550259..7bd4bb2002 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query77.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query77.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[182][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[208][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain with ss as (select s_store_sk, @@ -212,34 +212,36 @@ with ss as limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-3 - Stage-4 depends on stages: Stage-5 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 Stage-6 depends on stages: Stage-4 - Stage-7 depends on stages: Stage-6 - Stage-8 depends on stages: Stage-7 - Stage-1 depends on stages: Stage-8 + Stage-5 depends on stages: Stage-6 + Stage-7 depends on stages: Stage-5 + Stage-9 depends on stages: Stage-7 + Stage-8 depends on stages: Stage-9 + Stage-10 depends on stages: Stage-8 + Stage-1 depends on stages: Stage-10 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 10 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -247,24 +249,134 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work + Map 9 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work - Stage: Stage-3 + Stage: Stage-2 Spark + Edges: + Reducer 8 <- Map 7 (GROUP, 2) #### A masked pattern was here #### Vertices: - Map 13 + Map 7 + Map Operator Tree: + TableScan + alias: store_returns + filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 12893729500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) + Statistics: Num rows: 53634860 Data size: 12007980080 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sr_returned_date_sk (type: int), sr_store_sk (type: int), sr_return_amt (type: decimal(7,2)), sr_net_loss (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 53634860 Data size: 12007980080 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 5959021 Data size: 930848744 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 1 Map 10 + Statistics: Num rows: 5959021 Data size: 938349572 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3) + keys: _col6 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 40 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 40 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 8 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 2280 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 6816 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -273,23 +385,23 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-5 + Stage: Stage-6 Spark #### A masked pattern was here #### Vertices: - Map 19 + Map 16 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -298,25 +410,25 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-4 + Stage: Stage-5 Spark Edges: - Reducer 18 <- Map 17 (GROUP, 1) + Reducer 15 <- Map 14 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 17 + Map 14 Map Operator Tree: TableScan alias: catalog_returns filterExpr: cr_returned_date_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6437036420 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cr_returned_date_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6437036420 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_returned_date_sk (type: int), cr_return_amount (type: decimal(7,2)), cr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6437036420 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -325,21 +437,21 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2 input vertices: - 1 Map 19 - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE + 1 Map 16 + Statistics: Num rows: 3199657 Data size: 587614720 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: decimal(17,2)) Execution mode: vectorized Local Work: Map Reduce Local Work - Reducer 18 + Reducer 15 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -348,29 +460,29 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 1 - Stage: Stage-6 + Stage: Stage-7 Spark #### A masked pattern was here #### Vertices: - Map 16 + Map 13 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -379,23 +491,43 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-7 + Stage: Stage-9 Spark #### A masked pattern was here #### Vertices: - Map 25 + Map 23 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 24 Map Operator Tree: TableScan alias: web_page filterExpr: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wp_web_page_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -406,21 +538,111 @@ STAGE PLANS: Stage: Stage-8 Spark + Edges: + Reducer 22 <- Map 21 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 21 + Map Operator Tree: + TableScan + alias: web_returns + filterExpr: (wr_returned_date_sk is not null and wr_web_page_sk is not null) (type: boolean) + Statistics: Num rows: 14398467 Data size: 3189965948 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (wr_returned_date_sk is not null and wr_web_page_sk is not null) (type: boolean) + Statistics: Num rows: 13129719 Data size: 2908876076 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: wr_returned_date_sk (type: int), wr_web_page_sk (type: int), wr_return_amt (type: decimal(7,2)), wr_net_loss (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 13129719 Data size: 2908876076 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 23 + Statistics: Num rows: 1458758 Data size: 197744064 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 1 Map 24 + Statistics: Num rows: 1458758 Data size: 200112584 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3) + keys: _col6 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 21 Data size: 4788 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 21 Data size: 4788 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 22 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 21 Data size: 4788 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + + Stage: Stage-10 + Spark #### A masked pattern was here #### Vertices: - Map 30 + Map 19 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 20 Map Operator Tree: TableScan alias: web_page filterExpr: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wp_web_page_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -432,19 +654,11 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 35), Map 9 (PARTITION-LEVEL SORT, 35) - Reducer 11 <- Reducer 10 (GROUP, 43) - Reducer 15 <- Map 14 (GROUP, 336) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 21 <- Map 12 (PARTITION-LEVEL SORT, 154), Map 20 (PARTITION-LEVEL SORT, 154) - Reducer 22 <- Reducer 21 (GROUP, 186) - Reducer 23 <- Reducer 22 (PARTITION-LEVEL SORT, 99), Reducer 28 (PARTITION-LEVEL SORT, 99) - Reducer 27 <- Map 26 (PARTITION-LEVEL SORT, 11), Map 29 (PARTITION-LEVEL SORT, 11) - Reducer 28 <- Reducer 27 (GROUP, 13) - Reducer 3 <- Reducer 2 (GROUP, 481) - Reducer 4 <- Reducer 11 (PARTITION-LEVEL SORT, 262), Reducer 3 (PARTITION-LEVEL SORT, 262) - Reducer 5 <- Reducer 15 (GROUP, 1009), Reducer 23 (GROUP, 1009), Reducer 4 (GROUP, 1009) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 12 <- Map 11 (GROUP, 2) + Reducer 18 <- Map 17 (GROUP, 2) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 12 (GROUP, 2), Reducer 18 (GROUP, 2), Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -452,53 +666,62 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 127618581836 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 116392994012 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 12 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 116392994012 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 5 + Statistics: Num rows: 58365993 Data size: 7918461052 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 1 Map 6 + Statistics: Num rows: 58365993 Data size: 8012994500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3) + keys: _col6 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 320 Data size: 72960 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 320 Data size: 72960 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + Map 11 Map Operator Tree: TableScan alias: catalog_sales filterExpr: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 66640924712 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 66307683076 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_call_center_sk (type: int), cs_ext_sales_price (type: decimal(7,2)), cs_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 66307683076 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -507,171 +730,72 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3 input vertices: - 1 Map 16 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + 1 Map 13 + Statistics: Num rows: 31836679 Data size: 7092640852 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 12760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 12760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 20 + Map 17 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_sold_date_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 33404307092 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_sold_date_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143931136 Data size: 33387713828 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_web_page_sk (type: int), ws_ext_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 26 - Map Operator Tree: - TableScan - alias: web_returns - filterExpr: (wr_returned_date_sk is not null and wr_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (wr_returned_date_sk is not null and wr_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: wr_returned_date_sk (type: int), wr_web_page_sk (type: int), wr_return_amt (type: decimal(7,2)), wr_net_loss (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 29 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: store_returns - filterExpr: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (sr_returned_date_sk is not null and sr_store_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: sr_returned_date_sk (type: int), sr_store_sk (type: int), sr_return_amt (type: decimal(7,2)), sr_net_loss (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + Statistics: Num rows: 143931136 Data size: 33387713828 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 19 + Statistics: Num rows: 15991254 Data size: 3641839328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6 + input vertices: + 1 Map 20 + Statistics: Num rows: 15991254 Data size: 3641982200 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3) + keys: _col6 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 345 Data size: 78660 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 345 Data size: 78660 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Execution mode: vectorized - Reducer 10 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 - input vertices: - 1 Map 13 - Statistics: Num rows: 69685294 Data size: 5399255980 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3) - keys: _col6 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 69685294 Data size: 5399255980 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 69685294 Data size: 5399255980 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) - Reducer 11 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 34842647 Data size: 2699627990 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 34842647 Data size: 2699627990 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) - Reducer 15 + Reducer 12 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -681,7 +805,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -690,221 +814,102 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4 input vertices: - 1 Reducer 18 - Statistics: Num rows: 158394413 Data size: 57088528313 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 15 + Statistics: Num rows: 2 Data size: 904 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'catalog channel' (type: string), _col0 (type: int), _col1 (type: decimal(17,2)), _col3 (type: decimal(17,2)), (_col2 - _col4) (type: decimal(18,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 158394413 Data size: 57088528313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 878 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: int), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1912659936 Data size: 311808612993 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 23244 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 1912659936 Data size: 311808612993 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 23244 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) - Reducer 2 + Reducer 18 + Execution mode: vectorized Local Work: Map Reduce Local Work Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 23 Data size: 5244 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 + outputColumnNames: _col0, _col1, _col2, _col4, _col5 input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3) - keys: _col6 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) - Reducer 21 + 1 Reducer 22 + Statistics: Num rows: 23 Data size: 10172 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'web channel' (type: string), _col0 (type: int), _col1 (type: decimal(17,2)), COALESCE(_col4,0) (type: decimal(17,2)), (_col2 - COALESCE(_col5,0)) (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 23 Data size: 10005 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4) + keys: _col0 (type: string), _col1 (type: int), 0L (type: bigint) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 52 Data size: 23244 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 52 Data size: 23244 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) + Reducer 2 + Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 - input vertices: - 1 Map 25 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3) - keys: _col6 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) - Reducer 22 - Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) - Reducer 23 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 95833780 Data size: 13030622681 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 'web channel' (type: string), _col0 (type: int), _col1 (type: decimal(17,2)), COALESCE(_col4,0) (type: decimal(17,2)), (_col2 - COALESCE(_col5,0)) (type: decimal(18,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 95833780 Data size: 13030622681 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3), sum(_col4) - keys: _col0 (type: string), _col1 (type: int), 0L (type: bigint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1912659936 Data size: 311808612993 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 1912659936 Data size: 311808612993 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) - Reducer 27 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2280 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6 + outputColumnNames: _col0, _col1, _col2, _col4, _col5 input vertices: - 1 Map 30 - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3) - keys: _col6 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) - Reducer 28 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8711072 Data size: 801742469 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8711072 Data size: 801742469 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) + 1 Reducer 8 + Statistics: Num rows: 10 Data size: 4520 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'store channel' (type: string), _col0 (type: int), _col1 (type: decimal(17,2)), COALESCE(_col4,0) (type: decimal(17,2)), (_col2 - COALESCE(_col5,0)) (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 10 Data size: 4370 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4) + keys: _col0 (type: string), _col1 (type: int), 0L (type: bigint) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 52 Data size: 23244 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) + Statistics: Num rows: 52 Data size: 23244 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) Reducer 3 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) - Reducer 4 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 'store channel' (type: string), _col0 (type: int), _col1 (type: decimal(17,2)), COALESCE(_col4,0) (type: decimal(17,2)), (_col2 - COALESCE(_col5,0)) (type: decimal(18,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3), sum(_col4) - keys: _col0 (type: string), _col1 (type: int), 0L (type: bigint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1912659936 Data size: 311808612993 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: bigint) - Statistics: Num rows: 1912659936 Data size: 311808612993 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) - Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -912,31 +917,31 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 956329968 Data size: 155904306496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 9387 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: int), _col3 (type: decimal(27,2)), _col4 (type: decimal(27,2)), _col5 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 956329968 Data size: 155904306496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 9219 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ - Statistics: Num rows: 956329968 Data size: 155904306496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 9219 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(27,2)), _col3 (type: decimal(27,2)), _col4 (type: decimal(28,2)) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: decimal(27,2)), VALUE._col1 (type: decimal(27,2)), VALUE._col2 (type: decimal(28,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 956329968 Data size: 155904306496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 9219 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 16300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 9219 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 16300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 9219 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query78.q.out b/ql/src/test/results/clientpositive/perf/spark/query78.q.out index 15c7f04b30..44946db3c0 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query78.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query78.q.out @@ -113,192 +113,290 @@ order by limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 85), Reducer 14 (PARTITION-LEVEL SORT, 85) - Reducer 12 <- Reducer 11 (GROUP, 93) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 164), Map 15 (PARTITION-LEVEL SORT, 164) - Reducer 17 <- Map 10 (PARTITION-LEVEL SORT, 85), Reducer 20 (PARTITION-LEVEL SORT, 85) - Reducer 18 <- Reducer 17 (GROUP, 93) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 219), Reducer 8 (PARTITION-LEVEL SORT, 219) - Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 177), Map 21 (PARTITION-LEVEL SORT, 177) - Reducer 3 <- Reducer 2 (GROUP, 241) - Reducer 4 <- Reducer 12 (PARTITION-LEVEL SORT, 167), Reducer 3 (PARTITION-LEVEL SORT, 167) - Reducer 5 <- Reducer 18 (PARTITION-LEVEL SORT, 91), Reducer 4 (PARTITION-LEVEL SORT, 91) - Reducer 6 <- Reducer 5 (SORT, 1) - Reducer 8 <- Map 7 (PARTITION-LEVEL SORT, 432), Map 9 (PARTITION-LEVEL SORT, 432) + Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 1007), Map 8 (PARTITION-LEVEL SORT, 1007) #### A masked pattern was here #### Vertices: - Map 1 + Map 6 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: ss_sold_date_sk is not null (type: boolean) + Statistics: Num rows: 575995635 Data size: 134425788444 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ss_sold_date_sk is not null (type: boolean) + Statistics: Num rows: 550076554 Data size: 128376796624 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_wholesale_cost (type: decimal(7,2)), ss_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 550076554 Data size: 128376796624 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col3 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col3 (type: int) + Statistics: Num rows: 550076554 Data size: 128376796624 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + Execution mode: vectorized + Map 8 + Map Operator Tree: + TableScan + alias: store_returns + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sr_item_sk (type: int), sr_ticket_number (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 57591150 Data size: 460729200 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Reducer 7 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: int), _col3 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col8 + Statistics: Num rows: 563130026 Data size: 131561843792 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col8 is null (type: boolean) + Statistics: Num rows: 1 Data size: 244 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 244 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 14 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 276), Map 13 (PARTITION-LEVEL SORT, 276) + Reducer 12 <- Reducer 11 (GROUP, 2) + Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 274), Map 18 (PARTITION-LEVEL SORT, 274) + Reducer 17 <- Reducer 16 (GROUP, 35) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 17 (PARTITION-LEVEL SORT, 35), Reducer 3 (PARTITION-LEVEL SORT, 35) + Reducer 5 <- Reducer 4 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4, _col6, _col7, _col8 + input vertices: + 1 Reducer 7 + Statistics: Num rows: 1 Data size: 236 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col6), sum(_col7), sum(_col8) + keys: _col4 (type: int), _col3 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 10 Map Operator Tree: TableScan alias: web_sales filterExpr: ws_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 35128163668 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ws_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 35119429616 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_customer_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_wholesale_cost (type: decimal(7,2)), ws_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 35119429616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col3 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 35119429616 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized - Map 15 + Map 13 Map Operator Tree: TableScan alias: web_returns - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 115187736 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_item_sk (type: int), wr_order_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 115187736 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 115187736 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 19 + Map 15 Map Operator Tree: TableScan alias: catalog_sales filterExpr: ((cs_item_sk = cs_item_sk) and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 69929689548 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cs_item_sk = cs_item_sk) and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143274863 Data size: 34790001064 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int), cs_order_number (type: int), cs_quantity (type: int), cs_wholesale_cost (type: decimal(7,2)), cs_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143274863 Data size: 34790001064 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: int), _col3 (type: int) - Statistics: Num rows: 143994918 Data size: 19499804476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143274863 Data size: 34790001064 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized - Map 21 + Map 18 Map Operator Tree: TableScan alias: catalog_returns - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 230391048 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_item_sk (type: int), cr_order_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 230391048 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: ss_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ss_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_wholesale_cost (type: decimal(7,2)), ss_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col3 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col3 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) - Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: store_returns - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: sr_item_sk (type: int), sr_ticket_number (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 230391048 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 11 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col4, _col6, _col7, _col8 - Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col6), sum(_col7), sum(_col8) - keys: _col4 (type: int), _col3 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + 0 _col1 (type: int), _col3 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col8 + Statistics: Num rows: 143966864 Data size: 35108127504 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col8 is null (type: boolean) + Statistics: Num rows: 2825529 Data size: 689041008 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 + Statistics: Num rows: 2825529 Data size: 689041008 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4, _col6, _col7, _col8 + input vertices: + 0 Map 9 + Statistics: Num rows: 1008883 Data size: 237932944 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col6), sum(_col7), sum(_col8) + keys: _col4 (type: int), _col3 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1008883 Data size: 242129108 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1008883 Data size: 242129108 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) Reducer 12 Execution mode: vectorized Reduce Operator Tree: @@ -307,63 +405,59 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 43560808 Data size: 5923010147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1008883 Data size: 242129108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 43560808 Data size: 5923010147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1008883 Data size: 242129108 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col0 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col0 (type: int) - Statistics: Num rows: 43560808 Data size: 5923010147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1008883 Data size: 242129108 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 14 + Reducer 16 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 keys: - 0 _col1 (type: int), _col3 (type: int) + 0 _col2 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col8 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143274863 Data size: 34581241972 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col8 is null (type: boolean) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52189774 Data size: 12596677432 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + Statistics: Num rows: 52189774 Data size: 12596677432 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4, _col6, _col7, _col8 + input vertices: + 0 Map 14 + Statistics: Num rows: 18503137 Data size: 4306200088 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col6), sum(_col7), sum(_col8) + keys: _col3 (type: int), _col4 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 18503137 Data size: 4439709708 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 18503137 Data size: 4439709708 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) Reducer 17 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col4, _col6, _col7, _col8 - Statistics: Num rows: 87116928 Data size: 11797382144 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col6), sum(_col7), sum(_col8) - keys: _col3 (type: int), _col4 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 87116928 Data size: 11797382144 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 87116928 Data size: 11797382144 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 18 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -371,63 +465,18 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 43558464 Data size: 5898691072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18503137 Data size: 4439709708 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 43558464 Data size: 5898691072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18503137 Data size: 4365697160 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 43558464 Data size: 5898691072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18503137 Data size: 4365697160 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)) Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col4, _col6, _col7, _col8 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col6), sum(_col7), sum(_col8) - keys: _col4 (type: int), _col3 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 20 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: int), _col3 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col8 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col8 is null (type: boolean) - Statistics: Num rows: 79197206 Data size: 10724892626 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 - Statistics: Num rows: 79197206 Data size: 10724892626 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79197206 Data size: 10724892626 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -435,18 +484,18 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col0 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col0 (type: int) - Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) - Reducer 4 + Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -455,17 +504,17 @@ STAGE PLANS: 0 _col1 (type: int), _col0 (type: int) 1 _col1 (type: int), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col7, _col8, _col9 - Statistics: Num rows: 191662559 Data size: 16908526668 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (COALESCE(_col7,0) > 0) (type: boolean) - Statistics: Num rows: 63887519 Data size: 5636175497 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 63887519 Data size: 5636175497 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col7 (type: bigint), _col8 (type: decimal(17,2)), _col9 (type: decimal(17,2)) - Reducer 5 + Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -474,59 +523,36 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col7, _col8, _col9, _col11, _col12, _col13 - Statistics: Num rows: 70276272 Data size: 6199793181 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 25344 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (COALESCE(_col11,0) > 0) (type: boolean) - Statistics: Num rows: 23425424 Data size: 2066597727 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (COALESCE(_col7,0) + COALESCE(_col11,0)) (type: bigint), (COALESCE(_col8,0) + COALESCE(_col12,0)) (type: decimal(18,2)), (COALESCE(_col9,0) + COALESCE(_col13,0)) (type: decimal(18,2)), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), round((UDFToDouble(_col2) / UDFToDouble(COALESCE((_col7 + _col11),1))), 2) (type: double) outputColumnNames: _col0, _col1, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 23425424 Data size: 2066597727 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8640 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col9 (type: bigint), _col10 (type: decimal(17,2)), _col11 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(18,2)), _col8 (type: decimal(18,2)), _col12 (type: double) sort order: ++---++++ - Statistics: Num rows: 23425424 Data size: 2066597727 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8640 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: 2000 (type: int), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey2 (type: bigint), KEY.reducesinkkey3 (type: decimal(17,2)), KEY.reducesinkkey4 (type: decimal(17,2)), KEY.reducesinkkey5 (type: bigint), KEY.reducesinkkey6 (type: decimal(18,2)), KEY.reducesinkkey7 (type: decimal(18,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 23425424 Data size: 2066597727 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 5808 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 5808 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 5808 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 8 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col1 (type: int), _col3 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col8 is null (type: boolean) - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query79.q.out b/ql/src/test/results/clientpositive/perf/spark/query79.q.out index a83090f27c..912c58ed54 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query79.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query79.q.out @@ -52,19 +52,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year) IN (1998, 1999, 2000) and (d_dow = 1) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_dow = 1) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 391 Data size: 4692 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 391 Data size: 4692 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store filterExpr: (s_number_employees BETWEEN 200 AND 295 and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 172056 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_number_employees BETWEEN 200 AND 295 and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 189 Data size: 361171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 568 Data size: 57356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_city (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 189 Data size: 361171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 568 Data size: 57356 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col4 (type: int) @@ -72,19 +92,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 9 + Map 8 Map Operator Tree: TableScan alias: household_demographics filterExpr: (((hd_dep_count = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hd_dep_count = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 6000 Data size: 642000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3055 Data size: 36660 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6000 Data size: 642000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3055 Data size: 36660 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -96,10 +116,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 802), Reducer 6 (PARTITION-LEVEL SORT, 802) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 152), Reducer 5 (PARTITION-LEVEL SORT, 152) Reducer 3 <- Reducer 2 (SORT, 1) - Reducer 5 <- Map 4 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 6 <- Reducer 5 (GROUP, 529) + Reducer 5 <- Map 4 (GROUP, 37) #### A masked pattern was here #### Vertices: Map 1 @@ -107,19 +126,19 @@ STAGE PLANS: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 4 @@ -127,40 +146,59 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_hdemo_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 136523505560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 479121995 Data size: 113562343880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_hdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_coupon_amt (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year) IN (1998, 1999, 2000) and (d_dow = 1) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_dow = 1) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 479121995 Data size: 113562343880 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Map 6 + Statistics: Num rows: 102592623 Data size: 19858928684 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7, _col13 + input vertices: + 1 Map 7 + Statistics: Num rows: 34197543 Data size: 6300328799 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col13 + input vertices: + 1 Map 8 + Statistics: Num rows: 14510208 Data size: 1407490408 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col6), sum(_col7) + keys: _col1 (type: int), _col3 (type: int), _col5 (type: int), _col13 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 14510208 Data size: 4657776776 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + sort order: ++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + Statistics: Num rows: 14510208 Data size: 4657776776 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -170,15 +208,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7 - Statistics: Num rows: 421657640 Data size: 37198759428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14510208 Data size: 7269614208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col3 (type: int), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), substr(_col5, 1, 30) (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 - Statistics: Num rows: 421657640 Data size: 37198759428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14510208 Data size: 11259921408 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string), _col5 (type: decimal(17,2)) sort order: ++++ - Statistics: Num rows: 421657640 Data size: 37198759428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14510208 Data size: 11259921408 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: int), _col4 (type: decimal(17,2)) Reducer 3 @@ -187,62 +225,18 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: decimal(17,2)), KEY.reducesinkkey3 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 421657640 Data size: 37198759428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14510208 Data size: 11259921408 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 77600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 77600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col4 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7, _col13 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col13 - input vertices: - 1 Map 9 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col6), sum(_col7) - keys: _col1 (type: int), _col3 (type: int), _col5 (type: int), _col13 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) - sort order: ++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) - Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -250,16 +244,16 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14510208 Data size: 4657776776 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int), _col0 (type: int), _col3 (type: string), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14510208 Data size: 4657776772 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14510208 Data size: 4657776772 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) Stage: Stage-0 diff --git a/ql/src/test/results/clientpositive/perf/spark/query8.q.out b/ql/src/test/results/clientpositive/perf/spark/query8.q.out index 6b14eb9bb0..40cc449b11 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query8.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query8.q.out @@ -222,101 +222,79 @@ STAGE PLANS: Stage: Stage-3 Spark Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 586), Map 9 (PARTITION-LEVEL SORT, 586) - Reducer 11 <- Reducer 10 (GROUP, 349) - Reducer 12 <- Reducer 11 (GROUP, 59) - Reducer 7 <- Map 6 (GROUP, 159) - Reducer 8 <- Reducer 12 (GROUP, 109), Reducer 7 (GROUP, 109) + Reducer 10 <- Reducer 9 (GROUP, 2) + Reducer 11 <- Reducer 10 (GROUP, 2) + Reducer 6 <- Map 5 (GROUP, 2) + Reducer 7 <- Reducer 11 (GROUP, 2), Reducer 6 (GROUP, 2) + Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 48), Map 8 (PARTITION-LEVEL SORT, 48) #### A masked pattern was here #### Vertices: - Map 13 + Map 12 Map Operator Tree: TableScan alias: customer filterExpr: ((c_preferred_cust_flag = 'Y') and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 7120000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((c_preferred_cust_flag = 'Y') and c_current_addr_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 34400807926 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26666667 Data size: 2373333363 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_current_addr_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 40000000 Data size: 34400807926 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26666667 Data size: 2373333363 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 34400807926 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26666667 Data size: 2373333363 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 6 + Map 5 Map Operator Tree: TableScan alias: customer_address filterExpr: ((substr(ca_zip, 1, 5)) IN ('89436', '30868', '65085', '22977', '83927', '77557', '58429', '40697', '80614', '10502', '32779', '91137', '61265', '98294', '17921', '18427', '21203', '59362', '87291', '84093', '21505', '17184', '10866', '67898', '25797', '28055', '18377', '80332', '74535', '21757', '29742', '90885', '29898', '17819', '40811', '25990', '47513', '89531', '91068', '10391', '18846', '99223', '82637', '41368', '83658', '86199', '81625', '26696', '89338', '88425', '32200', '81427', '19053', '77471', '36610', '99823', '43276', '41249', '48584', '83550', '82276', '18842', '78890', '14090', '38123', '40936', '34425', '19850', '43286', '80072', '79188', '54191', '11395', '50497', '84861', '90733', '21068', '57666', '37119', '25004', '57835', '70067', '62878', '95806', '19303', '18840', '19124', '29785', '16737', '16022', '49613', '89977', '68310', '60069', '98360', '48649', '39050', '41793', '25002', '27413', '39736', '47208', '16515', '94808', '57648', '15009', '80015', '42961', '63982', '21744', '71853', '81087', '67468', '34175', '64008', '20261', '11201', '51799', '48043', '45645', '61163', '48375', '36447', '57042', '21218', '41100', '89951', '22745', '35851', '83326', '61125', '78298', '80752', '49858', '52940', '96976', '63792', '11376', '53582', '18717', '90226', '50530', '94203', '99447', '27670', '96577', '57856', '56372', '16165', '23427', '54561', '28806', '44439', '22926', '30123', '61451', '92397', '56979', '92309', '70873', '13355', '21801', '46346', '37562', '56458', '28286', '47306', '99555', '69399', '26234', '47546', '49661', '88601', '35943', '39936', '25632', '24611', '44166', '56648', '30379', '59785', '11110', '14329', '93815', '52226', '71381', '13842', '25612', '63294', '14664', '21077', '82626', '18799', '60915', '81020', '56447', '76619', '11433', '13414', '42548', '92713', '70467', '30884', '47484', '16072', '38936', '13036', '88376', '45539', '35901', '19506', '65690', '73957', '71850', '49231', '14276', '20005', '18384', '76615', '11635', '38177', '55607', '41369', '95447', '58581', '58149', '91946', '33790', '76232', '75692', '95464', '22246', '51061', '56692', '53121', '77209', '15482', '10688', '14868', '45907', '73520', '72666', '25734', '17959', '24677', '66446', '94627', '53535', '15560', '41967', '69297', '11929', '59403', '33283', '52232', '57350', '43933', '40921', '36635', '10827', '71286', '19736', '80619', '25251', '95042', '15526', '36496', '55854', '49124', '81980', '35375', '49157', '63512', '28944', '14946', '36503', '54010', '18767', '23969', '43905', '66979', '33113', '21286', '58471', '59080', '13395', '79144', '70373', '67031', '38360', '26705', '50906', '52406', '26066', '73146', '15884', '31897', '30045', '61068', '45550', '92454', '13376', '14354', '19770', '22928', '97790', '50723', '46081', '30202', '14410', '20223', '88500', '67298', '13261', '14172', '81410', '93578', '83583', '46047', '94167', '82564', '21156', '15799', '86709', '37931', '74703', '83103', '23054', '70470', '72008', '49247', '91911', '69998', '20961', '70070', '63197', '54853', '88191', '91830', '49521', '19454', '81450', '89091', '62378', '25683', '61869', '51744', '36580', '85778', '36871', '48121', '28810', '83712', '45486', '67393', '26935', '42393', '20132', '55349', '86057', '21309', '80218', '10094', '11357', '48819', '39734', '40758', '30432', '21204', '29467', '30214', '61024', '55307', '74621', '11622', '68908', '33032', '52868', '99194', '99900', '84936', '69036', '99149', '45013', '32895', '59004', '32322', '14933', '32936', '33562', '72550', '27385', '58049', '58200', '16808', '21360', '32961', '18586', '79307', '15492') and substr(substr(ca_zip, 1, 5), 1, 2) is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3560000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((substr(ca_zip, 1, 5)) IN ('89436', '30868', '65085', '22977', '83927', '77557', '58429', '40697', '80614', '10502', '32779', '91137', '61265', '98294', '17921', '18427', '21203', '59362', '87291', '84093', '21505', '17184', '10866', '67898', '25797', '28055', '18377', '80332', '74535', '21757', '29742', '90885', '29898', '17819', '40811', '25990', '47513', '89531', '91068', '10391', '18846', '99223', '82637', '41368', '83658', '86199', '81625', '26696', '89338', '88425', '32200', '81427', '19053', '77471', '36610', '99823', '43276', '41249', '48584', '83550', '82276', '18842', '78890', '14090', '38123', '40936', '34425', '19850', '43286', '80072', '79188', '54191', '11395', '50497', '84861', '90733', '21068', '57666', '37119', '25004', '57835', '70067', '62878', '95806', '19303', '18840', '19124', '29785', '16737', '16022', '49613', '89977', '68310', '60069', '98360', '48649', '39050', '41793', '25002', '27413', '39736', '47208', '16515', '94808', '57648', '15009', '80015', '42961', '63982', '21744', '71853', '81087', '67468', '34175', '64008', '20261', '11201', '51799', '48043', '45645', '61163', '48375', '36447', '57042', '21218', '41100', '89951', '22745', '35851', '83326', '61125', '78298', '80752', '49858', '52940', '96976', '63792', '11376', '53582', '18717', '90226', '50530', '94203', '99447', '27670', '96577', '57856', '56372', '16165', '23427', '54561', '28806', '44439', '22926', '30123', '61451', '92397', '56979', '92309', '70873', '13355', '21801', '46346', '37562', '56458', '28286', '47306', '99555', '69399', '26234', '47546', '49661', '88601', '35943', '39936', '25632', '24611', '44166', '56648', '30379', '59785', '11110', '14329', '93815', '52226', '71381', '13842', '25612', '63294', '14664', '21077', '82626', '18799', '60915', '81020', '56447', '76619', '11433', '13414', '42548', '92713', '70467', '30884', '47484', '16072', '38936', '13036', '88376', '45539', '35901', '19506', '65690', '73957', '71850', '49231', '14276', '20005', '18384', '76615', '11635', '38177', '55607', '41369', '95447', '58581', '58149', '91946', '33790', '76232', '75692', '95464', '22246', '51061', '56692', '53121', '77209', '15482', '10688', '14868', '45907', '73520', '72666', '25734', '17959', '24677', '66446', '94627', '53535', '15560', '41967', '69297', '11929', '59403', '33283', '52232', '57350', '43933', '40921', '36635', '10827', '71286', '19736', '80619', '25251', '95042', '15526', '36496', '55854', '49124', '81980', '35375', '49157', '63512', '28944', '14946', '36503', '54010', '18767', '23969', '43905', '66979', '33113', '21286', '58471', '59080', '13395', '79144', '70373', '67031', '38360', '26705', '50906', '52406', '26066', '73146', '15884', '31897', '30045', '61068', '45550', '92454', '13376', '14354', '19770', '22928', '97790', '50723', '46081', '30202', '14410', '20223', '88500', '67298', '13261', '14172', '81410', '93578', '83583', '46047', '94167', '82564', '21156', '15799', '86709', '37931', '74703', '83103', '23054', '70470', '72008', '49247', '91911', '69998', '20961', '70070', '63197', '54853', '88191', '91830', '49521', '19454', '81450', '89091', '62378', '25683', '61869', '51744', '36580', '85778', '36871', '48121', '28810', '83712', '45486', '67393', '26935', '42393', '20132', '55349', '86057', '21309', '80218', '10094', '11357', '48819', '39734', '40758', '30432', '21204', '29467', '30214', '61024', '55307', '74621', '11622', '68908', '33032', '52868', '99194', '99900', '84936', '69036', '99149', '45013', '32895', '59004', '32322', '14933', '32936', '33562', '72550', '27385', '58049', '58200', '16808', '21360', '32961', '18586', '79307', '15492') and substr(substr(ca_zip, 1, 5), 1, 2) is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20000000 Data size: 1780000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(ca_zip, 1, 5) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20000000 Data size: 1780000000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 70994 Data size: 13630848 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 70994 Data size: 13630848 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized - Map 9 + Map 8 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and substr(substr(ca_zip, 1, 5), 1, 2) is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and substr(substr(ca_zip, 1, 5), 1, 2) is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_zip (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 11 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -324,27 +302,27 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6761 Data size: 655817 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 10L) (type: boolean) - Statistics: Num rows: 7333333 Data size: 7442452291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2253 Data size: 218541 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(_col0, 1, 5) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 7333333 Data size: 7442452291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2253 Data size: 218541 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 7333333 Data size: 7442452291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1126 Data size: 216192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 7333333 Data size: 7442452291 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1126 Data size: 216192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 12 + Reducer 11 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -352,20 +330,20 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 3666666 Data size: 3721225638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1126 Data size: 216192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 13666666 Data size: 13870024459 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3098 Data size: 594816 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13666666 Data size: 13870024459 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3098 Data size: 594816 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 7 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -373,20 +351,20 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10000000 Data size: 10148798821 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5071 Data size: 973632 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 13666666 Data size: 13870024459 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3098 Data size: 594816 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13666666 Data size: 13870024459 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3098 Data size: 594816 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 8 + Reducer 7 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -396,36 +374,58 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6833333 Data size: 6935012229 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3098 Data size: 594816 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 1014 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1014 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 substr(_col0, 1, 2) (type: string) 1 substr(_col2, 1, 2) (type: string) + Reducer 9 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 26666667 Data size: 2373333363 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 67610 Data size: 6558170 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 67610 Data size: 6558170 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) Stage: Stage-2 Spark #### A masked pattern was here #### Vertices: - Map 14 + Map 13 Map Operator Tree: TableScan alias: store filterExpr: (s_store_sk is not null and substr(s_zip, 1, 2) is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 308424 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (s_store_sk is not null and substr(s_zip, 1, 2) is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 308424 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_zip (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 308424 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -434,8 +434,8 @@ STAGE PLANS: 1 substr(_col2, 1, 2) (type: string) outputColumnNames: _col1, _col2 input vertices: - 0 Reducer 8 - Statistics: Num rows: 1874 Data size: 3581903 Basic stats: COMPLETE Column stats: NONE + 0 Reducer 7 + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -443,13 +443,32 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work + Map 4 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_qoy = 1) and (d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_qoy = 1) and (d_year = 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 130 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 5 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Reducer 2 (GROUP, 481) - Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 2 <- Map 1 (GROUP, 2) + Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -457,76 +476,51 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66010002860 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 60203629900 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 5 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_qoy = 1) and (d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_qoy = 1) and (d_year = 2002) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 60203629900 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 37399754 Data size: 1596970464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2, _col8 + input vertices: + 1 Map 13 + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col8 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: decimal(17,2)) Execution mode: vectorized - Reducer 2 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col2, _col8 - input vertices: - 1 Map 14 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col8 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: decimal(17,2)) - Reducer 3 + Reducer 2 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -534,26 +528,26 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(17,2)) - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: decimal(17,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query80.q.out b/ql/src/test/results/clientpositive/perf/spark/query80.q.out index 63cca92556..7641b3ce5d 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query80.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query80.q.out @@ -208,14 +208,14 @@ STAGE PLANS: TableScan alias: promotion filterExpr: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 204700 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 102350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_promo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 102350 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -228,14 +228,14 @@ STAGE PLANS: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 177216 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -253,14 +253,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -273,19 +273,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 20 + Map 19 Map Operator Tree: TableScan alias: promotion filterExpr: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 204700 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 102350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_promo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 102350 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -293,24 +293,44 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work + Map 20 + Map Operator Tree: + TableScan + alias: catalog_page + filterExpr: cp_catalog_page_sk is not null (type: boolean) + Statistics: Num rows: 46000 Data size: 4784000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: cp_catalog_page_sk is not null (type: boolean) + Statistics: Num rows: 46000 Data size: 4784000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cp_catalog_page_sk (type: int), cp_catalog_page_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 46000 Data size: 4784000 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Stage: Stage-5 Spark #### A masked pattern was here #### Vertices: - Map 18 + Map 17 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -323,19 +343,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 29 + Map 28 Map Operator Tree: TableScan alias: promotion filterExpr: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2300 Data size: 204700 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((p_channel_tv = 'N') and p_promo_sk is not null) (type: boolean) - Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 102350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_promo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1150 Data size: 1356710 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1150 Data size: 102350 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -343,19 +363,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 30 + Map 29 Map Operator Tree: TableScan alias: web_site filterExpr: web_site_sk is not null (type: boolean) - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8736 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: web_site_sk is not null (type: boolean) - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8736 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: web_site_sk (type: int), web_site_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8736 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -368,19 +388,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 27 + Map 26 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -392,17 +412,16 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 329), Map 17 (PARTITION-LEVEL SORT, 329) - Reducer 14 <- Map 19 (PARTITION-LEVEL SORT, 371), Reducer 13 (PARTITION-LEVEL SORT, 371) - Reducer 15 <- Map 21 (PARTITION-LEVEL SORT, 447), Reducer 14 (PARTITION-LEVEL SORT, 447) - Reducer 16 <- Reducer 15 (GROUP, 491) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 432), Map 7 (PARTITION-LEVEL SORT, 432) - Reducer 23 <- Map 22 (PARTITION-LEVEL SORT, 164), Map 26 (PARTITION-LEVEL SORT, 164) - Reducer 24 <- Map 28 (PARTITION-LEVEL SORT, 187), Reducer 23 (PARTITION-LEVEL SORT, 187) - Reducer 25 <- Reducer 24 (GROUP, 247) - Reducer 3 <- Map 19 (PARTITION-LEVEL SORT, 483), Reducer 2 (PARTITION-LEVEL SORT, 483) - Reducer 4 <- Reducer 3 (GROUP, 640) - Reducer 5 <- Reducer 16 (GROUP, 1009), Reducer 25 (GROUP, 1009), Reducer 4 (GROUP, 1009) + Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 591), Map 16 (PARTITION-LEVEL SORT, 591) + Reducer 14 <- Map 18 (PARTITION-LEVEL SORT, 57), Reducer 13 (PARTITION-LEVEL SORT, 57) + Reducer 15 <- Reducer 14 (GROUP, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1009), Map 7 (PARTITION-LEVEL SORT, 1009) + Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 300), Map 25 (PARTITION-LEVEL SORT, 300) + Reducer 23 <- Map 27 (PARTITION-LEVEL SORT, 52), Reducer 22 (PARTITION-LEVEL SORT, 52) + Reducer 24 <- Reducer 23 (GROUP, 2) + Reducer 3 <- Map 18 (PARTITION-LEVEL SORT, 161), Reducer 2 (PARTITION-LEVEL SORT, 161) + Reducer 4 <- Reducer 3 (GROUP, 2) + Reducer 5 <- Reducer 15 (GROUP, 2), Reducer 24 (GROUP, 2), Reducer 4 (GROUP, 2) Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -411,19 +430,19 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_sk is not null and ss_promo_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 134426864332 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501693263 Data size: 117086047420 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_promo_sk (type: int), ss_ticket_number (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501693263 Data size: 117086047420 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col4 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col4 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501693263 Data size: 117086047420 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized Map 12 @@ -431,157 +450,137 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_sold_date_sk is not null and cs_catalog_page_sk is not null and cs_item_sk is not null and cs_promo_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 70091040996 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_catalog_page_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283691906 Data size: 69045009692 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_catalog_page_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_order_number (type: int), cs_ext_sales_price (type: decimal(7,2)), cs_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283691906 Data size: 69045009692 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int), _col4 (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: int), _col4 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283691906 Data size: 69045009692 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized - Map 17 + Map 16 Map Operator Tree: TableScan alias: catalog_returns filterExpr: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6552231944 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6552231944 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_item_sk (type: int), cr_order_number (type: int), cr_return_amount (type: decimal(7,2)), cr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6552231944 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 6552231944 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 19 + Map 18 Map Operator Tree: TableScan alias: item filterExpr: ((i_current_price > 50) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 53461408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_current_price > 50) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 154000 Data size: 17820544 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 154000 Data size: 17820544 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 154000 Data size: 17820544 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 21 - Map Operator Tree: - TableScan - alias: catalog_page - filterExpr: cp_catalog_page_sk is not null (type: boolean) - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cp_catalog_page_sk is not null (type: boolean) - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cp_catalog_page_sk (type: int), cp_catalog_page_id (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 46000 Data size: 21198808 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 22 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_sold_date_sk is not null and ws_web_site_sk is not null and ws_item_sk is not null and ws_promo_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 35132193572 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_promo_sk is not null and ws_sold_date_sk is not null and ws_web_site_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143894769 Data size: 35105869564 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_site_sk (type: int), ws_promo_sk (type: int), ws_order_number (type: int), ws_ext_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143894769 Data size: 35105869564 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col4 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col4 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143894769 Data size: 35105869564 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized - Map 26 + Map 25 Map Operator Tree: TableScan alias: web_returns filterExpr: wr_item_sk is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3195157944 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wr_item_sk is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3195157944 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_item_sk (type: int), wr_order_number (type: int), wr_return_amt (type: decimal(7,2)), wr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3195157944 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3195157944 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 28 + Map 27 Map Operator Tree: TableScan alias: item filterExpr: ((i_current_price > 50) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 53461408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_current_price > 50) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 154000 Data size: 17820544 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 154000 Data size: 17820544 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 154000 Data size: 221186819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 154000 Data size: 17820544 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 7 Map Operator Tree: TableScan alias: store_returns filterExpr: sr_item_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 12909836192 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: sr_item_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 12909836192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_item_sk (type: int), sr_ticket_number (type: int), sr_return_amt (type: decimal(7,2)), sr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 12909836192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 12909836192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) Execution mode: vectorized Reducer 13 @@ -595,7 +594,7 @@ STAGE PLANS: 0 _col2 (type: int), _col4 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col9, _col10 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 283691906 Data size: 108180285588 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -604,13 +603,13 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col9, _col10 input vertices: - 1 Map 18 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + 1 Map 17 + Statistics: Num rows: 31519166 Data size: 7268382492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31519166 Data size: 7268382492 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) Reducer 14 Local Work: @@ -623,7 +622,7 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col5, _col6, _col9, _col10 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10506389 Data size: 2267341564 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -632,41 +631,35 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col5, _col6, _col9, _col10 input vertices: - 1 Map 20 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) + 1 Map 19 + Statistics: Num rows: 5253195 Data size: 1033262404 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col6, _col9, _col10, _col18 + input vertices: + 1 Map 20 + Statistics: Num rows: 5253195 Data size: 1543240124 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col18 (type: string), _col5 (type: decimal(7,2)), COALESCE(_col9,0) (type: decimal(12,2)), (_col6 - COALESCE(_col10,0)) (type: decimal(13,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 5253195 Data size: 1543240124 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1), sum(_col2), sum(_col3) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 271922 Data size: 118557992 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 271922 Data size: 118557992 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col5, _col6, _col9, _col10, _col18 - Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col18 (type: string), _col5 (type: decimal(7,2)), COALESCE(_col9,0) (type: decimal(12,2)), (_col6 - COALESCE(_col10,0)) (type: decimal(13,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1), sum(_col2), sum(_col3) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) - Reducer 16 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -674,22 +667,22 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 16936856 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'catalog channel' (type: string), concat('catalog_page', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 231905279 Data size: 31404633508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) Reducer 2 @@ -703,7 +696,7 @@ STAGE PLANS: 0 _col1 (type: int), _col4 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col9, _col10 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 513598586 Data size: 232531324544 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -713,14 +706,14 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col9, _col10 input vertices: 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57062604 Data size: 20560680744 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57062604 Data size: 20560680744 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) - Reducer 23 + Reducer 22 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -731,7 +724,7 @@ STAGE PLANS: 0 _col1 (type: int), _col4 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col9, _col10 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143894769 Data size: 65984830808 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -740,15 +733,15 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col9, _col10 input vertices: - 1 Map 27 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + 1 Map 26 + Statistics: Num rows: 15987214 Data size: 6571919536 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15987214 Data size: 6571919536 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) - Reducer 24 + Reducer 23 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -759,7 +752,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col5, _col6, _col9, _col10 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5329072 Data size: 1647857928 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -768,8 +761,8 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col2, _col5, _col6, _col9, _col10 input vertices: - 1 Map 29 - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: COMPLETE Column stats: NONE + 1 Map 28 + Statistics: Num rows: 2664536 Data size: 603347844 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -778,25 +771,25 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col5, _col6, _col9, _col10, _col18 input vertices: - 1 Map 30 - Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + 1 Map 29 + Statistics: Num rows: 2664536 Data size: 859287184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: string), _col5 (type: decimal(7,2)), COALESCE(_col9,0) (type: decimal(12,2)), (_col6 - COALESCE(_col10,0)) (type: decimal(13,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2664536 Data size: 859287184 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2), sum(_col3) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 212 Data size: 92432 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 212 Data size: 92432 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) - Reducer 25 + Reducer 24 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -804,22 +797,22 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 23108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'web channel' (type: string), concat('web_site', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 53 Data size: 32595 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) Reducer 3 @@ -833,7 +826,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col5, _col6, _col9, _col10 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19020869 Data size: 3809364280 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -843,7 +836,7 @@ STAGE PLANS: outputColumnNames: _col2, _col5, _col6, _col9, _col10 input vertices: 1 Map 10 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9510435 Data size: 1679027060 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -853,22 +846,22 @@ STAGE PLANS: outputColumnNames: _col5, _col6, _col9, _col10, _col18 input vertices: 1 Map 11 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9510435 Data size: 2630070556 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col18 (type: string), _col5 (type: decimal(7,2)), COALESCE(_col9,0) (type: decimal(12,2)), (_col6 - COALESCE(_col10,0)) (type: decimal(13,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9510435 Data size: 2630070556 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2), sum(_col3) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9042 Data size: 3942312 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9042 Data size: 3942312 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) Reducer 4 Execution mode: vectorized @@ -878,22 +871,22 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 822 Data size: 358392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'store channel' (type: string), concat('store', _col0) (type: string), _col1 (type: decimal(17,2)), _col2 (type: decimal(22,2)), _col3 (type: decimal(23,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 822 Data size: 507174 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 2435062716 Data size: 264270971781 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59581 Data size: 37357287 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) Reducer 5 @@ -904,16 +897,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24356442 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(27,2)), _col4 (type: decimal(32,2)), _col5 (type: decimal(33,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: decimal(27,2)), _col3 (type: decimal(32,2)), _col4 (type: decimal(33,2)) Reducer 6 @@ -922,13 +915,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(27,2)), VALUE._col1 (type: decimal(32,2)), VALUE._col2 (type: decimal(33,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1217531358 Data size: 132135485890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38846 Data size: 24045674 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 61900 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 61900 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query81.q.out b/ql/src/test/results/clientpositive/perf/spark/query81.q.out index 60186d961c..269a5a3ef4 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query81.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query81.q.out @@ -59,141 +59,222 @@ with customer_total_return as limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-3 Spark - Edges: - Reducer 10 <- Reducer 16 (PARTITION-LEVEL SORT, 262), Reducer 9 (PARTITION-LEVEL SORT, 262) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 25), Map 17 (PARTITION-LEVEL SORT, 25) - Reducer 15 <- Map 18 (PARTITION-LEVEL SORT, 344), Reducer 14 (PARTITION-LEVEL SORT, 344) - Reducer 16 <- Reducer 15 (GROUP PARTITION-LEVEL SORT, 349) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 697), Map 5 (PARTITION-LEVEL SORT, 697) - Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 656), Reducer 2 (PARTITION-LEVEL SORT, 656) - Reducer 4 <- Reducer 3 (SORT, 1) - Reducer 7 <- Map 11 (PARTITION-LEVEL SORT, 25), Map 6 (PARTITION-LEVEL SORT, 25) - Reducer 8 <- Map 12 (PARTITION-LEVEL SORT, 344), Reducer 7 (PARTITION-LEVEL SORT, 344) - Reducer 9 <- Reducer 8 (GROUP, 349) #### A masked pattern was here #### Vertices: - Map 1 + Map 14 Map Operator Tree: TableScan - alias: customer - filterExpr: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: c_customer_sk (type: int), c_customer_id (type: string), c_current_addr_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Spark + Edges: + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 36), Map 15 (PARTITION-LEVEL SORT, 36) + Reducer 13 <- Reducer 12 (GROUP PARTITION-LEVEL SORT, 7) +#### A masked pattern was here #### + Vertices: Map 11 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: catalog_returns + filterExpr: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null) (type: boolean) + Statistics: Num rows: 28798881 Data size: 3501842564 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null) (type: boolean) + Statistics: Num rows: 28221532 Data size: 3431638916 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + expressions: cr_returned_date_sk (type: int), cr_returning_customer_sk (type: int), cr_returning_addr_sk (type: int), cr_return_amt_inc_tax (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 28221532 Data size: 3431638916 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 14 + Statistics: Num rows: 8749496 Data size: 982108468 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 8749496 Data size: 982108468 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Map 12 + Local Work: + Map Reduce Local Work + Map 15 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 13 - Map Operator Tree: - TableScan - alias: catalog_returns - filterExpr: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cr_returned_date_sk (type: int), cr_returning_customer_sk (type: int), cr_returning_addr_sk (type: int), cr_return_amt_inc_tax (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 12 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col7 + Statistics: Num rows: 8749496 Data size: 1701830236 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col7 (type: string), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4374748 Data size: 882570856 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 4374748 Data size: 882570856 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) + Reducer 13 Execution mode: vectorized - Map 17 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4374748 Data size: 882570856 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 4374748 Data size: 882570856 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), count(_col2) + keys: _col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 2472 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ((_col1 / _col2) * 1.2) (type: decimal(38,11)), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 2376 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 241), Map 5 (PARTITION-LEVEL SORT, 241) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 19), Reducer 8 (PARTITION-LEVEL SORT, 19) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 7 <- Map 10 (PARTITION-LEVEL SORT, 36), Map 6 (PARTITION-LEVEL SORT, 36) + Reducer 8 <- Reducer 7 (GROUP, 7) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: customer + filterExpr: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 30000000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 30000000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c_customer_sk (type: int), c_customer_id (type: string), c_current_addr_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 80000000 Data size: 30000000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 80000000 Data size: 30000000000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) Execution mode: vectorized - Map 18 + Map 10 Map Operator Tree: TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ca_address_sk is not null and ca_state is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map 5 @@ -201,19 +282,19 @@ STAGE PLANS: TableScan alias: customer_address filterExpr: ((ca_state = 'IL') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 41105468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_state = 'IL') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 805989910 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int), ca_street_number (type: string), ca_street_name (type: string), ca_street_type (type: string), ca_suite_number (type: string), ca_city (type: string), ca_county (type: string), ca_zip (type: string), ca_country (type: string), ca_gmt_offset (type: decimal(5,2)), ca_location_type (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col8, _col9, _col10, _col11 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 805989910 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 805989910 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: decimal(5,2)), _col11 (type: string) Execution mode: vectorized Map 6 @@ -221,111 +302,33 @@ STAGE PLANS: TableScan alias: catalog_returns filterExpr: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null and cr_returning_customer_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3501842564 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cr_returned_date_sk is not null and cr_returning_addr_sk is not null and cr_returning_customer_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27657410 Data size: 3363043732 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_returned_date_sk (type: int), cr_returning_customer_sk (type: int), cr_returning_addr_sk (type: int), cr_return_amt_inc_tax (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 27657410 Data size: 3363043732 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 9 + Statistics: Num rows: 8574602 Data size: 962477132 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 8574602 Data size: 962477132 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) Execution mode: vectorized - Reducer 10 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 24200000 Data size: 24560094211 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 > _col3) (type: boolean) - Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: decimal(17,2)) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 8066666 Data size: 8186697393 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 14 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 15 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col7 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col7 (type: string), _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)) - Reducer 16 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: decimal(17,2)) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), count(_col2) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ((_col1 / _col2) * 1.2) (type: decimal(38,11)), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 11000000 Data size: 11163678945 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(38,11)) + Local Work: + Map Reduce Local Work Reducer 2 Reduce Operator Tree: Join Operator @@ -335,12 +338,12 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col11, _col12, _col14, _col15, _col16, _col17 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1568628 Data size: 2055402112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1568628 Data size: 2055402112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: decimal(5,2)), _col17 (type: string) Reducer 3 Reduce Operator Tree: @@ -351,15 +354,15 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col4, _col5, _col7, _col8, _col9, _col10, _col11, _col12, _col14, _col15, _col16, _col17, _col20 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1401080 Data size: 1986895776 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: decimal(5,2)), _col17 (type: string), _col20 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1401080 Data size: 1986895776 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: decimal(5,2)), _col13 (type: string), _col14 (type: decimal(17,2)) sort order: +++++++++++++++ - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1401080 Data size: 1986895776 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 4 Execution mode: vectorized @@ -367,38 +370,22 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: string), KEY.reducesinkkey7 (type: string), KEY.reducesinkkey8 (type: string), KEY.reducesinkkey9 (type: string), KEY.reducesinkkey10 (type: string), KEY.reducesinkkey11 (type: string), KEY.reducesinkkey12 (type: decimal(5,2)), KEY.reducesinkkey13 (type: string), KEY.reducesinkkey14 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1401080 Data size: 1986895776 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 141888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), 'IL' (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: decimal(5,2)), _col13 (type: string), _col14 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 150488 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 150488 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 7 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) - Reducer 8 Reduce Operator Tree: Join Operator condition map: @@ -407,38 +394,57 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col3, _col7 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8574602 Data size: 1667812352 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3) keys: _col7 (type: string), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4287301 Data size: 864929114 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) - Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4287301 Data size: 864929114 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)) - Reducer 9 + Reducer 8 Execution mode: vectorized + Local Work: + Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4287301 Data size: 864929114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: string), _col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + Statistics: Num rows: 4287301 Data size: 864929114 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2, _col3 + input vertices: + 1 Reducer 13 + Statistics: Num rows: 4287301 Data size: 976398940 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col2 > _col3) (type: boolean) + Statistics: Num rows: 1429100 Data size: 325466240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1429100 Data size: 325466240 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1429100 Data size: 325466240 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(17,2)) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query82.q.out b/ql/src/test/results/clientpositive/perf/spark/query82.q.out index daadc88f97..c7f5cb53a7 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query82.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query82.q.out @@ -31,28 +31,29 @@ select i_item_id limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 7 + Map 6 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2002-05-30 00:00:00' AND TIMESTAMP'2002-07-29 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2002-05-30 00:00:00' AND TIMESTAMP'2002-07-29 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -61,66 +62,44 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 399), Map 5 (PARTITION-LEVEL SORT, 399), Map 6 (PARTITION-LEVEL SORT, 399) - Reducer 3 <- Reducer 2 (GROUP, 874) - Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_sales - filterExpr: ss_item_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ss_item_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ss_item_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 5 + Map 4 Map Operator Tree: TableScan alias: item filterExpr: ((i_manufact_id) IN (437, 129, 727, 663) and i_current_price BETWEEN 30 AND 60 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 186512804 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_manufact_id) IN (437, 129, 727, 663) and i_current_price BETWEEN 30 AND 60 and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 297 Data size: 119988 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string), i_current_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)) + Statistics: Num rows: 297 Data size: 119988 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) Execution mode: vectorized - Map 6 + Local Work: + Map Reduce Local Work + Map 5 Map Operator Tree: TableScan alias: inventory filterExpr: (inv_quantity_on_hand BETWEEN 100 AND 500 and inv_item_sk is not null and inv_date_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37584000 Data size: 443485108 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) (type: boolean) - Statistics: Num rows: 4176000 Data size: 65980122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4176000 Data size: 49276128 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: inv_date_sk (type: int), inv_item_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4176000 Data size: 65980122 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4176000 Data size: 49276128 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -129,66 +108,91 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1 input vertices: - 1 Map 7 - Statistics: Num rows: 4593600 Data size: 72578135 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4593600 Data size: 72578135 Basic stats: COMPLETE Column stats: NONE + 1 Map 6 + Statistics: Num rows: 463969 Data size: 1855876 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 736) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: ss_item_sk is not null (type: boolean) + Statistics: Num rows: 575995635 Data size: 2303982540 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ss_item_sk is not null (type: boolean) + Statistics: Num rows: 575995635 Data size: 2303982540 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ss_item_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 575995635 Data size: 2303982540 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + outputColumnNames: _col2, _col3, _col4 + input vertices: + 1 Map 4 + 2 Map 5 + Statistics: Num rows: 237894414 Data size: 94206187944 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 237894414 Data size: 94206187944 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + Statistics: Num rows: 237894414 Data size: 94206187944 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: vectorized Local Work: Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col1 (type: int) - outputColumnNames: _col2, _col3, _col4 - Statistics: Num rows: 1267190424 Data size: 111791907016 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1267190424 Data size: 111791907016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) - Statistics: Num rows: 1267190424 Data size: 111791907016 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: decimal(7,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26286282 Data size: 10409367672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26286282 Data size: 10409367672 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string), _col2 (type: decimal(7,2)) - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26286282 Data size: 10409367672 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 39600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 39600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query83.q.out b/ql/src/test/results/clientpositive/perf/spark/query83.q.out index 1199d295e5..514b480293 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query83.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query83.q.out @@ -131,381 +131,521 @@ with sr_items as limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3 + Stage-7 depends on stages: Stage-2 + Stage-6 depends on stages: Stage-7 + Stage-5 depends on stages: Stage-6 + Stage-10 depends on stages: Stage-5 + Stage-9 depends on stages: Stage-10 + Stage-8 depends on stages: Stage-9 + Stage-1 depends on stages: Stage-8 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-4 Spark - Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 2), Map 13 (PARTITION-LEVEL SORT, 2) - Reducer 12 <- Reducer 11 (GROUP, 2) - Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 41), Map 18 (PARTITION-LEVEL SORT, 41) - Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 40), Reducer 20 (PARTITION-LEVEL SORT, 40) - Reducer 17 <- Reducer 16 (GROUP, 43) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 30), Map 7 (PARTITION-LEVEL SORT, 30) - Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 2), Reducer 23 (PARTITION-LEVEL SORT, 2) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 2), Map 24 (PARTITION-LEVEL SORT, 2) - Reducer 23 <- Reducer 22 (GROUP, 2) - Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 16), Map 29 (PARTITION-LEVEL SORT, 16) - Reducer 27 <- Reducer 26 (PARTITION-LEVEL SORT, 13), Reducer 31 (PARTITION-LEVEL SORT, 13) - Reducer 28 <- Reducer 27 (GROUP, 13) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 27), Reducer 9 (PARTITION-LEVEL SORT, 27) - Reducer 31 <- Map 30 (PARTITION-LEVEL SORT, 2), Reducer 34 (PARTITION-LEVEL SORT, 2) - Reducer 33 <- Map 32 (PARTITION-LEVEL SORT, 2), Map 35 (PARTITION-LEVEL SORT, 2) - Reducer 34 <- Reducer 33 (GROUP, 2) - Reducer 4 <- Reducer 3 (GROUP, 29) - Reducer 5 <- Reducer 17 (PARTITION-LEVEL SORT, 42), Reducer 28 (PARTITION-LEVEL SORT, 42), Reducer 4 (PARTITION-LEVEL SORT, 42) - Reducer 6 <- Reducer 5 (SORT, 1) - Reducer 9 <- Map 8 (PARTITION-LEVEL SORT, 2), Reducer 12 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: - Map 1 + Map 10 Map Operator Tree: TableScan - alias: catalog_returns - filterExpr: (cr_item_sk is not null and cr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (cr_item_sk is not null and cr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 3652 Data size: 357896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: cr_returned_date_sk (type: int), cr_item_sk (type: int), cr_return_quantity (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int) + expressions: d_week_seq (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3652 Data size: 14608 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 658 Data size: 2632 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 10 + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark + Edges: + Reducer 9 <- Map 8 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 8 Map Operator Tree: TableScan alias: date_dim filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date (type: string), d_week_seq (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + input vertices: + 1 Map 10 + Statistics: Num rows: 3654 Data size: 343476 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reducer 9 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Reducer 9 + Statistics: Num rows: 1827 Data size: 7308 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 13 + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 18 Map Operator Tree: TableScan alias: date_dim filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3652 Data size: 357896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_week_seq (type: int) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3652 Data size: 14608 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 658 Data size: 2632 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 14 + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark + Edges: + Reducer 17 <- Map 16 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 16 Map Operator Tree: TableScan - alias: store_returns - filterExpr: (sr_item_sk is not null and sr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (sr_item_sk is not null and sr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + predicate: (d_date is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_return_quantity (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int) + expressions: d_date (type: string), d_week_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + input vertices: + 1 Map 18 + Statistics: Num rows: 3654 Data size: 343476 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 18 + Local Work: + Map Reduce Local Work + Reducer 17 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 15 Map Operator Tree: TableScan - alias: item - filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + predicate: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int), i_item_id (type: string) + expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Reducer 17 + Statistics: Num rows: 1827 Data size: 7308 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 19 + Local Work: + Map Reduce Local Work + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 26 Map Operator Tree: TableScan alias: date_dim - filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 3652 Data size: 357896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int), d_date (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + expressions: d_week_seq (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3652 Data size: 14608 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 658 Data size: 2632 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 21 + Local Work: + Map Reduce Local Work + + Stage: Stage-9 + Spark + Edges: + Reducer 25 <- Map 24 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 24 Map Operator Tree: TableScan alias: date_dim filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date (type: string), d_week_seq (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + input vertices: + 1 Map 26 + Statistics: Num rows: 3654 Data size: 343476 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized - Map 24 + Local Work: + Map Reduce Local Work + Reducer 25 + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1827 Data size: 171738 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 23 Map Operator Tree: TableScan alias: date_dim - filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (d_date is not null and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_week_seq (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + input vertices: + 1 Reducer 25 + Statistics: Num rows: 1827 Data size: 7308 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Map 25 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 6), Map 14 (PARTITION-LEVEL SORT, 6) + Reducer 13 <- Reducer 12 (GROUP, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 6 (PARTITION-LEVEL SORT, 4) + Reducer 20 <- Map 19 (PARTITION-LEVEL SORT, 2), Map 22 (PARTITION-LEVEL SORT, 2) + Reducer 21 <- Reducer 20 (GROUP, 2) + Reducer 3 <- Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 13 (PARTITION-LEVEL SORT, 2), Reducer 21 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2) + Reducer 5 <- Reducer 4 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: web_returns - filterExpr: (wr_item_sk is not null and wr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + alias: catalog_returns + filterExpr: (cr_item_sk is not null and cr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 28798881 Data size: 343281600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (wr_item_sk is not null and wr_returned_date_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + predicate: (cr_item_sk is not null and cr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 28798881 Data size: 343281600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: wr_returned_date_sk (type: int), wr_item_sk (type: int), wr_return_quantity (type: int) + expressions: cr_returned_date_sk (type: int), cr_item_sk (type: int), cr_return_quantity (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 343281600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 343281600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int) Execution mode: vectorized - Map 29 + Map 11 Map Operator Tree: TableScan - alias: item - filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + alias: store_returns + filterExpr: (sr_item_sk is not null and sr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 57591150 Data size: 674974912 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + predicate: (sr_item_sk is not null and sr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 55578005 Data size: 651380620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: i_item_sk (type: int), i_item_id (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_return_quantity (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 55578005 Data size: 651380620 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 55578005 Data size: 651380620 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: int) Execution mode: vectorized - Map 30 + Map 14 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int), d_date (type: string) + expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: vectorized - Map 32 + Map 19 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (d_week_seq is not null and d_date is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: web_returns + filterExpr: (wr_item_sk is not null and wr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 14398467 Data size: 167594272 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date is not null and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (wr_item_sk is not null and wr_returned_date_sk is not null) (type: boolean) + Statistics: Num rows: 13749816 Data size: 160044152 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date (type: string), d_week_seq (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + expressions: wr_returned_date_sk (type: int), wr_item_sk (type: int), wr_return_quantity (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 13749816 Data size: 160044152 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized - Map 35 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_week_seq (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13749816 Data size: 160044152 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: int) Execution mode: vectorized - Map 7 + Map 22 Map Operator Tree: TableScan alias: item filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized - Map 8 + Map 6 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: (i_item_sk is not null and i_item_id is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (d_date is not null and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int), d_date (type: string) + expressions: i_item_sk (type: int), i_item_id (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 48048000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) Execution mode: vectorized - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE Reducer 12 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reducer 15 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -514,36 +654,30 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: string) - Reducer 16 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - Statistics: Num rows: 69685294 Data size: 5399255980 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 69685294 Data size: 5399255980 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 69685294 Data size: 5399255980 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 17 + Statistics: Num rows: 55578005 Data size: 5986869100 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + input vertices: + 1 Map 15 + Statistics: Num rows: 9133323 Data size: 942081244 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 204284 Data size: 22062672 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 204284 Data size: 22062672 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 13 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -551,14 +685,16 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 34842647 Data size: 2699627990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51071 Data size: 5515668 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 34842647 Data size: 2699627990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51071 Data size: 5515668 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 2 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -567,62 +703,32 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: string) + Statistics: Num rows: 28798881 Data size: 3107974176 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + input vertices: + 1 Map 7 + Statistics: Num rows: 4505327 Data size: 466249036 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 97236 Data size: 10501488 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 97236 Data size: 10501488 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) Reducer 20 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 22 - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 23 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reducer 26 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -631,36 +737,30 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col4 - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: string) - Reducer 27 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 28 + Statistics: Num rows: 13749816 Data size: 1480026488 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + input vertices: + 1 Map 23 + Statistics: Num rows: 2073157 Data size: 213132400 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 46858 Data size: 5060664 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 46858 Data size: 5060664 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 21 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -668,84 +768,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 8711072 Data size: 801742469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46858 Data size: 5060664 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8711072 Data size: 801742469 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46858 Data size: 5060664 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4 - Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - keys: _col4 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 31 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 33 - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reducer 34 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE - Reducer 4 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -753,14 +783,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 17423323 Data size: 1849627061 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 48618 Data size: 5250744 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 17423323 Data size: 1849627061 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 48618 Data size: 5250744 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Reducer 5 + Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -771,49 +801,34 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col5 - Statistics: Num rows: 76653825 Data size: 5939181706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46858 Data size: 5810392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: bigint), (((UDFToDouble(_col3) / UDFToDouble(((_col3 + _col1) + _col5))) / 3.0D) * 100.0D) (type: double), _col1 (type: bigint), (((UDFToDouble(_col1) / UDFToDouble(((_col3 + _col1) + _col5))) / 3.0D) * 100.0D) (type: double), _col5 (type: bigint), (((UDFToDouble(_col5) / UDFToDouble(((_col3 + _col1) + _col5))) / 3.0D) * 100.0D) (type: double), (CAST( ((_col3 + _col1) + _col5) AS decimal(19,0)) / 3) (type: decimal(25,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 76653825 Data size: 5939181706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46858 Data size: 12183080 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ - Statistics: Num rows: 76653825 Data size: 5939181706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46858 Data size: 12183080 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: double), _col3 (type: bigint), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: decimal(25,6)) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: double), VALUE._col1 (type: bigint), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: decimal(25,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 76653825 Data size: 5939181706 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 46858 Data size: 12183080 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 7700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 26000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 7700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 26000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 9 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query84.q.out b/ql/src/test/results/clientpositive/perf/spark/query84.q.out index 0e62a3ee85..ad1a53a57c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query84.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query84.q.out @@ -39,29 +39,30 @@ select c_customer_id as customer_id limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-4 Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 7 Map Operator Tree: TableScan alias: income_band filterExpr: ((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287) and ib_income_band_sk is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287) and ib_income_band_sk is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ib_income_band_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -70,23 +71,43 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 5 + Map Operator Tree: + TableScan + alias: customer_address + filterExpr: ((ca_city = 'Hopewell') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 3880000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((ca_city = 'Hopewell') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 44643 Data size: 4330371 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 44643 Data size: 4285728 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 Map Operator Tree: TableScan alias: household_demographics filterExpr: (hd_demo_sk is not null and hd_income_band_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 57600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (hd_demo_sk is not null and hd_income_band_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 57600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int), hd_income_band_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 57600 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -95,8 +116,8 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0 input vertices: - 1 Map 9 - Statistics: Num rows: 7920 Data size: 847440 Basic stats: COMPLETE Column stats: NONE + 1 Map 7 + Statistics: Num rows: 721 Data size: 2884 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -105,158 +126,135 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 691), Map 4 (PARTITION-LEVEL SORT, 691), Reducer 6 (PARTITION-LEVEL SORT, 691) - Reducer 3 <- Reducer 2 (SORT, 1) - Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 697), Map 7 (PARTITION-LEVEL SORT, 697) #### A masked pattern was here #### Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: store_returns - filterExpr: sr_cdemo_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: sr_cdemo_sk is not null (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: sr_cdemo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 4 + Map 3 Map Operator Tree: TableScan alias: customer_demographics filterExpr: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 7447200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cd_demo_sk is not null (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 7447200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 7447200 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) Execution mode: vectorized - Map 5 + Local Work: + Map Reduce Local Work + Map 4 Map Operator Tree: TableScan alias: customer filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 23337609520 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74500295 Data size: 21733234924 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_id (type: string), c_current_cdemo_sk (type: int), c_current_hdemo_sk (type: int), c_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col3 (type: int) - sort order: + - Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 74500295 Data size: 21733234924 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col4, _col5 + input vertices: + 1 Map 5 + Statistics: Num rows: 83148 Data size: 23281448 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col4, _col5 + input vertices: + 1 Map 6 + Statistics: Num rows: 8315 Data size: 2328204 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) Execution mode: vectorized - Map 7 + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: customer_address - filterExpr: ((ca_city = 'Hopewell') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + alias: store_returns + filterExpr: sr_cdemo_sk is not null (type: boolean) + Statistics: Num rows: 57591150 Data size: 222310796 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((ca_city = 'Hopewell') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + predicate: sr_cdemo_sk is not null (type: boolean) + Statistics: Num rows: 55577698 Data size: 214538560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ca_address_sk (type: int) + expressions: sr_cdemo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55577698 Data size: 214538560 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + outputColumnNames: _col2, _col6, _col7 + input vertices: + 1 Map 3 + 2 Map 4 + Statistics: Num rows: 264534 Data size: 74069520 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: concat(concat(_col7, ', '), _col6) (type: string), _col2 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 264534 Data size: 101581056 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Statistics: Num rows: 264534 Data size: 101581056 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string) Execution mode: vectorized + Local Work: + Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col1 (type: int) - outputColumnNames: _col2, _col6, _col7 - Statistics: Num rows: 212960011 Data size: 183149913305 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: concat(concat(_col7, ', '), _col6) (type: string), _col2 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 212960011 Data size: 183149913305 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Statistics: Num rows: 212960011 Data size: 183149913305 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string) - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 212960011 Data size: 183149913305 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264534 Data size: 101581056 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 38400 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 38400 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 6 - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col4, _col5 - input vertices: - 1 Map 8 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col4 (type: string), _col5 (type: string) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query85.q.out b/ql/src/test/results/clientpositive/perf/spark/query85.q.out index af4a835507..0246043a1f 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query85.q.out @@ -165,28 +165,90 @@ order by substr(r_reason_desc,1,20) limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 5 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 652 Data size: 5216 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Stage: Stage-2 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 55), Map 6 (PARTITION-LEVEL SORT, 55) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 94), Reducer 2 (PARTITION-LEVEL SORT, 94) + Reducer 4 <- Map 8 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: - Map 14 + Map 1 + Map Operator Tree: + TableScan + alias: web_sales + filterExpr: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_web_page_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 35132189296 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) (type: boolean) + Statistics: Num rows: 47977044 Data size: 11704912368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_page_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 47977044 Data size: 11704912368 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6 + input vertices: + 1 Map 5 + Statistics: Num rows: 17130671 Data size: 4109922384 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col3 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col3 (type: int) + Statistics: Num rows: 17130671 Data size: 4109922384 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 12 Map Operator Tree: TableScan alias: web_page filterExpr: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wp_web_page_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 18408 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -194,19 +256,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 15 + Map 13 Map Operator Tree: TableScan alias: reason filterExpr: r_reason_sk is not null (type: boolean) - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 7272 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: r_reason_sk is not null (type: boolean) - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 7272 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: r_reason_sk (type: int), r_reason_desc (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 7272 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col13 (type: int) @@ -214,154 +276,66 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 52), Map 9 (PARTITION-LEVEL SORT, 52) - Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 67), Reducer 2 (PARTITION-LEVEL SORT, 67) - Reducer 4 <- Map 11 (PARTITION-LEVEL SORT, 68), Reducer 3 (PARTITION-LEVEL SORT, 68) - Reducer 5 <- Map 12 (PARTITION-LEVEL SORT, 12), Reducer 4 (PARTITION-LEVEL SORT, 12) - Reducer 6 <- Map 13 (PARTITION-LEVEL SORT, 165), Reducer 5 (PARTITION-LEVEL SORT, 165) - Reducer 7 <- Reducer 6 (GROUP, 71) - Reducer 8 <- Reducer 7 (SORT, 1) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: web_sales - filterExpr: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_web_page_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 48000888 Data size: 6526732556 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_page_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 48000888 Data size: 6526732556 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 48000888 Data size: 6526732556 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) - Execution mode: vectorized - Map 10 + Map 6 Map Operator Tree: TableScan alias: web_returns filterExpr: (wr_item_sk is not null and wr_order_number is not null and wr_refunded_cdemo_sk is not null and wr_returning_cdemo_sk is not null and wr_refunded_addr_sk is not null and wr_reason_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3415165604 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (wr_item_sk is not null and wr_order_number is not null and wr_reason_sk is not null and wr_refunded_addr_sk is not null and wr_refunded_cdemo_sk is not null and wr_returning_cdemo_sk is not null) (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11975292 Data size: 2840413864 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_item_sk (type: int), wr_refunded_cdemo_sk (type: int), wr_refunded_addr_sk (type: int), wr_returning_cdemo_sk (type: int), wr_reason_sk (type: int), wr_order_number (type: int), wr_fee (type: decimal(7,2)), wr_refunded_cash (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11975292 Data size: 2840413864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col5 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col5 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11975292 Data size: 2840413864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) Execution mode: vectorized - Map 11 + Map 7 Map Operator Tree: TableScan alias: cd1 filterExpr: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 340709400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 12 + Map 8 Map Operator Tree: TableScan alias: cd2 filterExpr: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 340709400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Map 13 - Map Operator Tree: - TableScan - alias: customer_address - filterExpr: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_address_sk (type: int), ca_state (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 265971 Data size: 48672693 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 52800977 Data size: 7179405967 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col3 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col3 (type: int) - Statistics: Num rows: 52800977 Data size: 7179405967 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) - Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -370,14 +344,14 @@ STAGE PLANS: 0 _col1 (type: int), _col3 (type: int) 1 _col0 (type: int), _col5 (type: int) outputColumnNames: _col2, _col4, _col5, _col6, _col10, _col11, _col12, _col13, _col15, _col16 - Statistics: Num rows: 58081075 Data size: 7897346734 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25617525 Data size: 11960574592 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col10 (type: int) sort order: + Map-reduce partition columns: _col10 (type: int) - Statistics: Num rows: 58081075 Data size: 7897346734 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25617525 Data size: 11960574592 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col11 (type: int), _col12 (type: int), _col13 (type: int), _col15 (type: decimal(7,2)), _col16 (type: decimal(7,2)) - Reducer 4 + Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -386,17 +360,19 @@ STAGE PLANS: 0 _col10 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col4, _col5, _col6, _col11, _col12, _col13, _col15, _col16, _col18, _col19 - Statistics: Num rows: 63889183 Data size: 8687081595 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3711392 Data size: 2272529352 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col18 = 'D') and (_col19 = 'Primary') and _col5 BETWEEN 50 AND 100) or ((_col18 = 'M') and (_col19 = '4 yr Degree') and _col5 BETWEEN 100 AND 150) or ((_col18 = 'U') and (_col19 = 'Advanced Degree') and _col5 BETWEEN 150 AND 200)) (type: boolean) - Statistics: Num rows: 5324097 Data size: 723923250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19635 Data size: 12023105 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col12 (type: int), _col18 (type: string), _col19 (type: string) sort order: +++ Map-reduce partition columns: _col12 (type: int), _col18 (type: string), _col19 (type: string) - Statistics: Num rows: 5324097 Data size: 723923250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19635 Data size: 12023105 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int), _col15 (type: decimal(7,2)), _col16 (type: decimal(7,2)) - Reducer 5 + Reducer 4 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -405,61 +381,81 @@ STAGE PLANS: 0 _col12 (type: int), _col18 (type: string), _col19 (type: string) 1 _col0 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: _col2, _col4, _col6, _col11, _col13, _col15, _col16 - Statistics: Num rows: 5856506 Data size: 796315592 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col11 (type: int) - sort order: + - Map-reduce partition columns: _col11 (type: int) - Statistics: Num rows: 5856506 Data size: 796315592 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col13 (type: int), _col15 (type: decimal(7,2)), _col16 (type: decimal(7,2)) - Reducer 6 + Statistics: Num rows: 19912 Data size: 6346632 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col11 (type: int) + 1 _col0 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Map 9 (GROUP, 2) + Reducer 11 <- Reducer 10 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 9 + Map Operator Tree: + TableScan + alias: customer_address + filterExpr: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 7480000000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((ca_country = 'United States') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 3740000000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ca_address_sk (type: int), ca_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20000000 Data size: 3740000000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col11 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4, _col6, _col13, _col15, _col16, _col24 + input vertices: + 0 Reducer 4 + Statistics: Num rows: 9956 Data size: 3669932 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((((_col24 = 'KY') or (_col24 = 'GA') or (_col24 = 'NM')) and _col6 BETWEEN 100 AND 200) or (((_col24 = 'MT') or (_col24 = 'OR') or (_col24 = 'IN')) and _col6 BETWEEN 150 AND 300) or (((_col24 = 'WI') or (_col24 = 'MO') or (_col24 = 'WV')) and _col6 BETWEEN 50 AND 250)) (type: boolean) + Statistics: Num rows: 3318 Data size: 1223256 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col13, _col15, _col16 + input vertices: + 1 Map 12 + Statistics: Num rows: 3318 Data size: 553100 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col13 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col15, _col16, _col28 + input vertices: + 1 Map 13 + Statistics: Num rows: 3318 Data size: 865470 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col4), count(_col4), sum(_col16), count(_col16), sum(_col15), count(_col15) + keys: _col28 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 72 Data size: 25416 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 72 Data size: 25416 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint) + Execution mode: vectorized Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col11 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col6, _col13, _col15, _col16, _col24 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((_col24 = 'KY') or (_col24 = 'GA') or (_col24 = 'NM')) and _col6 BETWEEN 100 AND 200) or (((_col24 = 'MT') or (_col24 = 'OR') or (_col24 = 'IN')) and _col6 BETWEEN 150 AND 300) or (((_col24 = 'WI') or (_col24 = 'MO') or (_col24 = 'WV')) and _col6 BETWEEN 50 AND 250)) (type: boolean) - Statistics: Num rows: 7333332 Data size: 7442451276 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col13, _col15, _col16 - input vertices: - 1 Map 14 - Statistics: Num rows: 8066665 Data size: 8186696581 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col13 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col15, _col16, _col28 - input vertices: - 1 Map 15 - Statistics: Num rows: 8873331 Data size: 9005366434 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col4), count(_col4), sum(_col16), count(_col16), sum(_col15), count(_col15) - keys: _col28 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 8873331 Data size: 9005366434 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8873331 Data size: 9005366434 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint) - Reducer 7 + Reducer 10 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -467,29 +463,29 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 25416 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col1) / _col2) (type: double), (_col3 / _col4) (type: decimal(37,22)), (_col5 / _col6) (type: decimal(37,22)), substr(_col0, 1, 20) (type: string) outputColumnNames: _col4, _col5, _col6, _col7 - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 59904 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col7 (type: string), _col4 (type: double), _col5 (type: decimal(37,22)), _col6 (type: decimal(37,22)) sort order: ++++ - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 59904 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 8 + Reducer 11 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: decimal(37,22)), KEY.reducesinkkey3 (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 59904 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 101400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 59904 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 101400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 59904 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query86.q.out b/ql/src/test/results/clientpositive/perf/spark/query86.q.out index 1d1e4ef3d3..c2eb08dd6f 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query86.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query86.q.out @@ -63,14 +63,14 @@ STAGE PLANS: TableScan alias: d1 filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -82,9 +82,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 174), Map 7 (PARTITION-LEVEL SORT, 174) - Reducer 3 <- Reducer 2 (GROUP, 556) - Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 278) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 16), Map 7 (PARTITION-LEVEL SORT, 16) + Reducer 3 <- Reducer 2 (GROUP, 2) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2) Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -93,14 +93,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_sold_date_sk is not null and ws_item_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 17276167908 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271872472 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_net_paid (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271872472 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -110,12 +110,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 6 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 1851437952 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 1851437952 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized Local Work: @@ -125,19 +125,19 @@ STAGE PLANS: TableScan alias: item filterExpr: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_class (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 85932000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Reducer 2 @@ -149,22 +149,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 4698587824 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col7 (type: string), _col6 (type: string), _col2 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15995224 Data size: 4698587824 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 522729705 Data size: 71076122589 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58140 Data size: 17558280 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 522729705 Data size: 71076122589 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58140 Data size: 17558280 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: decimal(17,2)) Reducer 3 Execution mode: vectorized @@ -174,16 +174,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 924120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(17,2)), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 924120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (grouping(_col3, 1) + grouping(_col3, 0)) (type: bigint), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string), _col2 (type: decimal(17,2)) sort order: ++- Map-reduce partition columns: (grouping(_col3, 1) + grouping(_col3, 0)) (type: bigint), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END (type: string) - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 924120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) Reducer 4 Execution mode: vectorized @@ -191,7 +191,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: decimal(17,2)), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 924120 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -212,15 +212,15 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 924120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: decimal(17,2)), _col0 (type: string), _col1 (type: string), (grouping(_col3, 1) + grouping(_col3, 0)) (type: bigint), rank_window_0 (type: int), CASE WHEN (((grouping(_col3, 1) + grouping(_col3, 0)) = 0)) THEN (_col0) ELSE (null) END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1499400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: bigint), _col5 (type: string), _col4 (type: int) sort order: -++ - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1499400 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: decimal(17,2)), _col1 (type: string), _col2 (type: string) Reducer 5 @@ -229,13 +229,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 261364852 Data size: 35538061226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3060 Data size: 1499400 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 49000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query87.q.out b/ql/src/test/results/clientpositive/perf/spark/query87.q.out index 8ac6dcedbe..48e8dd67cc 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query87.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query87.q.out @@ -57,14 +57,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -82,14 +82,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -107,14 +107,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7450998 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 827832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -126,14 +126,14 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 873), Map 9 (PARTITION-LEVEL SORT, 873) - Reducer 11 <- Reducer 10 (GROUP PARTITION-LEVEL SORT, 369) - Reducer 15 <- Map 13 (PARTITION-LEVEL SORT, 706), Map 14 (PARTITION-LEVEL SORT, 706) - Reducer 16 <- Reducer 15 (GROUP PARTITION-LEVEL SORT, 186) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 975), Map 13 (PARTITION-LEVEL SORT, 975) - Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 481) - Reducer 4 <- Reducer 11 (GROUP PARTITION-LEVEL SORT, 213), Reducer 3 (GROUP PARTITION-LEVEL SORT, 213) - Reducer 5 <- Reducer 16 (GROUP, 56), Reducer 4 (GROUP, 56) + Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 140), Map 9 (PARTITION-LEVEL SORT, 140) + Reducer 11 <- Reducer 10 (GROUP PARTITION-LEVEL SORT, 68) + Reducer 15 <- Map 13 (PARTITION-LEVEL SORT, 128), Map 14 (PARTITION-LEVEL SORT, 128) + Reducer 16 <- Reducer 15 (GROUP PARTITION-LEVEL SORT, 35) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 159), Map 13 (PARTITION-LEVEL SORT, 159) + Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 125) + Reducer 4 <- Reducer 11 (GROUP PARTITION-LEVEL SORT, 205), Reducer 3 (GROUP PARTITION-LEVEL SORT, 205) + Reducer 5 <- Reducer 16 (GROUP, 71), Reducer 4 (GROUP, 71) Reducer 6 <- Reducer 5 (GROUP, 1) #### A masked pattern was here #### Vertices: @@ -142,14 +142,14 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_sold_date_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 4400627472 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525327388 Data size: 4013520236 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -159,12 +159,12 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 7 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 5625297490 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 5625297490 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Execution mode: vectorized Local Work: @@ -174,19 +174,19 @@ STAGE PLANS: TableScan alias: customer filterExpr: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c_customer_sk is not null (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 14720000000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 14 @@ -194,14 +194,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_sold_date_sk is not null and ws_bill_customer_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151734616 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143930993 Data size: 1151161360 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -211,12 +211,12 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 17 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 1566997880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 1566997880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Execution mode: vectorized Local Work: @@ -226,14 +226,14 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_sold_date_sk is not null and cs_bill_customer_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 2292401892 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 2269540704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 285117831 Data size: 2269540704 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -243,12 +243,12 @@ STAGE PLANS: outputColumnNames: _col1, _col3 input vertices: 1 Map 12 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 3098704958 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 3098704958 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string) Execution mode: vectorized Local Work: @@ -262,17 +262,17 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Reducer 11 Execution mode: vectorized Reduce Operator Tree: @@ -280,36 +280,36 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8679659934 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 87116929 Data size: 11797382219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 8933080662 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 1L (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 87116929 Data size: 11797382219 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31677591 Data size: 9186501390 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 90043306 Data size: 26112558740 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 90043306 Data size: 26112558740 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 90043306 Data size: 26112558740 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 15 Reduce Operator Tree: @@ -320,17 +320,17 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Reducer 16 Execution mode: vectorized Reduce Operator Tree: @@ -338,36 +338,36 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4381599212 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 43560808 Data size: 5923010113 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4509529116 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 1L (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 43560808 Data size: 5923010113 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15991238 Data size: 4637459020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 8989551950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 8989551950 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 8989551950 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -378,17 +378,17 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col3, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized Reduce Operator Tree: @@ -396,36 +396,36 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 15992205910 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 16459131630 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 2L (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 58365715 Data size: 16926057350 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 90043306 Data size: 26112558740 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 90043306 Data size: 26112558740 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 261355616 Data size: 27168769766 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 90043306 Data size: 26112558740 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 4 Execution mode: vectorized @@ -435,39 +435,39 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 130677808 Data size: 13584384883 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 90043306 Data size: 26112558740 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col3 * 2) = _col4) and (_col3 > 0L)) (type: boolean) - Statistics: Num rows: 21779634 Data size: 2264064077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15007217 Data size: 4352092930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 21779634 Data size: 2264064077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15007217 Data size: 4352092930 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 10889817 Data size: 1132032038 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15007217 Data size: 4232035194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), 2L (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10889817 Data size: 1132032038 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15007217 Data size: 4352092930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: bigint), (_col3 * _col4) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 8989551950 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col4) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 8989551950 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 54450625 Data size: 7055042151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 8989551950 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 5 Execution mode: vectorized @@ -477,24 +477,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 27225312 Data size: 3527521010 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 8989551950 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: bigint), _col4 (type: bigint) outputColumnNames: _col3, _col4 - Statistics: Num rows: 27225312 Data size: 3527521010 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30998455 Data size: 495975280 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col3 * 2) = _col4) and (_col3 > 0L)) (type: boolean) - Statistics: Num rows: 4537552 Data size: 587920168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5166409 Data size: 82662544 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 4537552 Data size: 587920168 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5166409 Data size: 82662544 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 6 Execution mode: vectorized @@ -503,10 +503,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query88.q.out b/ql/src/test/results/clientpositive/perf/spark/query88.q.out index 6c1238a9b6..e4d9be7d4d 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query88.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query88.q.out @@ -184,80 +184,126 @@ from and store.s_store_name = 'ese') s8 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-2 depends on stages: Stage-3, Stage-4, Stage-5, Stage-6, Stage-7, Stage-8, Stage-9 - Stage-10 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-10 - Stage-4 is a root stage Stage-5 is a root stage - Stage-6 is a root stage - Stage-7 is a root stage + Stage-4 depends on stages: Stage-5 + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3, Stage-6, Stage-9, Stage-12, Stage-15, Stage-18, Stage-21 + Stage-26 depends on stages: Stage-2 + Stage-25 depends on stages: Stage-26 + Stage-24 depends on stages: Stage-25 + Stage-1 depends on stages: Stage-24 Stage-8 is a root stage - Stage-9 is a root stage + Stage-7 depends on stages: Stage-8 + Stage-6 depends on stages: Stage-7 + Stage-11 is a root stage + Stage-10 depends on stages: Stage-11 + Stage-9 depends on stages: Stage-10 + Stage-14 is a root stage + Stage-13 depends on stages: Stage-14 + Stage-12 depends on stages: Stage-13 + Stage-17 is a root stage + Stage-16 depends on stages: Stage-17 + Stage-15 depends on stages: Stage-16 + Stage-20 is a root stage + Stage-19 depends on stages: Stage-20 + Stage-18 depends on stages: Stage-19 + Stage-23 is a root stage + Stage-22 depends on stages: Stage-23 + Stage-21 depends on stages: Stage-22 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-5 Spark #### A masked pattern was here #### Vertices: - Map 10 + Map 7 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: time_dim + filterExpr: ((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 8 + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 Map Operator Tree: TableScan - alias: time_dim - filterExpr: ((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: t_time_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 7 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 9 + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 8 Map Operator Tree: TableScan alias: household_demographics filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 6 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -265,394 +311,254 @@ STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 12 <- Map 11 (GROUP, 1) - Reducer 17 <- Map 16 (GROUP, 1) - Reducer 22 <- Map 21 (GROUP, 1) - Reducer 27 <- Map 26 (GROUP, 1) - Reducer 32 <- Map 31 (GROUP, 1) - Reducer 37 <- Map 36 (GROUP, 1) - Reducer 7 <- Map 6 (GROUP, 1) + Reducer 10 <- Map 9 (GROUP, 1) + Reducer 15 <- Map 14 (GROUP, 1) + Reducer 20 <- Map 19 (GROUP, 1) + Reducer 25 <- Map 24 (GROUP, 1) + Reducer 30 <- Map 29 (GROUP, 1) + Reducer 35 <- Map 34 (GROUP, 1) + Reducer 40 <- Map 39 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 11 + Map 14 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 13 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 14 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 15 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 13 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 16 + Map 19 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 18 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 19 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 20 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 18 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 21 + Map 24 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 23 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 24 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 25 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 23 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 26 + Map 29 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 28 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 29 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 30 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 28 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 31 + Map 34 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 33 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 34 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 35 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 33 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 36 + Map 39 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 38 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 39 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 40 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 38 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 6 + Map 9 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 8 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 9 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 10 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 8 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Reducer 12 + Reducer 10 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -661,7 +567,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -672,7 +578,7 @@ STAGE PLANS: 5 6 7 - Reducer 17 + Reducer 15 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -681,7 +587,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -692,7 +598,7 @@ STAGE PLANS: 5 6 7 - Reducer 22 + Reducer 20 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -701,7 +607,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -712,7 +618,7 @@ STAGE PLANS: 5 6 7 - Reducer 27 + Reducer 25 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -721,7 +627,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -732,7 +638,7 @@ STAGE PLANS: 5 6 7 - Reducer 32 + Reducer 30 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -741,7 +647,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -752,7 +658,7 @@ STAGE PLANS: 5 6 7 - Reducer 37 + Reducer 35 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -761,7 +667,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -772,7 +678,7 @@ STAGE PLANS: 5 6 7 - Reducer 7 + Reducer 40 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -781,7 +687,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -793,23 +699,23 @@ STAGE PLANS: 6 7 - Stage: Stage-10 + Stage: Stage-26 Spark #### A masked pattern was here #### Vertices: - Map 3 + Map 2 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -817,43 +723,73 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 4 + + Stage: Stage-25 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: household_demographics - filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 2 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 5 + + Stage: Stage-24 + Spark +#### A masked pattern was here #### + Vertices: + Map 3 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 1 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -861,64 +797,44 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 1) + Reducer 5 <- Map 4 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 4 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 3 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 4 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 5 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 3 + Statistics: Num rows: 1806751 Data size: 14454008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Reducer 2 + Reducer 5 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -927,7 +843,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -948,43 +864,43 @@ STAGE PLANS: 7 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 input vertices: - 1 Reducer 7 - 2 Reducer 12 - 3 Reducer 17 - 4 Reducer 22 - 5 Reducer 27 - 6 Reducer 32 - 7 Reducer 37 - Statistics: Num rows: 1 Data size: 65 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 10 + 2 Reducer 15 + 3 Reducer 20 + 4 Reducer 25 + 5 Reducer 30 + 6 Reducer 35 + 7 Reducer 40 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col7 (type: bigint), _col6 (type: bigint), _col5 (type: bigint), _col4 (type: bigint), _col3 (type: bigint), _col2 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 65 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 65 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-4 + Stage: Stage-8 Spark #### A masked pattern was here #### Vertices: - Map 13 + Map 12 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 11) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 11) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -992,64 +908,94 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 14 - Map Operator Tree: - TableScan - alias: household_demographics - filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 12 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 15 + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 13 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 11 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-5 + Stage: Stage-11 Spark #### A masked pattern was here #### Vertices: - Map 18 + Map 17 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 11) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 11) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1057,64 +1003,94 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 19 + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 Map Operator Tree: TableScan - alias: household_demographics - filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 17 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 20 + + Stage: Stage-9 + Spark +#### A masked pattern was here #### + Vertices: + Map 18 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 16 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-6 + Stage: Stage-14 Spark #### A masked pattern was here #### Vertices: - Map 23 + Map 22 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 10) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 10) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1122,64 +1098,94 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 24 + + Stage: Stage-13 + Spark +#### A masked pattern was here #### + Vertices: + Map 21 Map Operator Tree: TableScan - alias: household_demographics - filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 22 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 25 + + Stage: Stage-12 + Spark +#### A masked pattern was here #### + Vertices: + Map 23 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 21 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-7 + Stage: Stage-17 Spark #### A masked pattern was here #### Vertices: - Map 28 + Map 27 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 10) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 10) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1187,64 +1193,94 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 29 + + Stage: Stage-16 + Spark +#### A masked pattern was here #### + Vertices: + Map 26 Map Operator Tree: TableScan - alias: household_demographics - filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 27 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 30 + + Stage: Stage-15 + Spark +#### A masked pattern was here #### + Vertices: + Map 28 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 26 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-8 + Stage: Stage-20 Spark #### A masked pattern was here #### Vertices: - Map 33 + Map 32 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 9) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 9) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1252,64 +1288,94 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 34 + + Stage: Stage-19 + Spark +#### A masked pattern was here #### + Vertices: + Map 31 Map Operator Tree: TableScan - alias: household_demographics - filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 32 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 35 + + Stage: Stage-18 + Spark +#### A masked pattern was here #### + Vertices: + Map 33 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 31 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Stage: Stage-9 + Stage: Stage-23 Spark #### A masked pattern was here #### Vertices: - Map 38 + Map 37 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 9) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 9) and (t_minute < 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1317,43 +1383,73 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 39 + + Stage: Stage-22 + Spark +#### A masked pattern was here #### + Vertices: + Map 36 Map Operator Tree: TableScan - alias: household_demographics - filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 37 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 40 + + Stage: Stage-21 + Spark +#### A masked pattern was here #### + Vertices: + Map 38 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 86400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 1091 Data size: 13092 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 36 + Statistics: Num rows: 2460956 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work diff --git a/ql/src/test/results/clientpositive/perf/spark/query89.q.out b/ql/src/test/results/clientpositive/perf/spark/query89.q.out index 8f6da8f6ff..58bb03e02c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query89.q.out @@ -62,19 +62,59 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 9 + Map 5 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int), d_moy (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 652 Data size: 7824 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 6 + Map Operator Tree: + TableScan + alias: item + filterExpr: ((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 132132000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 13860 Data size: 3963960 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: i_item_sk (type: int), i_brand (type: string), i_class (type: string), i_category (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 13860 Data size: 3963960 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 7 Map Operator Tree: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1704 Data size: 311832 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -86,11 +126,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 442), Reducer 2 (PARTITION-LEVEL SORT, 442) - Reducer 4 <- Reducer 3 (GROUP, 529) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 265) - Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 2 <- Map 1 (GROUP, 245) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 245) + Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -98,112 +136,60 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 68313011672 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) - Execution mode: vectorized - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2000) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_moy (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) - Execution mode: vectorized - Map 8 - Map Operator Tree: - TableScan - alias: item - filterExpr: ((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_brand (type: string), i_class (type: string), i_category (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + Statistics: Num rows: 525329897 Data size: 62304061328 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col6 + input vertices: + 1 Map 5 + Statistics: Num rows: 187574154 Data size: 20516905936 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col6, _col8, _col9, _col10 + input vertices: + 1 Map 6 + Statistics: Num rows: 54163045 Data size: 19031254930 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col6, _col8, _col9, _col10, _col12, _col13 + input vertices: + 1 Map 7 + Statistics: Num rows: 54163045 Data size: 28604321253 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col3) + keys: _col6 (type: int), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col12 (type: string), _col13 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 54163045 Data size: 31252076965 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 54163045 Data size: 31252076965 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col6 (type: decimal(17,2)) Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col6 (type: int) - Reducer 3 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col6, _col8, _col9, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col3, _col6, _col8, _col9, _col10, _col12, _col13 - input vertices: - 1 Map 9 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3) - keys: _col6 (type: int), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col12 (type: string), _col13 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - sort order: ++++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col6 (type: decimal(17,2)) - Reducer 4 + Reducer 2 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -211,20 +197,20 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54163045 Data size: 31252076965 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++ Map-reduce partition columns: _col3 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54163045 Data size: 31252076965 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col6 (type: decimal(17,2)) - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54163045 Data size: 31252076965 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -244,37 +230,37 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54163045 Data size: 31252076965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)) outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54163045 Data size: 31252076965 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END (type: boolean) - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27081522 Data size: 18659168658 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col2 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col0 (type: int), _col6 (type: decimal(17,2)), avg_window_0 (type: decimal(21,6)), (_col6 - avg_window_0) (type: decimal(22,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27081522 Data size: 21692299122 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col8 (type: decimal(22,6)), _col3 (type: string) sort order: ++ - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27081522 Data size: 21692299122 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: decimal(17,2)), _col7 (type: decimal(21,6)) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: int), VALUE._col5 (type: decimal(17,2)), VALUE._col6 (type: decimal(21,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27081522 Data size: 21692299122 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 80100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query9.q.out b/ql/src/test/results/clientpositive/perf/spark/query9.q.out index a43450147e..234057f9aa 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query9.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query9.q.out @@ -142,22 +142,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 21 AND 40 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63809443588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 21 AND 40 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_ext_list_price (type: decimal(7,2)) outputColumnNames: ss_ext_list_price - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_ext_list_price), count(ss_ext_list_price) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 12 @@ -165,22 +165,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 21 AND 40 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63808191988 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 21 AND 40 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: decimal(7,2)) outputColumnNames: ss_net_paid_inc_tax - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_net_paid_inc_tax), count(ss_net_paid_inc_tax) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 14 @@ -188,20 +188,20 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 41 AND 60 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 2200320404 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 41 AND 60 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map 16 @@ -209,22 +209,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 41 AND 60 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63809443588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 41 AND 60 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_ext_list_price (type: decimal(7,2)) outputColumnNames: ss_ext_list_price - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_ext_list_price), count(ss_ext_list_price) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 18 @@ -232,22 +232,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 41 AND 60 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63808191988 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 41 AND 60 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: decimal(7,2)) outputColumnNames: ss_net_paid_inc_tax - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_net_paid_inc_tax), count(ss_net_paid_inc_tax) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 2 @@ -255,20 +255,20 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 2200320404 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191998545 Data size: 733440136 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191998545 Data size: 733440136 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map 20 @@ -276,20 +276,20 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 61 AND 80 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 2200320404 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 61 AND 80 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map 22 @@ -297,22 +297,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 61 AND 80 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63809443588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 61 AND 80 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_ext_list_price (type: decimal(7,2)) outputColumnNames: ss_ext_list_price - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_ext_list_price), count(ss_ext_list_price) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 24 @@ -320,22 +320,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 61 AND 80 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63808191988 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 61 AND 80 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: decimal(7,2)) outputColumnNames: ss_net_paid_inc_tax - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_net_paid_inc_tax), count(ss_net_paid_inc_tax) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 26 @@ -343,20 +343,20 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 81 AND 100 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 2200320404 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 81 AND 100 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map 28 @@ -364,22 +364,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 81 AND 100 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63809443588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 81 AND 100 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_ext_list_price (type: decimal(7,2)) outputColumnNames: ss_ext_list_price - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089938304 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_ext_list_price), count(ss_ext_list_price) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 30 @@ -387,22 +387,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 81 AND 100 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63808191988 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 81 AND 100 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: decimal(7,2)) outputColumnNames: ss_net_paid_inc_tax - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 7089799200 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_net_paid_inc_tax), count(ss_net_paid_inc_tax) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 4 @@ -410,22 +410,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63809443588 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191998545 Data size: 21269814568 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_ext_list_price (type: decimal(7,2)) outputColumnNames: ss_ext_list_price - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191998545 Data size: 21269814568 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_ext_list_price), count(ss_ext_list_price) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 6 @@ -433,22 +433,22 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 63808191988 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 1 AND 20 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191998545 Data size: 21269397368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_net_paid_inc_tax (type: decimal(7,2)) outputColumnNames: ss_net_paid_inc_tax - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191998545 Data size: 21269397368 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ss_net_paid_inc_tax), count(ss_net_paid_inc_tax) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint) Execution mode: vectorized Map 8 @@ -456,20 +456,20 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_quantity BETWEEN 21 AND 40 (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 2200320404 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_quantity BETWEEN 21 AND 40 (type: boolean) - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999515 Data size: 244480048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reducer 11 @@ -481,11 +481,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -499,11 +499,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -517,7 +517,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -531,11 +531,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -549,11 +549,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -567,7 +567,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -581,11 +581,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -599,11 +599,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -617,7 +617,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -631,11 +631,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -649,7 +649,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -663,11 +663,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -681,11 +681,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -699,11 +699,11 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(37,22)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -717,7 +717,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -732,12 +732,12 @@ STAGE PLANS: TableScan alias: reason filterExpr: (r_reason_sk = 1) (type: boolean) - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (r_reason_sk = 1) (type: boolean) - Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -747,7 +747,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Reducer 3 - Statistics: Num rows: 36 Data size: 7524 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -757,7 +757,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Reducer 5 - Statistics: Num rows: 36 Data size: 11880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -767,7 +767,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Reducer 7 - Statistics: Num rows: 36 Data size: 16236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -777,7 +777,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4 input vertices: 1 Reducer 9 - Statistics: Num rows: 36 Data size: 16560 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -787,7 +787,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5 input vertices: 1 Reducer 11 - Statistics: Num rows: 36 Data size: 20916 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -797,7 +797,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6 input vertices: 1 Reducer 13 - Statistics: Num rows: 36 Data size: 25272 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 928 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -807,7 +807,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7 input vertices: 1 Reducer 15 - Statistics: Num rows: 36 Data size: 25596 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 944 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -817,7 +817,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 input vertices: 1 Reducer 17 - Statistics: Num rows: 36 Data size: 29952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1168 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -827,7 +827,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 input vertices: 1 Reducer 19 - Statistics: Num rows: 36 Data size: 34308 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1392 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -837,7 +837,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 input vertices: 1 Reducer 21 - Statistics: Num rows: 36 Data size: 34632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1408 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -847,7 +847,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 input vertices: 1 Reducer 23 - Statistics: Num rows: 36 Data size: 38988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -857,7 +857,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 input vertices: 1 Reducer 25 - Statistics: Num rows: 36 Data size: 43344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1856 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -867,7 +867,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 input vertices: 1 Reducer 27 - Statistics: Num rows: 36 Data size: 43668 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1872 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -877,7 +877,7 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 input vertices: 1 Reducer 29 - Statistics: Num rows: 36 Data size: 48024 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2096 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -887,14 +887,14 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 input vertices: 1 Reducer 31 - Statistics: Num rows: 36 Data size: 52380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2320 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CASE WHEN ((_col1 > 409437L)) THEN (_col2) ELSE (_col3) END (type: decimal(37,22)), CASE WHEN ((_col4 > 4595804L)) THEN (_col5) ELSE (_col6) END (type: decimal(37,22)), CASE WHEN ((_col7 > 7887297L)) THEN (_col8) ELSE (_col9) END (type: decimal(37,22)), CASE WHEN ((_col10 > 10872978L)) THEN (_col11) ELSE (_col12) END (type: decimal(37,22)), CASE WHEN ((_col13 > 43571537L)) THEN (_col14) ELSE (_col15) END (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 36 Data size: 52380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 36 Data size: 52380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 1120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query90.q.out b/ql/src/test/results/clientpositive/perf/spark/query90.q.out index 9f78d64bfb..9c2bee94de 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query90.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query90.q.out @@ -58,14 +58,14 @@ STAGE PLANS: TableScan alias: time_dim filterExpr: (t_hour BETWEEN 14 AND 15 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 691200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t_hour BETWEEN 14 AND 15 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -78,14 +78,14 @@ STAGE PLANS: TableScan alias: household_demographics filterExpr: ((hd_dep_count = 8) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 57600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((hd_dep_count = 8) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 655 Data size: 5240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 655 Data size: 5240 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -98,14 +98,14 @@ STAGE PLANS: TableScan alias: web_page filterExpr: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 36560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 4064 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wp_web_page_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 4064 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -125,14 +125,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1727601692 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895111 Data size: 1726311332 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_time_sk (type: int), ws_ship_hdemo_sk (type: int), ws_web_page_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895111 Data size: 1726311332 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -142,7 +142,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 9 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15977923 Data size: 127536220 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -152,7 +152,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 10 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1775325 Data size: 6958172 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -161,15 +161,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 11 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 161506 Data size: 1292048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -183,7 +183,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 @@ -198,14 +198,14 @@ STAGE PLANS: TableScan alias: web_page filterExpr: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4602 Data size: 36560 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 4064 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wp_web_page_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 4064 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -218,14 +218,14 @@ STAGE PLANS: TableScan alias: time_dim filterExpr: (t_hour BETWEEN 6 AND 7 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 691200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (t_hour BETWEEN 6 AND 7 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 76800 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -238,14 +238,14 @@ STAGE PLANS: TableScan alias: household_demographics filterExpr: ((hd_dep_count = 8) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 57600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((hd_dep_count = 8) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 655 Data size: 5240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 655 Data size: 5240 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -266,14 +266,14 @@ STAGE PLANS: TableScan alias: web_sales filterExpr: (ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1727601692 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895111 Data size: 1726311332 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_time_sk (type: int), ws_ship_hdemo_sk (type: int), ws_web_page_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895111 Data size: 1726311332 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -283,7 +283,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 4 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15977923 Data size: 127536220 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -293,7 +293,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 5 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1775325 Data size: 6958172 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -302,15 +302,15 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 6 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 161506 Data size: 1292048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: @@ -324,7 +324,7 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -334,15 +334,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Reducer 8 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (CAST( _col0 AS decimal(15,4)) / CAST( _col1 AS decimal(15,4))) (type: decimal(35,20)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(35,20)) sort order: + - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized @@ -350,13 +350,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(35,20)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query91.q.out b/ql/src/test/results/clientpositive/perf/spark/query91.q.out index 78f85acd47..84ce9af482 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query91.q.out @@ -69,19 +69,19 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 13 + Map 12 Map Operator Tree: TableScan alias: household_demographics filterExpr: ((hd_buy_potential like '0-500%') and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7200 Data size: 691200 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((hd_buy_potential like '0-500%') and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 345600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 345600 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -94,19 +94,39 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 12 + Map 10 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1999) and (d_moy = 11) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 600 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Map 11 Map Operator Tree: TableScan alias: call_center filterExpr: cc_call_center_sk is not null (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 17880 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cc_call_center_sk is not null (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 17880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cc_call_center_sk (type: int), cc_call_center_id (type: string), cc_name (type: string), cc_manager (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 17880 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -118,11 +138,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 11 (PARTITION-LEVEL SORT, 25), Map 9 (PARTITION-LEVEL SORT, 25) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 541), Map 7 (PARTITION-LEVEL SORT, 541) - Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 750), Reducer 2 (PARTITION-LEVEL SORT, 750) - Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 680), Reducer 3 (PARTITION-LEVEL SORT, 680) - Reducer 5 <- Reducer 4 (GROUP, 787) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 10), Map 7 (PARTITION-LEVEL SORT, 10) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 11), Reducer 2 (PARTITION-LEVEL SORT, 11) + Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 3), Reducer 3 (PARTITION-LEVEL SORT, 3) + Reducer 5 <- Reducer 4 (GROUP, 2) Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -131,58 +150,39 @@ STAGE PLANS: TableScan alias: customer filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 80000000 Data size: 1257609520 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74500295 Data size: 1171153504 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_hdemo_sk (type: int), c_current_addr_sk (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74500295 Data size: 1171153504 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 74500295 Data size: 1171153504 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int) Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 1999) and (d_moy = 11) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized Map 7 Map Operator Tree: TableScan alias: customer_demographics filterExpr: ((cd_education_status) IN ('Unknown', 'Advanced Degree') and (cd_marital_status) IN ('M', 'W') and (struct(cd_marital_status,cd_education_status)) IN (const struct('M','Unknown'), const struct('W','Advanced Degree')) and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1861800 Data size: 340709400 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cd_education_status) IN ('Unknown', 'Advanced Degree') and (cd_marital_status) IN ('M', 'W') and (struct(cd_marital_status,cd_education_status)) IN (const struct('M','Unknown'), const struct('W','Advanced Degree')) and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59105 Data size: 10816215 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59105 Data size: 10816215 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59105 Data size: 10816215 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 8 @@ -190,68 +190,62 @@ STAGE PLANS: TableScan alias: customer_address filterExpr: ((ca_gmt_offset = -7) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 4505468064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_gmt_offset = -7) and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 901093680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8000000 Data size: 928000000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 9 Map Operator Tree: TableScan alias: catalog_returns filterExpr: (cr_call_center_sk is not null and cr_returned_date_sk is not null and cr_returning_customer_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28798881 Data size: 3501909064 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cr_call_center_sk is not null and cr_returned_date_sk is not null and cr_returning_customer_sk is not null) (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27658583 Data size: 3363250268 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cr_returned_date_sk (type: int), cr_returning_customer_sk (type: int), cr_call_center_sk (type: int), cr_net_loss (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Statistics: Num rows: 27658583 Data size: 3363250268 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + input vertices: + 1 Map 10 + Statistics: Num rows: 657590 Data size: 12496776 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col8, _col9, _col10 + input vertices: + 1 Map 11 + Statistics: Num rows: 657590 Data size: 205411228 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 657590 Data size: 205411228 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: decimal(7,2)), _col8 (type: string), _col9 (type: string), _col10 (type: string) Execution mode: vectorized - Reducer 10 Local Work: Map Reduce Local Work - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col8, _col9, _col10 - input vertices: - 1 Map 12 - Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col8 (type: string), _col9 (type: string), _col10 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -261,12 +255,12 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col3, _col5, _col6 - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2398543 Data size: 448527545 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: int) sort order: + Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2398543 Data size: 448527545 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int), _col5 (type: string), _col6 (type: string) Reducer 3 Reduce Operator Tree: @@ -277,12 +271,12 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2, _col5, _col6 - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 479709 Data size: 87786751 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 479709 Data size: 87786751 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col5 (type: string), _col6 (type: string) Reducer 4 Local Work: @@ -295,7 +289,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col2, _col5, _col6, _col12, _col17, _col18, _col19 - Statistics: Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20876 Data size: 9874464 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -304,19 +298,19 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col5, _col6, _col12, _col17, _col18, _col19 input vertices: - 1 Map 13 - Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE + 1 Map 12 + Statistics: Num rows: 10438 Data size: 4937286 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col12) keys: _col5 (type: string), _col6 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) - Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) Reducer 5 Execution mode: vectorized @@ -326,15 +320,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 585 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: decimal(17,2)) sort order: - - Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 6 Execution mode: vectorized @@ -342,10 +336,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 406 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 406 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query92.q.out b/ql/src/test/results/clientpositive/perf/spark/query92.q.out index 7895ebc7bd..c702123ff5 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query92.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query92.q.out @@ -57,29 +57,30 @@ order by sum(ws_ext_discount_amt) limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4 + Stage-1 depends on stages: Stage-2 + Stage-4 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 5 + Map 8 Map Operator Tree: TableScan - alias: date_dim - filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: item + filterExpr: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 3691396 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + predicate: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 669 Data size: 5348 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: d_date_sk (type: int) + expressions: i_item_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 669 Data size: 5352 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -88,23 +89,25 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-3 + Stage: Stage-2 Spark + Edges: + Reducer 6 <- Map 5 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 9 + Map 4 Map Operator Tree: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -112,30 +115,19 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 261), Reducer 8 (PARTITION-LEVEL SORT, 261) - Reducer 3 <- Reducer 2 (GROUP, 1) - Reducer 4 <- Reducer 3 (SORT, 1) - Reducer 7 <- Map 6 (GROUP, 169) - Reducer 8 <- Map 10 (PARTITION-LEVEL SORT, 87), Reducer 7 (PARTITION-LEVEL SORT, 87) -#### A masked pattern was here #### - Vertices: - Map 1 + Map 5 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 17276148644 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271853208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271853208 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -144,49 +136,73 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2 input vertices: - 1 Map 5 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) + 1 Map 7 + Statistics: Num rows: 15995224 Data size: 1851418688 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2), count(_col2) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 55608 Data size: 6895392 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 55608 Data size: 6895392 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 10 - Map Operator Tree: - TableScan - alias: item - filterExpr: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((i_manufact_id = 269) and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Reducer 6 Execution mode: vectorized - Map 6 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6951 Data size: 861924 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6951 Data size: 806316 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 8 + Statistics: Num rows: 97 Data size: 11252 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col2 (type: int) + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 1) + Reducer 3 <- Reducer 2 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan alias: web_sales filterExpr: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 17276148644 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271853208 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966864 Data size: 17271853208 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -195,118 +211,96 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col2 input vertices: - 1 Map 9 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), count(_col2) - keys: _col1 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) + 1 Map 4 + Statistics: Num rows: 15995224 Data size: 1851418688 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col2, _col6 + input vertices: + 1 Reducer 6 + Statistics: Num rows: 7434 Data size: 832720 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) (type: boolean) + Statistics: Num rows: 2478 Data size: 277648 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: decimal(7,2)) + outputColumnNames: _col2 + Statistics: Num rows: 2478 Data size: 277648 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col2) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(17,2)) Execution mode: vectorized Local Work: Map Reduce Local Work Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col2, _col6 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) (type: boolean) - Statistics: Num rows: 58081078 Data size: 7897346909 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: decimal(7,2)) - outputColumnNames: _col2 - Statistics: Num rows: 58081078 Data size: 7897346909 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(17,2)) - Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: decimal(17,2)) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: decimal(17,2)) sort order: + - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 4 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(17,2)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 7 + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(37,22)) - Reducer 8 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(37,22)) + Local Work: + Map Reduce Local Work Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query93.q.out b/ql/src/test/results/clientpositive/perf/spark/query93.q.out index 2b098a8d38..7559f5a7f2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query93.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query93.q.out @@ -47,14 +47,14 @@ STAGE PLANS: TableScan alias: reason filterExpr: ((r_reason_desc = 'Did not like the warranty') and r_reason_sk is not null) (type: boolean) - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 72 Data size: 7272 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((r_reason_desc = 'Did not like the warranty') and r_reason_sk is not null) (type: boolean) - Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: r_reason_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -66,8 +66,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 436), Map 6 (PARTITION-LEVEL SORT, 436) - Reducer 3 <- Reducer 2 (GROUP, 437) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 552), Map 6 (PARTITION-LEVEL SORT, 552) + Reducer 3 <- Reducer 2 (GROUP, 1) Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -76,14 +76,14 @@ STAGE PLANS: TableScan alias: store_returns filterExpr: (sr_reason_sk is not null and sr_item_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 57591150 Data size: 905325744 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (sr_item_sk is not null and sr_reason_sk is not null and sr_ticket_number is not null) (type: boolean) - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55574563 Data size: 873625248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sr_item_sk (type: int), sr_reason_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55574563 Data size: 873625248 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -93,12 +93,12 @@ STAGE PLANS: outputColumnNames: _col0, _col2, _col3 input vertices: 1 Map 5 - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1522298 Data size: 12178388 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col2 (type: int) - Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1522298 Data size: 12178388 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int) Execution mode: vectorized Local Work: @@ -108,19 +108,19 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70616997888 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70616997888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70616997888 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col2 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 70616997888 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) Execution mode: vectorized Reducer 2 @@ -132,22 +132,22 @@ STAGE PLANS: 0 _col0 (type: int), _col2 (type: int) 1 _col0 (type: int), _col2 (type: int) outputColumnNames: _col3, _col7, _col9, _col10 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15586502 Data size: 56256940 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col7 (type: int), CASE WHEN (_col3 is not null) THEN ((CAST( (_col9 - _col3) AS decimal(10,0)) * _col10)) ELSE ((CAST( _col9 AS decimal(10,0)) * _col10)) END (type: decimal(18,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15586502 Data size: 56256940 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38308 Data size: 4290500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38308 Data size: 4290500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(28,2)) Reducer 3 Execution mode: vectorized @@ -157,11 +157,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38308 Data size: 4290500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: decimal(28,2)), _col0 (type: int) sort order: ++ - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38308 Data size: 4290500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 4 Execution mode: vectorized @@ -169,13 +169,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: int), KEY.reducesinkkey0 (type: decimal(28,2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38308 Data size: 4290500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 11204 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 11204 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query94.q.out b/ql/src/test/results/clientpositive/perf/spark/query94.q.out index addde2a10d..1a0ac140d2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query94.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query94.q.out @@ -70,14 +70,14 @@ STAGE PLANS: TableScan alias: web_site filterExpr: ((web_company_name = 'pri') and web_site_sk is not null) (type: boolean) - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 7728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((web_company_name = 'pri') and web_site_sk is not null) (type: boolean) - Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: web_site_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -95,14 +95,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -114,11 +114,11 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 13 <- Map 12 (GROUP, 11) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 327), Map 9 (PARTITION-LEVEL SORT, 327) - Reducer 3 <- Map 11 (PARTITION-LEVEL SORT, 357), Reducer 2 (PARTITION-LEVEL SORT, 357) - Reducer 4 <- Reducer 13 (PARTITION-LEVEL SORT, 230), Reducer 3 (PARTITION-LEVEL SORT, 230) - Reducer 5 <- Reducer 4 (GROUP, 124) + Reducer 13 <- Map 12 (GROUP, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 31), Map 9 (PARTITION-LEVEL SORT, 31) + Reducer 3 <- Map 11 (PARTITION-LEVEL SORT, 19), Reducer 2 (PARTITION-LEVEL SORT, 19) + Reducer 4 <- Reducer 13 (PARTITION-LEVEL SORT, 10), Reducer 3 (PARTITION-LEVEL SORT, 10) + Reducer 5 <- Reducer 4 (GROUP, 1) Reducer 6 <- Reducer 5 (GROUP, 1) Reducer 7 <- Reducer 6 (SORT, 1) #### A masked pattern was here #### @@ -128,14 +128,14 @@ STAGE PLANS: TableScan alias: ws1 filterExpr: (ws_ship_date_sk is not null and ws_ship_addr_sk is not null and ws_web_site_sk is not null and ws_order_number is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 35132052668 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895019 Data size: 35105789768 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_ship_date_sk (type: int), ws_ship_addr_sk (type: int), ws_web_site_sk (type: int), ws_warehouse_sk (type: int), ws_order_number (type: int), ws_ext_ship_cost (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895019 Data size: 35105789768 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -145,12 +145,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6 input vertices: 1 Map 8 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15987241 Data size: 3832485980 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15987241 Data size: 3832485980 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized Local Work: @@ -160,24 +160,24 @@ STAGE PLANS: TableScan alias: ws2 filterExpr: (ws_order_number is not null and ws_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_order_number is not null and ws_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966743 Data size: 1151590284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_order_number (type: int), ws_warehouse_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966743 Data size: 1151590284 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966743 Data size: 1151590284 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143966743 Data size: 1151590284 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Map 12 @@ -185,39 +185,39 @@ STAGE PLANS: TableScan alias: wr1 filterExpr: wr_order_number is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 57593868 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wr_order_number is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 57593868 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: wr_order_number (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7199233 Data size: 28796932 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7199233 Data size: 28796932 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 9 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_state = 'TX') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_state = 'TX') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 13 Execution mode: vectorized @@ -226,16 +226,16 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 7199233 Data size: 662597045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7199233 Data size: 28796932 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7199233 Data size: 662597045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7199233 Data size: 57593864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 7199233 Data size: 662597045 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7199233 Data size: 57593864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reducer 2 Local Work: @@ -248,7 +248,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15673790 Data size: 3694706056 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -258,12 +258,12 @@ STAGE PLANS: outputColumnNames: _col3, _col4, _col5, _col6 input vertices: 1 Map 10 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1161142500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int) sort order: + Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1161142500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Reducer 3 Reduce Operator Tree: @@ -275,16 +275,16 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3, _col4, _col5, _col6, _col14 residual filter predicates: {(_col3 <> _col14)} - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1181090340 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) outputColumnNames: _col4, _col5, _col6 - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1161142500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int) sort order: + Map-reduce partition columns: _col4 (type: int) - Statistics: Num rows: 210834322 Data size: 28667370686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1161142500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Reducer 4 Reduce Operator Tree: @@ -295,25 +295,25 @@ STAGE PLANS: 0 _col4 (type: int) 1 _col0 (type: int) outputColumnNames: _col4, _col5, _col6, _col14 - Statistics: Num rows: 231917759 Data size: 31534108438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1161286088 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col14 is null (type: boolean) - Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) outputColumnNames: _col4, _col5, _col6 - Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col5), sum(_col6) keys: _col4 (type: int) mode: hash outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)) Reducer 5 Execution mode: vectorized @@ -323,15 +323,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 115958879 Data size: 15767054151 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), sum(_col1), sum(_col2) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Reducer 6 Execution mode: vectorized @@ -340,15 +340,15 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col0 (type: bigint) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Reducer 7 @@ -357,13 +357,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query95.q.out b/ql/src/test/results/clientpositive/perf/spark/query95.q.out index 69dcfabd52..ff292db873 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query95.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query95.q.out @@ -76,14 +76,14 @@ STAGE PLANS: TableScan alias: web_site filterExpr: ((web_company_name = 'pri') and web_site_sk is not null) (type: boolean) - Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 7728 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((web_company_name = 'pri') and web_site_sk is not null) (type: boolean) - Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: web_site_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -101,14 +101,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -120,14 +120,14 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 306), Map 13 (PARTITION-LEVEL SORT, 306) - Reducer 12 <- Reducer 11 (GROUP, 169) - Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 306), Map 18 (PARTITION-LEVEL SORT, 306) - Reducer 16 <- Map 19 (PARTITION-LEVEL SORT, 179), Reducer 15 (PARTITION-LEVEL SORT, 179) - Reducer 17 <- Reducer 16 (GROUP, 186) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 327), Map 8 (PARTITION-LEVEL SORT, 327) - Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 381), Reducer 17 (PARTITION-LEVEL SORT, 381), Reducer 2 (PARTITION-LEVEL SORT, 381) - Reducer 4 <- Reducer 3 (GROUP, 448) + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 18), Map 13 (PARTITION-LEVEL SORT, 18) + Reducer 12 <- Reducer 11 (GROUP, 45) + Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 18), Map 18 (PARTITION-LEVEL SORT, 18) + Reducer 16 <- Map 19 (PARTITION-LEVEL SORT, 75), Reducer 15 (PARTITION-LEVEL SORT, 75) + Reducer 17 <- Reducer 16 (GROUP, 6) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 30), Map 8 (PARTITION-LEVEL SORT, 30) + Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 10), Reducer 17 (PARTITION-LEVEL SORT, 10), Reducer 2 (PARTITION-LEVEL SORT, 10) + Reducer 4 <- Reducer 3 (GROUP, 5) Reducer 5 <- Reducer 4 (GROUP, 1) Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### @@ -137,14 +137,14 @@ STAGE PLANS: TableScan alias: ws1 filterExpr: (ws_order_number is not null and ws_ship_date_sk is not null and ws_ship_addr_sk is not null and ws_web_site_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 34556185692 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895019 Data size: 34530353280 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_ship_date_sk (type: int), ws_ship_addr_sk (type: int), ws_web_site_sk (type: int), ws_order_number (type: int), ws_ext_ship_cost (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 143895019 Data size: 34530353280 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -154,12 +154,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3, _col4, _col5 input vertices: 1 Map 7 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15987241 Data size: 3768680604 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15987241 Data size: 3768680604 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Execution mode: vectorized Local Work: @@ -169,19 +169,19 @@ STAGE PLANS: TableScan alias: ws1 filterExpr: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_warehouse_sk (type: int), ws_order_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Map 13 @@ -189,19 +189,19 @@ STAGE PLANS: TableScan alias: ws2 filterExpr: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_warehouse_sk (type: int), ws_order_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Map 14 @@ -209,19 +209,19 @@ STAGE PLANS: TableScan alias: ws1 filterExpr: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_warehouse_sk (type: int), ws_order_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Map 18 @@ -229,19 +229,19 @@ STAGE PLANS: TableScan alias: ws2 filterExpr: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ws_order_number is not null (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ws_warehouse_sk (type: int), ws_order_number (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 1151877648 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Map 19 @@ -249,38 +249,38 @@ STAGE PLANS: TableScan alias: web_returns filterExpr: wr_order_number is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 57593868 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: wr_order_number is not null (type: boolean) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 57593868 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: wr_order_number (type: int) outputColumnNames: _col13 - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3916383024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col13 (type: int) sort order: + Map-reduce partition columns: _col13 (type: int) - Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14398467 Data size: 3916383024 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 8 Map Operator Tree: TableScan alias: customer_address filterExpr: ((ca_state = 'TX') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40000000 Data size: 3600000000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((ca_state = 'TX') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ca_address_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 784314 Data size: 70588260 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reducer 11 Reduce Operator Tree: @@ -291,24 +291,24 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 16943002616 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 <> _col2) (type: boolean) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 16943002616 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 16943002616 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 5647763336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 5647763336 Basic stats: COMPLETE Column stats: COMPLETE Reducer 12 Execution mode: vectorized Reduce Operator Tree: @@ -316,12 +316,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14686712 Data size: 58746848 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14686712 Data size: 58746848 Basic stats: COMPLETE Column stats: COMPLETE Reducer 15 Reduce Operator Tree: Join Operator @@ -331,19 +331,19 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 16943002616 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 <> _col2) (type: boolean) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 16943002616 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 5647763336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1411940834 Data size: 5647763336 Basic stats: COMPLETE Column stats: COMPLETE Reducer 16 Reduce Operator Tree: Join Operator @@ -353,17 +353,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col13 (type: int) outputColumnNames: _col14 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1384229738 Data size: 5536918952 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col14 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 176175692 Data size: 704702768 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 176175692 Data size: 704702768 Basic stats: COMPLETE Column stats: COMPLETE Reducer 17 Execution mode: vectorized Reduce Operator Tree: @@ -371,12 +371,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8007986 Data size: 32031944 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8007986 Data size: 32031944 Basic stats: COMPLETE Column stats: COMPLETE Reducer 2 Local Work: Map Reduce Local Work @@ -388,7 +388,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15673790 Data size: 3632154484 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -398,12 +398,12 @@ STAGE PLANS: outputColumnNames: _col3, _col4, _col5 input vertices: 1 Map 9 - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1141194588 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: int) sort order: + Map-reduce partition columns: _col3 (type: int) - Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1141194588 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 3 Reduce Operator Tree: @@ -416,18 +416,18 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col3, _col4, _col5 - Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5022875 Data size: 1141194588 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col5) keys: _col3 (type: int) mode: hash outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2511437 Data size: 572607636 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2511437 Data size: 572607636 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)) Reducer 4 Execution mode: vectorized @@ -437,15 +437,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2511437 Data size: 572607636 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), sum(_col1), sum(_col2) mode: partial2 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Reducer 5 Execution mode: vectorized @@ -454,15 +454,15 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col0 (type: bigint) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)) Reducer 6 @@ -471,13 +471,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query96.q.out b/ql/src/test/results/clientpositive/perf/spark/query96.q.out index ba41c765ea..7457bf14e7 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query96.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query96.q.out @@ -29,28 +29,30 @@ order by count(*) limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-3 Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-4 Spark #### A masked pattern was here #### Vertices: - Map 4 + Map 2 Map Operator Tree: TableScan alias: time_dim filterExpr: ((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86400 Data size: 1036800 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1515 Data size: 18180 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -58,43 +60,73 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 5 + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: household_demographics - filterExpr: ((hd_dep_count = 5) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 6600966584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((hd_dep_count = 5) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hd_demo_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 501695814 Data size: 5749483336 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 2 + Statistics: Num rows: 16240953 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 6 + + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 3 Map Operator Tree: TableScan - alias: store - filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + filterExpr: ((hd_dep_count = 5) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 57600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((hd_dep_count = 5) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 655 Data size: 5240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator + Statistics: Num rows: 655 Data size: 5240 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 1 + Statistics: Num rows: 1477476 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -102,94 +134,74 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 1) - Reducer 3 <- Reducer 2 (SORT, 1) + Reducer 5 <- Map 4 (GROUP, 1) + Reducer 6 <- Reducer 5 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 4 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: store + filterExpr: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 156768 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 155 Data size: 14260 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 155 Data size: 14105 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 input vertices: - 1 Map 4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - input vertices: - 1 Map 5 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 6 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + 0 Map 3 + Statistics: Num rows: 1084713 Data size: 8677704 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized Local Work: Map Reduce Local Work - Reducer 2 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 - Reducer 3 + Reducer 6 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query97.q.out b/ql/src/test/results/clientpositive/perf/spark/query97.q.out index c4f4804452..9b752cc8ac 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query97.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query97.q.out @@ -62,14 +62,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -87,14 +87,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -106,10 +106,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 437) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 386), Reducer 7 (PARTITION-LEVEL SORT, 386) + Reducer 2 <- Map 1 (GROUP, 4) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 5), Reducer 7 (PARTITION-LEVEL SORT, 5) Reducer 4 <- Reducer 3 (GROUP, 1) - Reducer 7 <- Map 6 (GROUP, 336) + Reducer 7 <- Map 6 (GROUP, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -117,14 +117,14 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: ss_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 6704610012 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ss_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550076554 Data size: 6402910972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550076554 Data size: 6402910972 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -134,17 +134,17 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 389926812 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col2 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 389926812 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 389926812 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -153,14 +153,14 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 3444361236 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cs_sold_date_sk is not null (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 3427137516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_item_sk (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 286549727 Data size: 3427137516 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -170,17 +170,17 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 8 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31836679 Data size: 248965852 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: int), _col2 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31836679 Data size: 248965852 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31836679 Data size: 248965852 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Local Work: Map Reduce Local Work @@ -191,12 +191,12 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 389926812 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 389926812 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Reduce Operator Tree: Join Operator @@ -206,19 +206,19 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: int) 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12370931353 Data size: 98961723244 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CASE WHEN ((_col0 is not null and _col2 is null)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((_col0 is null and _col2 is not null)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((_col0 is not null and _col2 is not null)) THEN (1) ELSE (0) END (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12370931353 Data size: 98961723244 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint) Reducer 4 @@ -228,13 +228,13 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -246,12 +246,12 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31836679 Data size: 248965852 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31836679 Data size: 248965852 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/spark/query98.q.out b/ql/src/test/results/clientpositive/perf/spark/query98.q.out index f1d7caa38b..dcaf40b320 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query98.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query98.q.out @@ -75,14 +75,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 7158802 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 795368 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -94,9 +94,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 442), Map 7 (PARTITION-LEVEL SORT, 442) - Reducer 3 <- Reducer 2 (GROUP, 481) - Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 241) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 35), Map 7 (PARTITION-LEVEL SORT, 35) + Reducer 3 <- Reducer 2 (GROUP, 99) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 99) Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -105,14 +105,14 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 66112867736 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550076554 Data size: 63137871608 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -122,12 +122,12 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 6 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 4317086488 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61115434 Data size: 4317086488 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: decimal(7,2)) Execution mode: vectorized Local Work: @@ -137,19 +137,19 @@ STAGE PLANS: TableScan alias: item filterExpr: ((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 462000 Data size: 268753408 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string), i_current_price (type: decimal(7,2)), i_class (type: string), i_category (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 138600 Data size: 80626112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)), _col4 (type: string), _col5 (type: string) Execution mode: vectorized Reducer 2 @@ -161,18 +161,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 10597377742 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2) keys: _col10 (type: string), _col9 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12650856302 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) sort order: +++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12650856302 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: decimal(17,2)) Reducer 3 Execution mode: vectorized @@ -182,12 +182,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12650856302 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12650856302 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)) Reducer 4 Execution mode: vectorized @@ -195,7 +195,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: decimal(7,2)), VALUE._col4 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12650856302 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -215,15 +215,15 @@ STAGE PLANS: name: sum window function: GenericUDAFSumHiveDecimal window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12650856302 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: decimal(7,2)), _col5 (type: decimal(17,2)), ((_col5 * 100) / sum_window_0) (type: decimal(38,17)), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 14704295774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string), _col6 (type: string), _col0 (type: string), _col5 (type: decimal(38,17)) sort order: +++++ - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 14704295774 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: decimal(7,2)), _col4 (type: decimal(17,2)) Reducer 5 Execution mode: vectorized @@ -231,10 +231,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: decimal(7,2)), VALUE._col1 (type: decimal(17,2)), KEY.reducesinkkey4 (type: decimal(38,17)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12870832674 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18334631 Data size: 12870832674 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/spark/query99.q.out b/ql/src/test/results/clientpositive/perf/spark/query99.q.out index f541da81a6..5fcecb51a2 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query99.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query99.q.out @@ -81,14 +81,14 @@ STAGE PLANS: TableScan alias: date_dim filterExpr: (d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 584392 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 64928 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col1 (type: int) @@ -101,14 +101,14 @@ STAGE PLANS: TableScan alias: call_center filterExpr: cc_call_center_sk is not null (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cc_call_center_sk is not null (type: boolean) - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cc_call_center_sk (type: int), cc_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6120 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col2 (type: int) @@ -121,14 +121,14 @@ STAGE PLANS: TableScan alias: warehouse filterExpr: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col4 (type: int) @@ -141,14 +141,14 @@ STAGE PLANS: TableScan alias: ship_mode filterExpr: sm_ship_mode_sk is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: sm_ship_mode_sk is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sm_ship_mode_sk (type: int), sm_type (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Spark HashTable Sink Operator keys: 0 _col3 (type: int) @@ -160,7 +160,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (GROUP, 447) + Reducer 2 <- Map 1 (GROUP, 25) Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -169,14 +169,14 @@ STAGE PLANS: TableScan alias: catalog_sales filterExpr: (cs_warehouse_sk is not null and cs_ship_mode_sk is not null and cs_call_center_sk is not null and cs_ship_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 5730999696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 282273729 Data size: 5617249132 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cs_sold_date_sk (type: int), cs_ship_date_sk (type: int), cs_call_center_sk (type: int), cs_ship_mode_sk (type: int), cs_warehouse_sk (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 282273729 Data size: 5617249132 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -186,7 +186,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 input vertices: 1 Map 4 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31361601 Data size: 599006572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -196,7 +196,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3, _col4, _col8 input vertices: 1 Map 5 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31361601 Data size: 3552638590 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -206,7 +206,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3, _col8, _col10 input vertices: 1 Map 6 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 31361601 Data size: 6569002334 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -216,22 +216,22 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col8, _col10, _col12 input vertices: 1 Map 7 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 15680800 Data size: 4536140792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(_col10, 1, 20) (type: string), _col12 (type: string), _col8 (type: string), CASE WHEN (((_col1 - _col0) <= 30)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 30) and ((_col1 - _col0) <= 60))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 60) and ((_col1 - _col0) <= 90))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 90) and ((_col1 - _col0) <= 120))) THEN (1) ELSE (0) END (type: int), CASE WHEN (((_col1 - _col0) > 120)) THEN (1) ELSE (0) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 15680800 Data size: 4536140792 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 7840400 Data size: 3183202400 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 7840400 Data size: 3183202400 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) Execution mode: vectorized @@ -245,15 +245,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3920200 Data size: 1591601200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col0 (type: string) outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3920200 Data size: 2312918000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col8 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3920200 Data size: 2312918000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) Reducer 3 @@ -262,13 +262,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3920200 Data size: 2312918000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 59000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 100 Data size: 59000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/perf/tez/query1.q.out b/ql/src/test/results/clientpositive/perf/tez/query1.q.out index 58c422d556..8e46e1e348 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query1.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query1.q.out @@ -64,102 +64,102 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_161] - Limit [LIM_160] (rows=100 width=860) + Limit [LIM_160] (rows=100 width=100) Number of rows:100 - Select Operator [SEL_159] (rows=32266667 width=860) + Select Operator [SEL_159] (rows=816091 width=100) Output:["_col0"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_50] - Select Operator [SEL_49] (rows=32266667 width=860) + Select Operator [SEL_49] (rows=816091 width=100) Output:["_col0"] - Filter Operator [FIL_48] (rows=32266667 width=860) + Filter Operator [FIL_48] (rows=816091 width=324) predicate:(_col2 > _col7) - Merge Join Operator [MERGEJOIN_134] (rows=96800003 width=860) + Merge Join Operator [MERGEJOIN_134] (rows=2448274 width=324) Conds:RS_45._col1=RS_158._col1(Inner),Output:["_col2","_col6","_col7"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_132] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_132] (rows=2369298 width=213) Conds:RS_42._col0=RS_153._col0(Inner),Output:["_col1","_col2","_col6"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] PartitionCols:_col0 - Select Operator [SEL_152] (rows=80000000 width=860) + Select Operator [SEL_152] (rows=80000000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_151] (rows=80000000 width=860) + Filter Operator [FIL_151] (rows=80000000 width=104) predicate:c_customer_sk is not null - TableScan [TS_17] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id"] + TableScan [TS_17] (rows=80000000 width=104) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_131] (rows=34842647 width=77) + Merge Join Operator [MERGEJOIN_131] (rows=2369298 width=114) Conds:RS_147._col1=RS_150._col0(Inner),Output:["_col0","_col1","_col2"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_150] PartitionCols:_col0 - Select Operator [SEL_149] (rows=852 width=1910) + Select Operator [SEL_149] (rows=35 width=90) Output:["_col0"] - Filter Operator [FIL_148] (rows=852 width=1910) + Filter Operator [FIL_148] (rows=35 width=90) predicate:((s_state = 'NM') and s_store_sk is not null) - TableScan [TS_14] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] + TableScan [TS_14] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_147] PartitionCols:_col1 - Select Operator [SEL_146] (rows=31675133 width=77) + Select Operator [SEL_146] (rows=14291868 width=119) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_145] (rows=31675133 width=77) + Group By Operator [GBY_145] (rows=14291868 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_11] PartitionCols:_col0, _col1 - Group By Operator [GBY_10] (rows=63350266 width=77) + Group By Operator [GBY_10] (rows=16855704 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_130] (rows=63350266 width=77) + Merge Join Operator [MERGEJOIN_130] (rows=16855704 width=107) Conds:RS_139._col0=RS_143._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_139] PartitionCols:_col0 - Select Operator [SEL_137] (rows=57591150 width=77) + Select Operator [SEL_137] (rows=51757026 width=119) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_135] (rows=57591150 width=77) + Filter Operator [FIL_135] (rows=51757026 width=119) predicate:(sr_customer_sk is not null and sr_returned_date_sk is not null and sr_store_sk is not null) - TableScan [TS_0] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"] + TableScan [TS_0] (rows=57591150 width=119) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_customer_sk","sr_store_sk","sr_fee"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_143] PartitionCols:_col0 - Select Operator [SEL_142] (rows=36524 width=1119) + Select Operator [SEL_142] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_141] (rows=36524 width=1119) + Filter Operator [FIL_141] (rows=652 width=8) predicate:((d_year = 2000) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_158] PartitionCols:_col1 - Select Operator [SEL_157] (rows=15837566 width=77) + Select Operator [SEL_157] (rows=31 width=115) Output:["_col0","_col1"] - Group By Operator [GBY_156] (rows=15837566 width=77) + Group By Operator [GBY_156] (rows=31 width=123) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Select Operator [SEL_155] (rows=31675133 width=77) + Select Operator [SEL_155] (rows=14291868 width=119) Output:["_col1","_col2"] - Group By Operator [GBY_154] (rows=31675133 width=77) + Group By Operator [GBY_154] (rows=14291868 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col0 - Group By Operator [GBY_30] (rows=63350266 width=77) + Group By Operator [GBY_30] (rows=17467258 width=119) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_133] (rows=63350266 width=77) + Merge Join Operator [MERGEJOIN_133] (rows=17467258 width=107) Conds:RS_140._col0=RS_144._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_140] PartitionCols:_col0 - Select Operator [SEL_138] (rows=57591150 width=77) + Select Operator [SEL_138] (rows=53634860 width=119) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_136] (rows=57591150 width=77) + Filter Operator [FIL_136] (rows=53634860 width=119) predicate:(sr_returned_date_sk is not null and sr_store_sk is not null) Please refer to the previous TableScan [TS_0] <-Map 10 [SIMPLE_EDGE] vectorized diff --git a/ql/src/test/results/clientpositive/perf/tez/query10.q.out b/ql/src/test/results/clientpositive/perf/tez/query10.q.out index 5b55d44d91..2bcc8ab360 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query10.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query10.q.out @@ -117,20 +117,21 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 10 <- Reducer 13 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Map 20 <- Reducer 16 (BROADCAST_EDGE) -Map 21 <- Reducer 19 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 12 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (SIMPLE_EDGE) -Reducer 16 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 12 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 18 <- Reducer 17 (SIMPLE_EDGE) -Reducer 19 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Map 10 <- Reducer 14 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Map 21 <- Reducer 12 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Map 22 <- Reducer 12 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 13 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (SIMPLE_EDGE) +Reducer 17 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 13 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) +Reducer 19 <- Reducer 18 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 20 <- Map 13 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 15 (ONE_TO_ONE_EDGE), Reducer 18 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 16 (ONE_TO_ONE_EDGE), Reducer 19 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) @@ -140,190 +141,210 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_225] - Limit [LIM_224] (rows=100 width=88) + File Output Operator [FS_230] + Limit [LIM_229] (rows=1 width=419) Number of rows:100 - Select Operator [SEL_223] (rows=1045432122 width=88) + Select Operator [SEL_228] (rows=1 width=419) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_222] - Select Operator [SEL_221] (rows=1045432122 width=88) + SHUFFLE [RS_227] + Select Operator [SEL_226] (rows=1 width=419) Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col8","_col10","_col12"] - Group By Operator [GBY_220] (rows=1045432122 width=88) + Group By Operator [GBY_225] (rows=1 width=379) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Group By Operator [GBY_62] (rows=2090864244 width=88) + Group By Operator [GBY_62] (rows=1 width=379) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Top N Key Operator [TNK_103] (rows=2090864244 width=88) + Top N Key Operator [TNK_103] (rows=2771 width=379) keys:_col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13,sort order:++++++++,top n:100 - Select Operator [SEL_61] (rows=2090864244 width=88) + Select Operator [SEL_61] (rows=2771 width=379) Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Filter Operator [FIL_60] (rows=2090864244 width=88) + Filter Operator [FIL_60] (rows=2771 width=379) predicate:(_col15 is not null or _col17 is not null) - Merge Join Operator [MERGEJOIN_173] (rows=2090864244 width=88) - Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_211._col0(Left Outer),RS_55._col0=RS_219._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15","_col17"] - <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_55] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_169] (rows=96800003 width=860) - Conds:RS_50._col1=RS_182._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_182] - PartitionCols:_col0 - Select Operator [SEL_181] (rows=1861800 width=385) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_180] (rows=1861800 width=385) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_50] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_168] (rows=88000001 width=860) - Conds:RS_176._col2=RS_179._col0(Inner),Output:["_col0","_col1"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_176] - PartitionCols:_col2 - Select Operator [SEL_175] (rows=80000000 width=860) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_174] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_179] - PartitionCols:_col0 - Select Operator [SEL_178] (rows=40000000 width=1014) - Output:["_col0"] - Filter Operator [FIL_177] (rows=40000000 width=1014) - predicate:((ca_county) IN ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + Merge Join Operator [MERGEJOIN_173] (rows=2771 width=379) + Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_216._col0(Left Outer),RS_55._col0=RS_224._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15","_col17"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0 - Group By Operator [GBY_54] (rows=633595212 width=88) + Group By Operator [GBY_54] (rows=55819 width=0) Output:["_col0"],keys:_col0 - Select Operator [SEL_18] (rows=633595212 width=88) + Select Operator [SEL_18] (rows=20713610 width=0) Output:["_col0"] - Merge Join Operator [MERGEJOIN_170] (rows=633595212 width=88) - Conds:RS_203._col0=RS_185._col0(Inner),Output:["_col1"] - <-Map 12 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_170] (rows=20713610 width=0) + Conds:RS_205._col0=RS_185._col0(Inner),Output:["_col1"] + <-Map 13 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_185] PartitionCols:_col0 - Select Operator [SEL_184] (rows=4058 width=1119) + Select Operator [SEL_184] (rows=72 width=12) Output:["_col0"] - Filter Operator [FIL_183] (rows=4058 width=1119) + Filter Operator [FIL_183] (rows=72 width=12) predicate:((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) - TableScan [TS_12] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_12] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_203] + SHUFFLE [RS_205] PartitionCols:_col0 - Select Operator [SEL_202] (rows=575995635 width=88) + Select Operator [SEL_204] (rows=525327388 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_201] (rows=575995635 width=88) + Filter Operator [FIL_203] (rows=525327388 width=7) predicate:((ss_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_9] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] - <-Reducer 13 [BROADCAST_EDGE] vectorized + TableScan [TS_9] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_200] + Group By Operator [GBY_199] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3647763)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_136] + Group By Operator [GBY_135] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=3647763)"] + Select Operator [SEL_134] (rows=3914656 width=4) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_169] (rows=3914656 width=375) + Conds:RS_50._col1=RS_182._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_182] + PartitionCols:_col0 + Select Operator [SEL_181] (rows=1861800 width=375) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Filter Operator [FIL_180] (rows=1861800 width=375) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=375) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_168] (rows=3860070 width=5) + Conds:RS_176._col2=RS_179._col0(Inner),Output:["_col0","_col1"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_176] + PartitionCols:_col2 + Select Operator [SEL_175] (rows=77201384 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_174] (rows=77201384 width=11) + predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=11) + default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_179] + PartitionCols:_col0 + Select Operator [SEL_178] (rows=2000000 width=102) + Output:["_col0"] + Filter Operator [FIL_177] (rows=2000000 width=102) + predicate:((ca_county) IN ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County') and ca_address_sk is not null) + TableScan [TS_3] (rows=40000000 width=102) + default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county"] + <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_198] Group By Operator [GBY_197] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_194] Group By Operator [GBY_191] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_186] (rows=4058 width=1119) + Select Operator [SEL_186] (rows=72 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_184] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_200] - Group By Operator [GBY_199] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=96800000)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_136] - Group By Operator [GBY_135] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"] - Select Operator [SEL_134] (rows=96800003 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_169] - <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_211] + <-Reducer 3 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_55] PartitionCols:_col0 - Select Operator [SEL_210] (rows=79201469 width=135) + Please refer to the previous Merge Join Operator [MERGEJOIN_169] + <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_216] + PartitionCols:_col0 + Select Operator [SEL_215] (rows=55819 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_209] (rows=79201469 width=135) + Group By Operator [GBY_214] (rows=55819 width=3) Output:["_col0"],keys:KEY._col0 - <-Reducer 14 [SIMPLE_EDGE] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Group By Operator [GBY_29] (rows=158402938 width=135) + Group By Operator [GBY_29] (rows=55819 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_171] (rows=158402938 width=135) - Conds:RS_208._col0=RS_187._col0(Inner),Output:["_col1"] - <-Map 12 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_171] (rows=5675186 width=3) + Conds:RS_213._col0=RS_187._col0(Inner),Output:["_col1"] + <-Map 13 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_187] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_184] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_208] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_213] PartitionCols:_col0 - Select Operator [SEL_207] (rows=144002668 width=135) + Select Operator [SEL_212] (rows=143930993 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_206] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_19] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_205] - Group By Operator [GBY_204] (rows=1 width=12) + Filter Operator [FIL_211] (rows=143930993 width=7) + predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (ws_bill_customer_sk BETWEEN DynamicValue(RS_56_store_sales_ss_customer_sk_min) AND DynamicValue(RS_56_store_sales_ss_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_56_store_sales_ss_customer_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_19] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_201] + Please refer to the previous Group By Operator [GBY_199] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_209] + Group By Operator [GBY_208] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_116] + Group By Operator [GBY_115] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_114] (rows=55819 width=0) + Output:["_col0"] + Please refer to the previous Group By Operator [GBY_54] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_207] + Group By Operator [GBY_206] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_195] Group By Operator [GBY_192] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_188] (rows=4058 width=1119) + Select Operator [SEL_188] (rows=72 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_184] - <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_219] + <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_224] PartitionCols:_col0 - Select Operator [SEL_218] (rows=158394413 width=135) + Select Operator [SEL_223] (rows=55425 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_217] (rows=158394413 width=135) + Group By Operator [GBY_222] (rows=55425 width=3) Output:["_col0"],keys:KEY._col0 - <-Reducer 17 [SIMPLE_EDGE] + <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 - Group By Operator [GBY_43] (rows=316788826 width=135) + Group By Operator [GBY_43] (rows=55425 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_172] (rows=316788826 width=135) - Conds:RS_216._col0=RS_189._col0(Inner),Output:["_col1"] - <-Map 12 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_172] (rows=11162598 width=3) + Conds:RS_221._col0=RS_189._col0(Inner),Output:["_col1"] + <-Map 13 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_189] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_184] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_215] (rows=287989836 width=135) + Select Operator [SEL_220] (rows=285115246 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_214] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_33] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_213] - Group By Operator [GBY_212] (rows=1 width=12) + Filter Operator [FIL_219] (rows=285115246 width=7) + predicate:((cs_ship_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (cs_ship_customer_sk BETWEEN DynamicValue(RS_56_store_sales_ss_customer_sk_min) AND DynamicValue(RS_56_store_sales_ss_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_56_store_sales_ss_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_33] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_202] + Please refer to the previous Group By Operator [GBY_199] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_210] + Please refer to the previous Group By Operator [GBY_208] + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_218] + Group By Operator [GBY_217] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_196] Group By Operator [GBY_193] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_190] (rows=4058 width=1119) + Select Operator [SEL_190] (rows=72 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_184] diff --git a/ql/src/test/results/clientpositive/perf/tez/query11.q.out b/ql/src/test/results/clientpositive/perf/tez/query11.q.out index 4dfd2933ba..06df50ee56 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query11.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query11.q.out @@ -151,8 +151,8 @@ Plan optimized by CBO. Vertex dependency in root stage Map 1 <- Reducer 21 (BROADCAST_EDGE) Map 11 <- Reducer 23 (BROADCAST_EDGE) -Map 15 <- Reducer 20 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE) -Map 7 <- Reducer 22 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE) +Map 15 <- Reducer 20 (BROADCAST_EDGE) +Map 7 <- Reducer 22 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) @@ -165,8 +165,6 @@ Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 21 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 22 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 23 <- Map 19 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 24 (CUSTOM_SIMPLE_EDGE) -Reducer 26 <- Map 24 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 24 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 10 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) @@ -179,165 +177,154 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_360] - Limit [LIM_359] (rows=100 width=88) + File Output Operator [FS_350] + Limit [LIM_349] (rows=100 width=85) Number of rows:100 - Select Operator [SEL_358] (rows=574987679 width=88) + Select Operator [SEL_348] (rows=93786629 width=85) Output:["_col0"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_93] - Select Operator [SEL_92] (rows=574987679 width=88) + Select Operator [SEL_92] (rows=93786629 width=85) Output:["_col0"] - Filter Operator [FIL_91] (rows=574987679 width=88) + Filter Operator [FIL_91] (rows=93786629 width=533) predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col8 / _col3))) ELSE ((null > (_col8 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END - Merge Join Operator [MERGEJOIN_283] (rows=1149975359 width=88) - Conds:RS_325._col0=RS_337._col0(Inner),RS_337._col0=RS_347._col0(Inner),RS_337._col0=RS_357._col0(Inner),Output:["_col1","_col3","_col5","_col7","_col8"] + Merge Join Operator [MERGEJOIN_283] (rows=187573258 width=533) + Conds:RS_319._col0=RS_329._col0(Inner),RS_329._col0=RS_339._col0(Inner),RS_329._col0=RS_347._col0(Inner),Output:["_col1","_col3","_col5","_col7","_col8"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_337] + SHUFFLE [RS_329] PartitionCols:_col0 - Select Operator [SEL_336] (rows=116159124 width=88) + Select Operator [SEL_328] (rows=62524419 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_335] (rows=116159124 width=88) + Filter Operator [FIL_327] (rows=62524419 width=212) predicate:(_col7 > 0) - Select Operator [SEL_334] (rows=348477374 width=88) + Select Operator [SEL_326] (rows=187573258 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_333] (rows=348477374 width=88) + Group By Operator [GBY_325] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_38] (rows=696954748 width=88) + Group By Operator [GBY_38] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_36] (rows=696954748 width=88) + Select Operator [SEL_36] (rows=187573258 width=847) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_278] (rows=696954748 width=88) - Conds:RS_33._col1=RS_316._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + Merge Join Operator [MERGEJOIN_278] (rows=187573258 width=847) + Conds:RS_33._col1=RS_315._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_316] + SHUFFLE [RS_315] PartitionCols:_col0 - Select Operator [SEL_312] (rows=80000000 width=860) + Select Operator [SEL_312] (rows=80000000 width=656) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_311] (rows=80000000 width=860) + Filter Operator [FIL_311] (rows=80000000 width=656) predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_71] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] + TableScan [TS_71] (rows=80000000 width=656) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_277] (rows=633595212 width=88) - Conds:RS_332._col0=RS_294._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_277] (rows=187573258 width=199) + Conds:RS_324._col0=RS_294._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_294] PartitionCols:_col0 - Select Operator [SEL_288] (rows=36524 width=1119) + Select Operator [SEL_288] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_285] (rows=36524 width=1119) + Filter Operator [FIL_285] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_68] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_68] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_332] + SHUFFLE [RS_324] PartitionCols:_col0 - Select Operator [SEL_331] (rows=575995635 width=88) + Select Operator [SEL_323] (rows=525327388 width=221) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_330] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_34_customer_c_customer_sk_min) AND DynamicValue(RS_34_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_34_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_21] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] + Filter Operator [FIL_322] (rows=525327388 width=221) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_21] (rows=575995635 width=221) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_327] - Group By Operator [GBY_326] (rows=1 width=12) + BROADCAST [RS_321] + Group By Operator [GBY_320] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_304] Group By Operator [GBY_300] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_295] (rows=36524 width=1119) + Select Operator [SEL_295] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_288] - <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_329] - Group By Operator [GBY_328] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_322] - Group By Operator [GBY_320] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_317] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_312] <-Reducer 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_347] + SHUFFLE [RS_339] PartitionCols:_col0 - Select Operator [SEL_346] (rows=29040539 width=135) + Select Operator [SEL_338] (rows=17130654 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_345] (rows=29040539 width=135) + Filter Operator [FIL_337] (rows=17130654 width=212) predicate:(_col7 > 0) - Select Operator [SEL_344] (rows=87121617 width=135) + Select Operator [SEL_336] (rows=51391963 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_343] (rows=87121617 width=135) + Group By Operator [GBY_335] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_61] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_60] (rows=174243235 width=135) + Group By Operator [GBY_60] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_58] (rows=174243235 width=135) + Select Operator [SEL_58] (rows=51391963 width=875) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_280] (rows=174243235 width=135) - Conds:RS_55._col1=RS_318._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + Merge Join Operator [MERGEJOIN_280] (rows=51391963 width=875) + Conds:RS_55._col1=RS_316._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] + SHUFFLE [RS_316] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_312] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_279] (rows=158402938 width=135) - Conds:RS_342._col0=RS_296._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_279] (rows=51391963 width=227) + Conds:RS_334._col0=RS_296._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_296] PartitionCols:_col0 - Select Operator [SEL_289] (rows=36524 width=1119) + Select Operator [SEL_289] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_286] (rows=36524 width=1119) + Filter Operator [FIL_286] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) Please refer to the previous TableScan [TS_68] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_342] + SHUFFLE [RS_334] PartitionCols:_col0 - Select Operator [SEL_341] (rows=144002668 width=135) + Select Operator [SEL_333] (rows=143930993 width=231) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_340] (rows=144002668 width=135) + Filter Operator [FIL_332] (rows=143930993 width=231) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_53_date_dim_d_date_sk_min) AND DynamicValue(RS_53_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_53_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_43] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] + TableScan [TS_43] (rows=144002668 width=231) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_339] - Group By Operator [GBY_338] (rows=1 width=12) + BROADCAST [RS_331] + Group By Operator [GBY_330] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_305] Group By Operator [GBY_301] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_297] (rows=36524 width=1119) + Select Operator [SEL_297] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_289] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_357] + SHUFFLE [RS_347] PartitionCols:_col0 - Select Operator [SEL_356] (rows=348477374 width=88) + Select Operator [SEL_346] (rows=187573258 width=297) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_355] (rows=348477374 width=88) + Group By Operator [GBY_345] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_83] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_82] (rows=696954748 width=88) + Group By Operator [GBY_82] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_80] (rows=696954748 width=88) + Select Operator [SEL_80] (rows=187573258 width=847) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_282] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_282] (rows=187573258 width=847) Conds:RS_77._col1=RS_313._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_313] @@ -346,71 +333,60 @@ Stage-0 <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_281] (rows=633595212 width=88) - Conds:RS_354._col0=RS_290._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_281] (rows=187573258 width=199) + Conds:RS_344._col0=RS_290._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_290] PartitionCols:_col0 - Select Operator [SEL_287] (rows=36524 width=1119) + Select Operator [SEL_287] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_284] (rows=36524 width=1119) + Filter Operator [FIL_284] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_68] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_354] + SHUFFLE [RS_344] PartitionCols:_col0 - Select Operator [SEL_353] (rows=575995635 width=88) + Select Operator [SEL_343] (rows=525327388 width=221) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_352] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_78_customer_c_customer_sk_min) AND DynamicValue(RS_78_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_78_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_75_date_dim_d_date_sk_min) AND DynamicValue(RS_75_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_75_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_65] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] + Filter Operator [FIL_342] (rows=525327388 width=221) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_75_date_dim_d_date_sk_min) AND DynamicValue(RS_75_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_75_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_65] (rows=575995635 width=221) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_349] - Group By Operator [GBY_348] (rows=1 width=12) + BROADCAST [RS_341] + Group By Operator [GBY_340] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_302] Group By Operator [GBY_298] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_291] (rows=36524 width=1119) + Select Operator [SEL_291] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_287] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_351] - Group By Operator [GBY_350] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] - Group By Operator [GBY_319] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_314] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_312] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_325] + SHUFFLE [RS_319] PartitionCols:_col0 - Select Operator [SEL_324] (rows=87121617 width=135) + Select Operator [SEL_318] (rows=51391963 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_323] (rows=87121617 width=135) + Group By Operator [GBY_317] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_17] (rows=174243235 width=135) + Group By Operator [GBY_17] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_15] (rows=174243235 width=135) + Select Operator [SEL_15] (rows=51391963 width=875) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_276] (rows=174243235 width=135) - Conds:RS_12._col1=RS_315._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + Merge Join Operator [MERGEJOIN_276] (rows=51391963 width=875) + Conds:RS_12._col1=RS_314._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_315] + SHUFFLE [RS_314] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_312] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_275] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_275] (rows=51391963 width=227) Conds:RS_310._col0=RS_292._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_292] @@ -419,12 +395,12 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_310] PartitionCols:_col0 - Select Operator [SEL_309] (rows=144002668 width=135) + Select Operator [SEL_309] (rows=143930993 width=231) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_308] (rows=144002668 width=135) + Filter Operator [FIL_308] (rows=143930993 width=231) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] + TableScan [TS_0] (rows=144002668 width=231) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"] <-Reducer 21 [BROADCAST_EDGE] vectorized BROADCAST [RS_307] Group By Operator [GBY_306] (rows=1 width=12) @@ -433,7 +409,7 @@ Stage-0 SHUFFLE [RS_303] Group By Operator [GBY_299] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_293] (rows=36524 width=1119) + Select Operator [SEL_293] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_287] diff --git a/ql/src/test/results/clientpositive/perf/tez/query12.q.out b/ql/src/test/results/clientpositive/perf/tez/query12.q.out index 151bebf35a..446f304cc2 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query12.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query12.q.out @@ -80,62 +80,62 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_86] - Limit [LIM_85] (rows=100 width=135) + Limit [LIM_85] (rows=100 width=802) Number of rows:100 - Select Operator [SEL_84] (rows=87121617 width=135) + Select Operator [SEL_84] (rows=4798568 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_83] - Select Operator [SEL_82] (rows=87121617 width=135) + Select Operator [SEL_82] (rows=4798568 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_81] (rows=87121617 width=135) + PTF Operator [PTF_81] (rows=4798568 width=689) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"_col1"}] - Select Operator [SEL_80] (rows=87121617 width=135) + Select Operator [SEL_80] (rows=4798568 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_79] PartitionCols:_col1 - Group By Operator [GBY_78] (rows=87121617 width=135) + Group By Operator [GBY_78] (rows=4798568 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_16] (rows=174243235 width=135) + Group By Operator [GBY_16] (rows=4798568 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8 - Merge Join Operator [MERGEJOIN_58] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_58] (rows=4798568 width=689) Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_69] PartitionCols:_col0 - Select Operator [SEL_68] (rows=462000 width=1436) + Select Operator [SEL_68] (rows=138600 width=581) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_67] (rows=462000 width=1436) + Filter Operator [FIL_67] (rows=138600 width=581) predicate:((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] + TableScan [TS_6] (rows=462000 width=581) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_57] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_57] (rows=15995224 width=115) Conds:RS_77._col0=RS_61._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Select Operator [SEL_60] (rows=8116 width=1119) + Select Operator [SEL_60] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_59] (rows=8116 width=1119) + Filter Operator [FIL_59] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_77] PartitionCols:_col0 - Select Operator [SEL_76] (rows=144002668 width=135) + Select Operator [SEL_76] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_75] (rows=144002668 width=135) + Filter Operator [FIL_75] (rows=143966864 width=119) predicate:((ws_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] + TableScan [TS_0] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_74] Group By Operator [GBY_73] (rows=1 width=12) @@ -144,7 +144,7 @@ Stage-0 SHUFFLE [RS_72] Group By Operator [GBY_71] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_70] (rows=462000 width=1436) + Select Operator [SEL_70] (rows=138600 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_68] <-Reducer 8 [BROADCAST_EDGE] vectorized @@ -155,7 +155,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_64] Group By Operator [GBY_63] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_62] (rows=8116 width=1119) + Select Operator [SEL_62] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_60] diff --git a/ql/src/test/results/clientpositive/perf/tez/query13.q.out b/ql/src/test/results/clientpositive/perf/tez/query13.q.out index 6274d2a667..5bedb06887 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query13.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query13.q.out @@ -101,16 +101,14 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Map 16 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) @@ -119,104 +117,104 @@ Stage-0 limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_167] - Select Operator [SEL_166] (rows=1 width=256) + File Output Operator [FS_157] + Select Operator [SEL_156] (rows=1 width=344) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_165] (rows=1 width=256) + Group By Operator [GBY_155] (rows=1 width=256) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)"] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_37] Group By Operator [GBY_36] (rows=1 width=256) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)"] - Merge Join Operator [MERGEJOIN_121] (rows=8066665 width=1014) - Conds:RS_32._col4=RS_156._col0(Inner),Output:["_col5","_col7","_col8"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_156] + Merge Join Operator [MERGEJOIN_121] (rows=5070 width=0) + Conds:RS_32._col4=RS_154._col0(Inner),Output:["_col5","_col7","_col8"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_154] PartitionCols:_col0 - Select Operator [SEL_155] (rows=1704 width=1910) + Select Operator [SEL_153] (rows=1704 width=4) Output:["_col0"] - Filter Operator [FIL_154] (rows=1704 width=1910) + Filter Operator [FIL_152] (rows=1704 width=4) predicate:s_store_sk is not null - TableScan [TS_15] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"] + TableScan [TS_15] (rows=1704 width=4) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col4 - Filter Operator [FIL_31] (rows=7333332 width=1014) + Filter Operator [FIL_31] (rows=5070 width=86) predicate:((((_col18 = 'KY') or (_col18 = 'GA') or (_col18 = 'NM')) and _col9 BETWEEN 100 AND 200) or (((_col18 = 'MT') or (_col18 = 'OR') or (_col18 = 'IN')) and _col9 BETWEEN 150 AND 300) or (((_col18 = 'WI') or (_col18 = 'MO') or (_col18 = 'WV')) and _col9 BETWEEN 50 AND 250)) - Merge Join Operator [MERGEJOIN_120] (rows=22000000 width=1014) - Conds:RS_28._col3=RS_148._col0(Inner),Output:["_col4","_col5","_col7","_col8","_col9","_col18"] + Merge Join Operator [MERGEJOIN_120] (rows=15218 width=86) + Conds:RS_28._col3=RS_151._col0(Inner),Output:["_col4","_col5","_col7","_col8","_col9","_col18"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] + SHUFFLE [RS_151] PartitionCols:_col0 - Select Operator [SEL_147] (rows=20000000 width=1014) + Select Operator [SEL_150] (rows=20000000 width=187) Output:["_col0","_col1"] - Filter Operator [FIL_146] (rows=20000000 width=1014) + Filter Operator [FIL_149] (rows=20000000 width=187) predicate:((ca_country = 'United States') and ca_address_sk is not null) - TableScan [TS_12] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"] + TableScan [TS_12] (rows=40000000 width=187) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col3 - Filter Operator [FIL_27] (rows=10647918 width=88) + Filter Operator [FIL_27] (rows=30435 width=183) predicate:(((_col13 = 'D') and (_col14 = 'Primary') and _col6 BETWEEN 50 AND 100 and (_col16 = 1)) or ((_col13 = 'M') and (_col14 = '4 yr Degree') and _col6 BETWEEN 100 AND 150 and (_col16 = 3)) or ((_col13 = 'U') and (_col14 = 'Advanced Degree') and _col6 BETWEEN 150 AND 200 and (_col16 = 1))) - Merge Join Operator [MERGEJOIN_119] (rows=255550079 width=88) + Merge Join Operator [MERGEJOIN_119] (rows=4017301 width=183) Conds:RS_24._col2=RS_140._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col13","_col14","_col16"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_140] PartitionCols:_col0 - Select Operator [SEL_139] (rows=7200 width=107) + Select Operator [SEL_139] (rows=1309 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_138] (rows=7200 width=107) + Filter Operator [FIL_138] (rows=1309 width=8) predicate:((hd_dep_count) IN (3, 1) and hd_demo_sk is not null) - TableScan [TS_9] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"] + TableScan [TS_9] (rows=7200 width=8) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_118] (rows=232318249 width=88) + Merge Join Operator [MERGEJOIN_118] (rows=22096687 width=498) Conds:RS_21._col1=RS_132._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col13","_col14"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_132] PartitionCols:_col0 - Select Operator [SEL_131] (rows=1861800 width=385) + Select Operator [SEL_131] (rows=265971 width=183) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_130] (rows=1861800 width=385) + Filter Operator [FIL_130] (rows=265971 width=183) predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + TableScan [TS_6] (rows=1861800 width=183) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_117] (rows=211198404 width=88) - Conds:RS_164._col0=RS_124._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + Merge Join Operator [MERGEJOIN_117] (rows=54458905 width=409) + Conds:RS_148._col0=RS_124._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_124] PartitionCols:_col0 - Select Operator [SEL_123] (rows=36524 width=1119) + Select Operator [SEL_123] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_122] (rows=36524 width=1119) + Filter Operator [FIL_122] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_164] + SHUFFLE [RS_148] PartitionCols:_col0 - Select Operator [SEL_163] (rows=191998545 width=88) + Select Operator [SEL_147] (rows=152520430 width=450) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Filter Operator [FIL_162] (rows=191998545 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_29_customer_address_ca_address_sk_min) AND DynamicValue(RS_29_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_29_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_22_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_22_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_22_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_33_store_s_store_sk_min) AND DynamicValue(RS_33_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_33_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"] + Filter Operator [FIL_146] (rows=152520430 width=450) + predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_22_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_22_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_22_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=450) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_137] Group By Operator [GBY_136] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1861800)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_135] Group By Operator [GBY_134] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1861800)"] - Select Operator [SEL_133] (rows=1861800 width=385) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_133] (rows=265971 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_131] <-Reducer 13 [BROADCAST_EDGE] vectorized @@ -227,31 +225,9 @@ Stage-0 SHUFFLE [RS_143] Group By Operator [GBY_142] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_141] (rows=7200 width=107) + Select Operator [SEL_141] (rows=1309 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_139] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_153] - Group By Operator [GBY_152] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_151] - Group By Operator [GBY_150] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_149] (rows=20000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_147] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_161] - Group By Operator [GBY_160] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_159] - Group By Operator [GBY_158] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_157] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_155] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_129] Group By Operator [GBY_128] (rows=1 width=12) @@ -260,7 +236,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_127] Group By Operator [GBY_126] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_125] (rows=36524 width=1119) + Select Operator [SEL_125] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_123] diff --git a/ql/src/test/results/clientpositive/perf/tez/query14.q.out b/ql/src/test/results/clientpositive/perf/tez/query14.q.out index b9efa45853..6ab2f13b5e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query14.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query14.q.out @@ -210,34 +210,30 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 108 (BROADCAST_EDGE) -Map 100 <- Reducer 103 (BROADCAST_EDGE), Reducer 71 (BROADCAST_EDGE) -Map 110 <- Reducer 105 (BROADCAST_EDGE), Reducer 74 (BROADCAST_EDGE) -Map 111 <- Reducer 107 (BROADCAST_EDGE), Reducer 77 (BROADCAST_EDGE) -Map 112 <- Reducer 58 (BROADCAST_EDGE), Reducer 81 (BROADCAST_EDGE), Reducer 98 (BROADCAST_EDGE) -Map 113 <- Reducer 62 (BROADCAST_EDGE), Reducer 91 (BROADCAST_EDGE), Reducer 99 (BROADCAST_EDGE) +Map 1 <- Reducer 102 (BROADCAST_EDGE) +Map 104 <- Reducer 99 (BROADCAST_EDGE) +Map 105 <- Reducer 101 (BROADCAST_EDGE) +Map 106 <- Reducer 58 (BROADCAST_EDGE), Reducer 77 (BROADCAST_EDGE) +Map 107 <- Reducer 62 (BROADCAST_EDGE), Reducer 87 (BROADCAST_EDGE) Map 17 <- Reducer 22 (BROADCAST_EDGE) Map 33 <- Reducer 38 (BROADCAST_EDGE) -Map 43 <- Reducer 109 (BROADCAST_EDGE) +Map 43 <- Reducer 103 (BROADCAST_EDGE) Map 47 <- Reducer 26 (BROADCAST_EDGE) Map 48 <- Reducer 40 (BROADCAST_EDGE) -Map 49 <- Reducer 54 (BROADCAST_EDGE), Reducer 66 (BROADCAST_EDGE), Reducer 78 (BROADCAST_EDGE) -Reducer 101 <- Map 100 (SIMPLE_EDGE), Map 102 (SIMPLE_EDGE) -Reducer 103 <- Map 102 (CUSTOM_SIMPLE_EDGE) -Reducer 104 <- Map 102 (SIMPLE_EDGE), Map 110 (SIMPLE_EDGE) -Reducer 105 <- Map 102 (CUSTOM_SIMPLE_EDGE) -Reducer 106 <- Map 102 (SIMPLE_EDGE), Map 111 (SIMPLE_EDGE) -Reducer 107 <- Map 102 (CUSTOM_SIMPLE_EDGE) -Reducer 108 <- Map 102 (CUSTOM_SIMPLE_EDGE) -Reducer 109 <- Map 102 (CUSTOM_SIMPLE_EDGE) +Map 49 <- Reducer 54 (BROADCAST_EDGE), Reducer 66 (BROADCAST_EDGE) +Map 94 <- Reducer 97 (BROADCAST_EDGE) +Reducer 100 <- Map 105 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE) +Reducer 101 <- Map 96 (CUSTOM_SIMPLE_EDGE) +Reducer 102 <- Map 96 (CUSTOM_SIMPLE_EDGE) +Reducer 103 <- Map 96 (CUSTOM_SIMPLE_EDGE) Reducer 11 <- Union 10 (CUSTOM_SIMPLE_EDGE) Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 29 (CUSTOM_SIMPLE_EDGE), Reducer 57 (CUSTOM_SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 13 <- Map 1 (SIMPLE_EDGE), Map 102 (SIMPLE_EDGE), Union 14 (CONTAINS) +Reducer 13 <- Map 1 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE), Union 14 (CONTAINS) Reducer 15 <- Union 14 (CUSTOM_SIMPLE_EDGE) Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 32 (CUSTOM_SIMPLE_EDGE), Reducer 61 (CUSTOM_SIMPLE_EDGE), Union 6 (CONTAINS) Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE), Union 10 (CONTAINS) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 102 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 20 <- Map 17 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE), Union 14 (CONTAINS) Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) Reducer 23 <- Map 21 (SIMPLE_EDGE), Map 47 (SIMPLE_EDGE), Union 24 (CONTAINS) @@ -256,660 +252,610 @@ Reducer 4 <- Union 3 (CUSTOM_SIMPLE_EDGE) Reducer 40 <- Map 37 (CUSTOM_SIMPLE_EDGE) Reducer 41 <- Map 37 (SIMPLE_EDGE), Map 48 (SIMPLE_EDGE), Union 28 (CONTAINS) Reducer 42 <- Map 37 (SIMPLE_EDGE), Map 48 (SIMPLE_EDGE), Union 31 (CONTAINS) -Reducer 44 <- Map 102 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE), Union 24 (CONTAINS) -Reducer 45 <- Map 102 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 46 <- Map 102 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE), Union 31 (CONTAINS) +Reducer 44 <- Map 43 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE), Union 24 (CONTAINS) +Reducer 45 <- Map 43 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE), Union 28 (CONTAINS) +Reducer 46 <- Map 43 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE), Union 31 (CONTAINS) Reducer 5 <- Reducer 25 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 52 (CUSTOM_SIMPLE_EDGE), Union 6 (CONTAINS) Reducer 50 <- Map 49 (SIMPLE_EDGE), Map 53 (SIMPLE_EDGE) Reducer 51 <- Map 63 (SIMPLE_EDGE), Reducer 50 (SIMPLE_EDGE), Reducer 65 (ONE_TO_ONE_EDGE) Reducer 52 <- Reducer 51 (SIMPLE_EDGE) Reducer 54 <- Map 53 (CUSTOM_SIMPLE_EDGE) -Reducer 55 <- Map 112 (SIMPLE_EDGE), Map 53 (SIMPLE_EDGE) -Reducer 56 <- Map 63 (SIMPLE_EDGE), Reducer 55 (SIMPLE_EDGE), Reducer 80 (ONE_TO_ONE_EDGE) +Reducer 55 <- Map 106 (SIMPLE_EDGE), Map 53 (SIMPLE_EDGE) +Reducer 56 <- Map 63 (SIMPLE_EDGE), Reducer 55 (SIMPLE_EDGE), Reducer 76 (ONE_TO_ONE_EDGE) Reducer 57 <- Reducer 56 (SIMPLE_EDGE) Reducer 58 <- Map 53 (CUSTOM_SIMPLE_EDGE) -Reducer 59 <- Map 113 (SIMPLE_EDGE), Map 53 (SIMPLE_EDGE) -Reducer 60 <- Map 63 (SIMPLE_EDGE), Reducer 59 (SIMPLE_EDGE), Reducer 90 (ONE_TO_ONE_EDGE) +Reducer 59 <- Map 107 (SIMPLE_EDGE), Map 53 (SIMPLE_EDGE) +Reducer 60 <- Map 63 (SIMPLE_EDGE), Reducer 59 (SIMPLE_EDGE), Reducer 86 (ONE_TO_ONE_EDGE) Reducer 61 <- Reducer 60 (SIMPLE_EDGE) Reducer 62 <- Map 53 (CUSTOM_SIMPLE_EDGE) Reducer 64 <- Map 63 (SIMPLE_EDGE), Reducer 70 (ONE_TO_ONE_EDGE) Reducer 65 <- Reducer 64 (SIMPLE_EDGE) Reducer 66 <- Reducer 65 (CUSTOM_SIMPLE_EDGE) -Reducer 67 <- Map 63 (SIMPLE_EDGE), Reducer 101 (SIMPLE_EDGE) +Reducer 67 <- Map 63 (SIMPLE_EDGE), Reducer 95 (SIMPLE_EDGE) Reducer 68 <- Reducer 67 (SIMPLE_EDGE), Union 69 (CONTAINS) Reducer 7 <- Union 6 (SIMPLE_EDGE) Reducer 70 <- Union 69 (SIMPLE_EDGE) -Reducer 71 <- Map 63 (CUSTOM_SIMPLE_EDGE) -Reducer 72 <- Map 63 (SIMPLE_EDGE), Reducer 104 (SIMPLE_EDGE) -Reducer 73 <- Reducer 72 (SIMPLE_EDGE), Union 69 (CONTAINS) -Reducer 74 <- Map 63 (CUSTOM_SIMPLE_EDGE) -Reducer 75 <- Map 63 (SIMPLE_EDGE), Reducer 106 (SIMPLE_EDGE) -Reducer 76 <- Reducer 75 (SIMPLE_EDGE), Union 69 (CONTAINS) -Reducer 77 <- Map 63 (CUSTOM_SIMPLE_EDGE) -Reducer 78 <- Map 63 (CUSTOM_SIMPLE_EDGE) -Reducer 79 <- Map 63 (SIMPLE_EDGE), Reducer 85 (ONE_TO_ONE_EDGE) +Reducer 71 <- Map 63 (SIMPLE_EDGE), Reducer 98 (SIMPLE_EDGE) +Reducer 72 <- Reducer 71 (SIMPLE_EDGE), Union 69 (CONTAINS) +Reducer 73 <- Map 63 (SIMPLE_EDGE), Reducer 100 (SIMPLE_EDGE) +Reducer 74 <- Reducer 73 (SIMPLE_EDGE), Union 69 (CONTAINS) +Reducer 75 <- Map 63 (SIMPLE_EDGE), Reducer 81 (ONE_TO_ONE_EDGE) +Reducer 76 <- Reducer 75 (SIMPLE_EDGE) +Reducer 77 <- Reducer 76 (CUSTOM_SIMPLE_EDGE) +Reducer 78 <- Map 63 (SIMPLE_EDGE), Reducer 95 (SIMPLE_EDGE) +Reducer 79 <- Reducer 78 (SIMPLE_EDGE), Union 80 (CONTAINS) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) -Reducer 80 <- Reducer 79 (SIMPLE_EDGE) -Reducer 81 <- Reducer 80 (CUSTOM_SIMPLE_EDGE) -Reducer 82 <- Map 63 (SIMPLE_EDGE), Reducer 101 (SIMPLE_EDGE) -Reducer 83 <- Reducer 82 (SIMPLE_EDGE), Union 84 (CONTAINS) -Reducer 85 <- Union 84 (SIMPLE_EDGE) -Reducer 86 <- Reducer 82 (SIMPLE_EDGE), Union 87 (CONTAINS) -Reducer 88 <- Union 87 (SIMPLE_EDGE) -Reducer 89 <- Map 63 (SIMPLE_EDGE), Reducer 88 (ONE_TO_ONE_EDGE) -Reducer 9 <- Map 1 (SIMPLE_EDGE), Map 102 (SIMPLE_EDGE), Union 10 (CONTAINS) -Reducer 90 <- Reducer 89 (SIMPLE_EDGE) -Reducer 91 <- Reducer 90 (CUSTOM_SIMPLE_EDGE) -Reducer 92 <- Map 63 (SIMPLE_EDGE), Reducer 104 (SIMPLE_EDGE) -Reducer 93 <- Reducer 92 (SIMPLE_EDGE), Union 84 (CONTAINS) -Reducer 94 <- Reducer 92 (SIMPLE_EDGE), Union 87 (CONTAINS) -Reducer 95 <- Map 63 (SIMPLE_EDGE), Reducer 106 (SIMPLE_EDGE) -Reducer 96 <- Reducer 95 (SIMPLE_EDGE), Union 84 (CONTAINS) -Reducer 97 <- Reducer 95 (SIMPLE_EDGE), Union 87 (CONTAINS) -Reducer 98 <- Map 63 (CUSTOM_SIMPLE_EDGE) -Reducer 99 <- Map 63 (CUSTOM_SIMPLE_EDGE) +Reducer 81 <- Union 80 (SIMPLE_EDGE) +Reducer 82 <- Reducer 78 (SIMPLE_EDGE), Union 83 (CONTAINS) +Reducer 84 <- Union 83 (SIMPLE_EDGE) +Reducer 85 <- Map 63 (SIMPLE_EDGE), Reducer 84 (ONE_TO_ONE_EDGE) +Reducer 86 <- Reducer 85 (SIMPLE_EDGE) +Reducer 87 <- Reducer 86 (CUSTOM_SIMPLE_EDGE) +Reducer 88 <- Map 63 (SIMPLE_EDGE), Reducer 98 (SIMPLE_EDGE) +Reducer 89 <- Reducer 88 (SIMPLE_EDGE), Union 80 (CONTAINS) +Reducer 9 <- Map 1 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE), Union 10 (CONTAINS) +Reducer 90 <- Reducer 88 (SIMPLE_EDGE), Union 83 (CONTAINS) +Reducer 91 <- Map 63 (SIMPLE_EDGE), Reducer 100 (SIMPLE_EDGE) +Reducer 92 <- Reducer 91 (SIMPLE_EDGE), Union 80 (CONTAINS) +Reducer 93 <- Reducer 91 (SIMPLE_EDGE), Union 83 (CONTAINS) +Reducer 95 <- Map 94 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE) +Reducer 97 <- Map 96 (CUSTOM_SIMPLE_EDGE) +Reducer 98 <- Map 104 (SIMPLE_EDGE), Map 96 (SIMPLE_EDGE) +Reducer 99 <- Map 96 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 8 vectorized - File Output Operator [FS_1743] - Limit [LIM_1742] (rows=100 width=237) + File Output Operator [FS_1723] + Limit [LIM_1722] (rows=100 width=223) Number of rows:100 - Select Operator [SEL_1741] (rows=1016388080 width=237) + Select Operator [SEL_1721] (rows=121728 width=222) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1740] - Select Operator [SEL_1739] (rows=1016388080 width=237) + SHUFFLE [RS_1720] + Select Operator [SEL_1719] (rows=121728 width=222) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_1738] (rows=1016388080 width=237) + Group By Operator [GBY_1718] (rows=121728 width=230) Output:["_col0","_col1","_col2","_col3","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 6 [SIMPLE_EDGE] <-Reducer 12 [CONTAINS] Reduce Output Operator [RS_1474] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_1473] (rows=2032776160 width=237) + Group By Operator [GBY_1473] (rows=304320 width=230) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L - Top N Key Operator [TNK_1472] (rows=406555232 width=237) + Top N Key Operator [TNK_1472] (rows=121728 width=220) keys:_col0, _col1, _col2, _col3, 0L,sort order:+++++,top n:100 - Select Operator [SEL_1470] (rows=116155905 width=264) + Select Operator [SEL_1470] (rows=40576 width=222) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_1469] (rows=116155905 width=264) + Filter Operator [FIL_1469] (rows=40576 width=243) predicate:(_col5 > _col1) - Merge Join Operator [MERGEJOIN_1468] (rows=348467716 width=264) + Merge Join Operator [MERGEJOIN_1468] (rows=121728 width=243) Conds:(Inner),(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1749] - Select Operator [SEL_1748] (rows=1 width=8) - Filter Operator [FIL_1747] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_1729] + Select Operator [SEL_1728] (rows=1 width=8) + Filter Operator [FIL_1727] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_1746] (rows=1 width=8) + Group By Operator [GBY_1726] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_1745] (rows=1 width=8) - Group By Operator [GBY_1744] (rows=1 width=8) + Select Operator [SEL_1725] (rows=1 width=8) + Group By Operator [GBY_1724] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Union 10 [CUSTOM_SIMPLE_EDGE] <-Reducer 19 [CONTAINS] Reduce Output Operator [RS_1499] Group By Operator [GBY_1498] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1497] (rows=1108786976 width=108) + Select Operator [SEL_1497] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1495] (rows=316788826 width=135) + Select Operator [SEL_1495] (rows=31836679 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1494] (rows=316788826 width=135) - Conds:RS_1821._col0=RS_1808._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1494] (rows=31836679 width=3) + Conds:RS_1797._col0=RS_1784._col0(Inner),Output:["_col1"] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1808] + SHUFFLE [RS_1784] PartitionCols:_col0 - Select Operator [SEL_1803] (rows=8116 width=1119) + Select Operator [SEL_1779] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_1802] (rows=8116 width=1119) + Filter Operator [FIL_1778] (rows=8116 width=8) predicate:(d_date_sk is not null and d_year BETWEEN 1998 AND 2000) - TableScan [TS_13] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_13] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1821] + SHUFFLE [RS_1797] PartitionCols:_col0 - Select Operator [SEL_1819] (rows=287989836 width=135) + Select Operator [SEL_1795] (rows=286549727 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1818] (rows=287989836 width=135) + Filter Operator [FIL_1794] (rows=286549727 width=7) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_17_date_dim_d_date_sk_min) AND DynamicValue(RS_17_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_17_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_10] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity"] + TableScan [TS_10] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_quantity"] <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1817] - Group By Operator [GBY_1816] (rows=1 width=12) + BROADCAST [RS_1793] + Group By Operator [GBY_1792] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1814] - Group By Operator [GBY_1812] (rows=1 width=12) + SHUFFLE [RS_1790] + Group By Operator [GBY_1788] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1805] (rows=8116 width=1119) + Select Operator [SEL_1781] (rows=8116 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1803] + Please refer to the previous Select Operator [SEL_1779] <-Reducer 35 [CONTAINS] Reduce Output Operator [RS_1535] Group By Operator [GBY_1534] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1533] (rows=1108786976 width=108) + Select Operator [SEL_1533] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1531] (rows=158402938 width=135) + Select Operator [SEL_1531] (rows=15995224 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1530] (rows=158402938 width=135) - Conds:RS_1849._col0=RS_1836._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1530] (rows=15995224 width=3) + Conds:RS_1825._col0=RS_1812._col0(Inner),Output:["_col1"] <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1836] + SHUFFLE [RS_1812] PartitionCols:_col0 - Select Operator [SEL_1831] (rows=8116 width=1119) + Select Operator [SEL_1807] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_1830] (rows=8116 width=1119) + Filter Operator [FIL_1806] (rows=8116 width=8) predicate:(d_date_sk is not null and d_year BETWEEN 1998 AND 2000) - TableScan [TS_24] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_24] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1849] + SHUFFLE [RS_1825] PartitionCols:_col0 - Select Operator [SEL_1847] (rows=144002668 width=135) + Select Operator [SEL_1823] (rows=143966864 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1846] (rows=144002668 width=135) + Filter Operator [FIL_1822] (rows=143966864 width=7) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) - TableScan [TS_21] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity"] + TableScan [TS_21] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_quantity"] <-Reducer 38 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1845] - Group By Operator [GBY_1844] (rows=1 width=12) + BROADCAST [RS_1821] + Group By Operator [GBY_1820] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1842] - Group By Operator [GBY_1840] (rows=1 width=12) + SHUFFLE [RS_1818] + Group By Operator [GBY_1816] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1833] (rows=8116 width=1119) + Select Operator [SEL_1809] (rows=8116 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1831] + Please refer to the previous Select Operator [SEL_1807] <-Reducer 9 [CONTAINS] Reduce Output Operator [RS_1467] Group By Operator [GBY_1466] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1465] (rows=1108786976 width=108) + Select Operator [SEL_1465] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1463] (rows=633595212 width=88) + Select Operator [SEL_1463] (rows=61115434 width=2) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1462] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_1462] (rows=61115434 width=2) Conds:RS_1645._col0=RS_1626._col0(Inner),Output:["_col1"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1626] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1626] PartitionCols:_col0 - Select Operator [SEL_1615] (rows=8116 width=1119) + Select Operator [SEL_1615] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_1614] (rows=8116 width=1119) + Filter Operator [FIL_1614] (rows=8116 width=8) predicate:(d_date_sk is not null and d_year BETWEEN 1999 AND 2001) - TableScan [TS_97] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_97] (rows=73049 width=8) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1645] PartitionCols:_col0 - Select Operator [SEL_1643] (rows=575995635 width=88) + Select Operator [SEL_1643] (rows=550076554 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1642] (rows=575995635 width=88) + Filter Operator [FIL_1642] (rows=550076554 width=7) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity"] - <-Reducer 108 [BROADCAST_EDGE] vectorized + TableScan [TS_0] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_quantity"] + <-Reducer 102 [BROADCAST_EDGE] vectorized BROADCAST [RS_1641] Group By Operator [GBY_1640] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 102 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1638] + <-Map 96 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1638] Group By Operator [GBY_1633] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1623] (rows=8116 width=1119) + Select Operator [SEL_1623] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1615] <-Reducer 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1752] - Select Operator [SEL_1751] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_1732] + Select Operator [SEL_1731] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_1750] (rows=1 width=120) + Group By Operator [GBY_1730] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Union 28 [CUSTOM_SIMPLE_EDGE] <-Reducer 27 [CONTAINS] Reduce Output Operator [RS_1517] Group By Operator [GBY_1516] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1515] (rows=1108786976 width=108) + Select Operator [SEL_1515] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1513] (rows=316788826 width=135) + Select Operator [SEL_1513] (rows=31836679 width=110) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1512] (rows=316788826 width=135) - Conds:RS_1828._col0=RS_1809._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1512] (rows=31836679 width=110) + Conds:RS_1804._col0=RS_1785._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1809] + SHUFFLE [RS_1785] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1803] + Please refer to the previous Select Operator [SEL_1779] <-Map 47 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1828] + SHUFFLE [RS_1804] PartitionCols:_col0 - Select Operator [SEL_1826] (rows=287989836 width=135) + Select Operator [SEL_1802] (rows=286549727 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1825] (rows=287989836 width=135) + Filter Operator [FIL_1801] (rows=286549727 width=119) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_62_date_dim_d_date_sk_min) AND DynamicValue(RS_62_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_62_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_55] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"] + TableScan [TS_55] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_quantity","cs_list_price"] <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1824] - Group By Operator [GBY_1823] (rows=1 width=12) + BROADCAST [RS_1800] + Group By Operator [GBY_1799] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1815] - Group By Operator [GBY_1813] (rows=1 width=12) + SHUFFLE [RS_1791] + Group By Operator [GBY_1789] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1807] (rows=8116 width=1119) + Select Operator [SEL_1783] (rows=8116 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1803] + Please refer to the previous Select Operator [SEL_1779] <-Reducer 41 [CONTAINS] Reduce Output Operator [RS_1553] Group By Operator [GBY_1552] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1551] (rows=1108786976 width=108) + Select Operator [SEL_1551] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1549] (rows=158402938 width=135) + Select Operator [SEL_1549] (rows=15995224 width=115) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1548] (rows=158402938 width=135) - Conds:RS_1856._col0=RS_1837._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1548] (rows=15995224 width=115) + Conds:RS_1832._col0=RS_1813._col0(Inner),Output:["_col1","_col2"] <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1837] + SHUFFLE [RS_1813] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1831] + Please refer to the previous Select Operator [SEL_1807] <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1856] + SHUFFLE [RS_1832] PartitionCols:_col0 - Select Operator [SEL_1854] (rows=144002668 width=135) + Select Operator [SEL_1830] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1853] (rows=144002668 width=135) + Filter Operator [FIL_1829] (rows=143966864 width=119) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_73_date_dim_d_date_sk_min) AND DynamicValue(RS_73_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_73_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) - TableScan [TS_66] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"] + TableScan [TS_66] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_quantity","ws_list_price"] <-Reducer 40 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1852] - Group By Operator [GBY_1851] (rows=1 width=12) + BROADCAST [RS_1828] + Group By Operator [GBY_1827] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1843] - Group By Operator [GBY_1841] (rows=1 width=12) + SHUFFLE [RS_1819] + Group By Operator [GBY_1817] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1835] (rows=8116 width=1119) + Select Operator [SEL_1811] (rows=8116 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1831] + Please refer to the previous Select Operator [SEL_1807] <-Reducer 45 [CONTAINS] Reduce Output Operator [RS_1571] Group By Operator [GBY_1570] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1569] (rows=1108786976 width=108) + Select Operator [SEL_1569] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1567] (rows=633595212 width=88) + Select Operator [SEL_1567] (rows=61115434 width=69) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1566] (rows=633595212 width=88) - Conds:RS_1863._col0=RS_1627._col0(Inner),Output:["_col1","_col2"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1627] + Merge Join Operator [MERGEJOIN_1566] (rows=61115434 width=69) + Conds:RS_1839._col0=RS_1627._col0(Inner),Output:["_col1","_col2"] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1627] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1863] + SHUFFLE [RS_1839] PartitionCols:_col0 - Select Operator [SEL_1861] (rows=575995635 width=88) + Select Operator [SEL_1837] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1860] (rows=575995635 width=88) + Filter Operator [FIL_1836] (rows=550076554 width=114) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_52_date_dim_d_date_sk_min) AND DynamicValue(RS_52_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_52_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) - TableScan [TS_45] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"] - <-Reducer 109 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1859] - Group By Operator [GBY_1858] (rows=1 width=12) + TableScan [TS_45] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_quantity","ss_list_price"] + <-Reducer 103 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1835] + Group By Operator [GBY_1834] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 102 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1639] + <-Map 96 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1639] Group By Operator [GBY_1634] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1625] (rows=8116 width=1119) + Select Operator [SEL_1625] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1615] <-Reducer 57 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1772] - Group By Operator [GBY_1771] (rows=348467716 width=135) + PARTITION_ONLY_SHUFFLE [RS_1750] + Group By Operator [GBY_1749] (rows=121728 width=131) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 56 [SIMPLE_EDGE] SHUFFLE [RS_369] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_368] (rows=696935432 width=135) + Group By Operator [GBY_368] (rows=121728 width=131) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_366] (rows=696935432 width=135) + Select Operator [SEL_366] (rows=1742885 width=32) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_1430] (rows=696935432 width=135) - Conds:RS_362._col1=RS_1703._col0(Inner),RS_362._col1=RS_1762._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] + Merge Join Operator [MERGEJOIN_1430] (rows=1742885 width=32) + Conds:RS_362._col1=RS_1699._col0(Inner),RS_362._col1=RS_1740._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1703] + SHUFFLE [RS_1699] PartitionCols:_col0 - Select Operator [SEL_1687] (rows=462000 width=1436) + Select Operator [SEL_1687] (rows=462000 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1678] (rows=462000 width=1436) + Filter Operator [FIL_1678] (rows=462000 width=15) predicate:i_item_sk is not null - TableScan [TS_91] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"] - <-Reducer 80 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1762] + TableScan [TS_91] (rows=462000 width=15) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id"] + <-Reducer 76 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1740] PartitionCols:_col0 - Group By Operator [GBY_1761] (rows=254100 width=1436) + Group By Operator [GBY_1739] (rows=362 width=4) Output:["_col0"],keys:KEY._col0 - <-Reducer 79 [SIMPLE_EDGE] + <-Reducer 75 [SIMPLE_EDGE] SHUFFLE [RS_356] PartitionCols:_col0 - Group By Operator [GBY_355] (rows=508200 width=1436) + Group By Operator [GBY_355] (rows=362 width=4) Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_1429] (rows=508200 width=1436) - Conds:RS_1699._col1, _col2, _col3=RS_1760._col0, _col1, _col2(Inner),Output:["_col0"] + Merge Join Operator [MERGEJOIN_1429] (rows=724 width=4) + Conds:RS_1695._col1, _col2, _col3=RS_1738._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1699] + SHUFFLE [RS_1695] PartitionCols:_col1, _col2, _col3 - Select Operator [SEL_1683] (rows=462000 width=1436) + Select Operator [SEL_1683] (rows=458612 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1674] (rows=462000 width=1436) + Filter Operator [FIL_1674] (rows=458612 width=15) predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null) Please refer to the previous TableScan [TS_91] - <-Reducer 85 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_1760] + <-Reducer 81 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_1738] PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_1759] (rows=1 width=108) + Select Operator [SEL_1737] (rows=1 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1758] (rows=1 width=108) + Filter Operator [FIL_1736] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1757] (rows=304916424 width=108) + Group By Operator [GBY_1735] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Union 84 [SIMPLE_EDGE] - <-Reducer 83 [CONTAINS] vectorized - Reduce Output Operator [RS_1897] + <-Union 80 [SIMPLE_EDGE] + <-Reducer 79 [CONTAINS] vectorized + Reduce Output Operator [RS_1867] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1896] (rows=609832849 width=108) + Group By Operator [GBY_1866] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1895] (rows=348477374 width=88) + Group By Operator [GBY_1865] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 82 [SIMPLE_EDGE] + <-Reducer 78 [SIMPLE_EDGE] SHUFFLE [RS_300] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_299] (rows=696954748 width=88) + Group By Operator [GBY_299] (rows=365184 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 - Merge Join Operator [MERGEJOIN_1424] (rows=696954748 width=88) - Conds:RS_295._col1=RS_1700._col0(Inner),Output:["_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_1424] (rows=60667254 width=11) + Conds:RS_295._col1=RS_1696._col0(Inner),Output:["_col5","_col6","_col7"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1700] + SHUFFLE [RS_1696] PartitionCols:_col0 - Select Operator [SEL_1684] (rows=462000 width=1436) + Select Operator [SEL_1684] (rows=458612 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1675] (rows=462000 width=1436) + Filter Operator [FIL_1675] (rows=458612 width=15) predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null) Please refer to the previous TableScan [TS_91] - <-Reducer 101 [SIMPLE_EDGE] + <-Reducer 95 [SIMPLE_EDGE] SHUFFLE [RS_295] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1408] (rows=633595212 width=88) - Conds:RS_1871._col0=RS_1616._col0(Inner),Output:["_col1"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1616] + Merge Join Operator [MERGEJOIN_1408] (rows=61115434 width=4) + Conds:RS_1845._col0=RS_1616._col0(Inner),Output:["_col1"] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1616] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] - <-Map 100 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1871] + <-Map 94 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1845] PartitionCols:_col0 - Select Operator [SEL_1870] (rows=575995635 width=88) + Select Operator [SEL_1844] (rows=550076554 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1869] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_107_iss_i_item_sk_min) AND DynamicValue(RS_107_iss_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_107_iss_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_104_d1_d_date_sk_min) AND DynamicValue(RS_104_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_104_d1_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_94] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"] - <-Reducer 103 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1866] - Group By Operator [GBY_1865] (rows=1 width=12) + Filter Operator [FIL_1843] (rows=550076554 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_104_d1_d_date_sk_min) AND DynamicValue(RS_104_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_104_d1_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_94] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] + <-Reducer 97 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1842] + Group By Operator [GBY_1841] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 102 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1635] + <-Map 96 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1635] Group By Operator [GBY_1630] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1617] (rows=8116 width=1119) + Select Operator [SEL_1617] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1615] - <-Reducer 71 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1868] - Group By Operator [GBY_1867] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 63 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1714] - Group By Operator [GBY_1708] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1692] (rows=462000 width=1436) - Output:["_col0"] - Select Operator [SEL_1681] (rows=462000 width=1436) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1672] (rows=462000 width=1436) - predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null) - Please refer to the previous TableScan [TS_91] - <-Reducer 93 [CONTAINS] vectorized - Reduce Output Operator [RS_1903] + <-Reducer 89 [CONTAINS] vectorized + Reduce Output Operator [RS_1873] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1902] (rows=609832849 width=108) + Group By Operator [GBY_1872] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1901] (rows=174233858 width=135) + Group By Operator [GBY_1871] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 92 [SIMPLE_EDGE] + <-Reducer 88 [SIMPLE_EDGE] SHUFFLE [RS_320] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_319] (rows=348467716 width=135) + Group By Operator [GBY_319] (rows=243456 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 - Merge Join Operator [MERGEJOIN_1426] (rows=348467716 width=135) - Conds:RS_315._col1=RS_1701._col0(Inner),Output:["_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_1426] (rows=31603210 width=11) + Conds:RS_315._col1=RS_1697._col0(Inner),Output:["_col5","_col6","_col7"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1701] + SHUFFLE [RS_1697] PartitionCols:_col0 - Select Operator [SEL_1685] (rows=462000 width=1436) + Select Operator [SEL_1685] (rows=458612 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1676] (rows=462000 width=1436) + Filter Operator [FIL_1676] (rows=458612 width=15) predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null) Please refer to the previous TableScan [TS_91] - <-Reducer 104 [SIMPLE_EDGE] + <-Reducer 98 [SIMPLE_EDGE] SHUFFLE [RS_315] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1410] (rows=316788826 width=135) - Conds:RS_1881._col0=RS_1618._col0(Inner),Output:["_col1"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1618] + Merge Join Operator [MERGEJOIN_1410] (rows=31836679 width=4) + Conds:RS_1853._col0=RS_1618._col0(Inner),Output:["_col1"] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1618] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] - <-Map 110 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1881] + <-Map 104 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1853] PartitionCols:_col0 - Select Operator [SEL_1880] (rows=287989836 width=135) + Select Operator [SEL_1852] (rows=286549727 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1879] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_127_ics_i_item_sk_min) AND DynamicValue(RS_127_ics_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_127_ics_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_124_d2_d_date_sk_min) AND DynamicValue(RS_124_d2_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_124_d2_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_114] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk"] - <-Reducer 105 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1876] - Group By Operator [GBY_1875] (rows=1 width=12) + Filter Operator [FIL_1851] (rows=286549727 width=7) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_124_d2_d_date_sk_min) AND DynamicValue(RS_124_d2_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_124_d2_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_114] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk"] + <-Reducer 99 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1850] + Group By Operator [GBY_1849] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 102 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1636] + <-Map 96 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1636] Group By Operator [GBY_1631] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1619] (rows=8116 width=1119) + Select Operator [SEL_1619] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1615] - <-Reducer 74 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1878] - Group By Operator [GBY_1877] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 63 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1715] - Group By Operator [GBY_1709] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1694] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1681] - <-Reducer 96 [CONTAINS] vectorized - Reduce Output Operator [RS_1909] + <-Reducer 92 [CONTAINS] vectorized + Reduce Output Operator [RS_1879] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1908] (rows=609832849 width=108) + Group By Operator [GBY_1878] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1907] (rows=87121617 width=135) + Group By Operator [GBY_1877] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 95 [SIMPLE_EDGE] + <-Reducer 91 [SIMPLE_EDGE] SHUFFLE [RS_341] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_340] (rows=174243235 width=135) + Group By Operator [GBY_340] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 - Merge Join Operator [MERGEJOIN_1428] (rows=174243235 width=135) - Conds:RS_336._col1=RS_1702._col0(Inner),Output:["_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_1428] (rows=15877926 width=11) + Conds:RS_336._col1=RS_1698._col0(Inner),Output:["_col5","_col6","_col7"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1702] + SHUFFLE [RS_1698] PartitionCols:_col0 - Select Operator [SEL_1686] (rows=462000 width=1436) + Select Operator [SEL_1686] (rows=458612 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1677] (rows=462000 width=1436) + Filter Operator [FIL_1677] (rows=458612 width=15) predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null) Please refer to the previous TableScan [TS_91] - <-Reducer 106 [SIMPLE_EDGE] + <-Reducer 100 [SIMPLE_EDGE] SHUFFLE [RS_336] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1412] (rows=158402938 width=135) - Conds:RS_1891._col0=RS_1620._col0(Inner),Output:["_col1"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1620] + Merge Join Operator [MERGEJOIN_1412] (rows=15995224 width=4) + Conds:RS_1861._col0=RS_1620._col0(Inner),Output:["_col1"] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1620] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] - <-Map 111 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1891] + <-Map 105 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1861] PartitionCols:_col0 - Select Operator [SEL_1890] (rows=144002668 width=135) + Select Operator [SEL_1860] (rows=143966864 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_1889] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_148_iws_i_item_sk_min) AND DynamicValue(RS_148_iws_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_148_iws_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_145_d3_d_date_sk_min) AND DynamicValue(RS_145_d3_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_145_d3_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_135] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk"] - <-Reducer 107 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1886] - Group By Operator [GBY_1885] (rows=1 width=12) + Filter Operator [FIL_1859] (rows=143966864 width=7) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_145_d3_d_date_sk_min) AND DynamicValue(RS_145_d3_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_145_d3_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_135] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk"] + <-Reducer 101 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1858] + Group By Operator [GBY_1857] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 102 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1637] + <-Map 96 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1637] Group By Operator [GBY_1632] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1621] (rows=8116 width=1119) + Select Operator [SEL_1621] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1615] - <-Reducer 77 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1888] - Group By Operator [GBY_1887] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 63 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1716] - Group By Operator [GBY_1710] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1696] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1681] <-Reducer 55 [SIMPLE_EDGE] SHUFFLE [RS_362] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1422] (rows=316788826 width=135) - Conds:RS_1770._col0=RS_1660._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_1422] (rows=7790806 width=98) + Conds:RS_1748._col0=RS_1660._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1660] PartitionCols:_col0 - Select Operator [SEL_1657] (rows=18262 width=1119) + Select Operator [SEL_1657] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_1656] (rows=18262 width=1119) + Filter Operator [FIL_1656] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_85] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 112 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1770] + TableScan [TS_85] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 106 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1748] PartitionCols:_col0 - Select Operator [SEL_1769] (rows=287989836 width=135) + Select Operator [SEL_1747] (rows=286549727 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1768] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_363_item_i_item_sk_min) AND DynamicValue(RS_363_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_363_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_364_item_i_item_sk_min) AND DynamicValue(RS_364_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_364_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_360_date_dim_d_date_sk_min) AND DynamicValue(RS_360_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_360_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_271] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_quantity","cs_list_price"] + Filter Operator [FIL_1746] (rows=286549727 width=123) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_364_item_i_item_sk_min) AND DynamicValue(RS_364_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_364_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_360_date_dim_d_date_sk_min) AND DynamicValue(RS_360_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_360_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_271] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_quantity","cs_list_price"] <-Reducer 58 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1754] - Group By Operator [GBY_1753] (rows=1 width=12) + BROADCAST [RS_1734] + Group By Operator [GBY_1733] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 53 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1668] Group By Operator [GBY_1665] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1661] (rows=18262 width=1119) + Select Operator [SEL_1661] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1657] - <-Reducer 81 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1767] - Group By Operator [GBY_1766] (rows=1 width=12) + <-Reducer 77 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1745] + Group By Operator [GBY_1744] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 80 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1765] - Group By Operator [GBY_1764] (rows=1 width=12) + <-Reducer 76 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1743] + Group By Operator [GBY_1742] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1763] (rows=254100 width=1436) + Select Operator [SEL_1741] (rows=362 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_1761] - <-Reducer 98 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1756] - Group By Operator [GBY_1755] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 63 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1718] - Group By Operator [GBY_1712] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1704] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1687] + Please refer to the previous Group By Operator [GBY_1739] <-Reducer 16 [CONTAINS] Reduce Output Operator [RS_1487] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_1486] (rows=2032776160 width=237) + Group By Operator [GBY_1486] (rows=304320 width=230) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L - Top N Key Operator [TNK_1485] (rows=406555232 width=237) + Top N Key Operator [TNK_1485] (rows=121728 width=220) keys:_col0, _col1, _col2, _col3, 0L,sort order:+++++,top n:100 - Select Operator [SEL_1483] (rows=58081078 width=264) + Select Operator [SEL_1483] (rows=40576 width=218) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_1482] (rows=58081078 width=264) + Filter Operator [FIL_1482] (rows=40576 width=243) predicate:(_col5 > _col1) - Merge Join Operator [MERGEJOIN_1481] (rows=174243235 width=264) + Merge Join Operator [MERGEJOIN_1481] (rows=121728 width=243) Conds:(Inner),(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1778] - Select Operator [SEL_1777] (rows=1 width=8) - Filter Operator [FIL_1776] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_1756] + Select Operator [SEL_1755] (rows=1 width=8) + Filter Operator [FIL_1754] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_1775] (rows=1 width=8) + Group By Operator [GBY_1753] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_1774] (rows=1 width=8) - Group By Operator [GBY_1773] (rows=1 width=8) + Select Operator [SEL_1752] (rows=1 width=8) + Group By Operator [GBY_1751] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Union 14 [CUSTOM_SIMPLE_EDGE] <-Reducer 13 [CONTAINS] Reduce Output Operator [RS_1480] Group By Operator [GBY_1479] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1478] (rows=1108786976 width=108) + Select Operator [SEL_1478] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1476] (rows=633595212 width=88) + Select Operator [SEL_1476] (rows=61115434 width=2) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1475] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_1475] (rows=61115434 width=2) Conds:RS_1646._col0=RS_1628._col0(Inner),Output:["_col1"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1628] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1628] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] <-Map 1 [SIMPLE_EDGE] vectorized @@ -920,250 +866,239 @@ Stage-0 Reduce Output Operator [RS_1505] Group By Operator [GBY_1504] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1503] (rows=1108786976 width=108) + Select Operator [SEL_1503] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1501] (rows=316788826 width=135) + Select Operator [SEL_1501] (rows=31836679 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1500] (rows=316788826 width=135) - Conds:RS_1822._col0=RS_1810._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1500] (rows=31836679 width=3) + Conds:RS_1798._col0=RS_1786._col0(Inner),Output:["_col1"] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1810] + SHUFFLE [RS_1786] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1803] + Please refer to the previous Select Operator [SEL_1779] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1822] + SHUFFLE [RS_1798] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1819] + Please refer to the previous Select Operator [SEL_1795] <-Reducer 36 [CONTAINS] Reduce Output Operator [RS_1541] Group By Operator [GBY_1540] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1539] (rows=1108786976 width=108) + Select Operator [SEL_1539] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1537] (rows=158402938 width=135) + Select Operator [SEL_1537] (rows=15995224 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1536] (rows=158402938 width=135) - Conds:RS_1850._col0=RS_1838._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1536] (rows=15995224 width=3) + Conds:RS_1826._col0=RS_1814._col0(Inner),Output:["_col1"] <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1838] + SHUFFLE [RS_1814] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1831] + Please refer to the previous Select Operator [SEL_1807] <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1850] + SHUFFLE [RS_1826] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1847] + Please refer to the previous Select Operator [SEL_1823] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1781] - Select Operator [SEL_1780] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_1759] + Select Operator [SEL_1758] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_1779] (rows=1 width=120) + Group By Operator [GBY_1757] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Union 31 [CUSTOM_SIMPLE_EDGE] <-Reducer 30 [CONTAINS] Reduce Output Operator [RS_1523] Group By Operator [GBY_1522] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1521] (rows=1108786976 width=108) + Select Operator [SEL_1521] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1519] (rows=316788826 width=135) + Select Operator [SEL_1519] (rows=31836679 width=110) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1518] (rows=316788826 width=135) - Conds:RS_1829._col0=RS_1811._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1518] (rows=31836679 width=110) + Conds:RS_1805._col0=RS_1787._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1811] + SHUFFLE [RS_1787] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1803] + Please refer to the previous Select Operator [SEL_1779] <-Map 47 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1829] + SHUFFLE [RS_1805] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1826] + Please refer to the previous Select Operator [SEL_1802] <-Reducer 42 [CONTAINS] Reduce Output Operator [RS_1559] Group By Operator [GBY_1558] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1557] (rows=1108786976 width=108) + Select Operator [SEL_1557] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1555] (rows=158402938 width=135) + Select Operator [SEL_1555] (rows=15995224 width=115) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1554] (rows=158402938 width=135) - Conds:RS_1857._col0=RS_1839._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1554] (rows=15995224 width=115) + Conds:RS_1833._col0=RS_1815._col0(Inner),Output:["_col1","_col2"] <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1839] + SHUFFLE [RS_1815] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1831] + Please refer to the previous Select Operator [SEL_1807] <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1857] + SHUFFLE [RS_1833] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1854] + Please refer to the previous Select Operator [SEL_1830] <-Reducer 46 [CONTAINS] Reduce Output Operator [RS_1577] Group By Operator [GBY_1576] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1575] (rows=1108786976 width=108) + Select Operator [SEL_1575] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1573] (rows=633595212 width=88) + Select Operator [SEL_1573] (rows=61115434 width=69) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1572] (rows=633595212 width=88) - Conds:RS_1864._col0=RS_1629._col0(Inner),Output:["_col1","_col2"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1629] + Merge Join Operator [MERGEJOIN_1572] (rows=61115434 width=69) + Conds:RS_1840._col0=RS_1629._col0(Inner),Output:["_col1","_col2"] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1629] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1864] + SHUFFLE [RS_1840] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1861] + Please refer to the previous Select Operator [SEL_1837] <-Reducer 61 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1801] - Group By Operator [GBY_1800] (rows=174243235 width=135) + PARTITION_ONLY_SHUFFLE [RS_1777] + Group By Operator [GBY_1776] (rows=121728 width=131) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 60 [SIMPLE_EDGE] SHUFFLE [RS_559] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_558] (rows=348486471 width=135) + Group By Operator [GBY_558] (rows=121728 width=131) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_556] (rows=348486471 width=135) + Select Operator [SEL_556] (rows=875196 width=123) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_1445] (rows=348486471 width=135) - Conds:RS_552._col1=RS_1706._col0(Inner),RS_552._col1=RS_1791._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] + Merge Join Operator [MERGEJOIN_1445] (rows=875196 width=123) + Conds:RS_552._col1=RS_1701._col0(Inner),RS_552._col1=RS_1767._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1706] + SHUFFLE [RS_1701] PartitionCols:_col0 - Select Operator [SEL_1689] (rows=462000 width=1436) + Select Operator [SEL_1689] (rows=462000 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1680] (rows=462000 width=1436) + Filter Operator [FIL_1680] (rows=462000 width=15) predicate:i_item_sk is not null Please refer to the previous TableScan [TS_91] - <-Reducer 90 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1791] + <-Reducer 86 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1767] PartitionCols:_col0 - Group By Operator [GBY_1790] (rows=254100 width=1436) + Group By Operator [GBY_1766] (rows=362 width=4) Output:["_col0"],keys:KEY._col0 - <-Reducer 89 [SIMPLE_EDGE] + <-Reducer 85 [SIMPLE_EDGE] SHUFFLE [RS_546] PartitionCols:_col0 - Group By Operator [GBY_545] (rows=508200 width=1436) + Group By Operator [GBY_545] (rows=362 width=4) Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_1444] (rows=508200 width=1436) - Conds:RS_1705._col1, _col2, _col3=RS_1789._col0, _col1, _col2(Inner),Output:["_col0"] + Merge Join Operator [MERGEJOIN_1444] (rows=724 width=4) + Conds:RS_1700._col1, _col2, _col3=RS_1765._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1705] + SHUFFLE [RS_1700] PartitionCols:_col1, _col2, _col3 - Select Operator [SEL_1688] (rows=462000 width=1436) + Select Operator [SEL_1688] (rows=458612 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1679] (rows=462000 width=1436) + Filter Operator [FIL_1679] (rows=458612 width=15) predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null) Please refer to the previous TableScan [TS_91] - <-Reducer 88 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_1789] + <-Reducer 84 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_1765] PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_1788] (rows=1 width=108) + Select Operator [SEL_1764] (rows=1 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1787] (rows=1 width=108) + Filter Operator [FIL_1763] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1786] (rows=304916424 width=108) + Group By Operator [GBY_1762] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Union 87 [SIMPLE_EDGE] - <-Reducer 86 [CONTAINS] vectorized - Reduce Output Operator [RS_1900] + <-Union 83 [SIMPLE_EDGE] + <-Reducer 82 [CONTAINS] vectorized + Reduce Output Operator [RS_1870] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1899] (rows=609832849 width=108) + Group By Operator [GBY_1869] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1898] (rows=348477374 width=88) + Group By Operator [GBY_1868] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 82 [SIMPLE_EDGE] + <-Reducer 78 [SIMPLE_EDGE] SHUFFLE [RS_490] PartitionCols:_col0, _col1, _col2 Please refer to the previous Group By Operator [GBY_299] - <-Reducer 94 [CONTAINS] vectorized - Reduce Output Operator [RS_1906] + <-Reducer 90 [CONTAINS] vectorized + Reduce Output Operator [RS_1876] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1905] (rows=609832849 width=108) + Group By Operator [GBY_1875] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1904] (rows=174233858 width=135) + Group By Operator [GBY_1874] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 92 [SIMPLE_EDGE] + <-Reducer 88 [SIMPLE_EDGE] SHUFFLE [RS_510] PartitionCols:_col0, _col1, _col2 Please refer to the previous Group By Operator [GBY_319] - <-Reducer 97 [CONTAINS] vectorized - Reduce Output Operator [RS_1912] + <-Reducer 93 [CONTAINS] vectorized + Reduce Output Operator [RS_1882] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1911] (rows=609832849 width=108) + Group By Operator [GBY_1881] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1910] (rows=87121617 width=135) + Group By Operator [GBY_1880] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 95 [SIMPLE_EDGE] + <-Reducer 91 [SIMPLE_EDGE] SHUFFLE [RS_531] PartitionCols:_col0, _col1, _col2 Please refer to the previous Group By Operator [GBY_340] <-Reducer 59 [SIMPLE_EDGE] SHUFFLE [RS_552] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1437] (rows=158402938 width=135) - Conds:RS_1799._col0=RS_1662._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_1437] (rows=3942084 width=118) + Conds:RS_1775._col0=RS_1662._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1662] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1657] - <-Map 113 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1799] + <-Map 107 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1775] PartitionCols:_col0 - Select Operator [SEL_1798] (rows=144002668 width=135) + Select Operator [SEL_1774] (rows=143966864 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1797] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_553_item_i_item_sk_min) AND DynamicValue(RS_553_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_553_item_i_item_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_554_item_i_item_sk_min) AND DynamicValue(RS_554_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_554_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_550_date_dim_d_date_sk_min) AND DynamicValue(RS_550_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_550_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_461] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_quantity","ws_list_price"] + Filter Operator [FIL_1773] (rows=143966864 width=123) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_554_item_i_item_sk_min) AND DynamicValue(RS_554_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_554_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_550_date_dim_d_date_sk_min) AND DynamicValue(RS_550_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_550_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_461] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_quantity","ws_list_price"] <-Reducer 62 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1783] - Group By Operator [GBY_1782] (rows=1 width=12) + BROADCAST [RS_1761] + Group By Operator [GBY_1760] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 53 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1669] Group By Operator [GBY_1666] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1663] (rows=18262 width=1119) + Select Operator [SEL_1663] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1657] - <-Reducer 91 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1796] - Group By Operator [GBY_1795] (rows=1 width=12) + <-Reducer 87 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1772] + Group By Operator [GBY_1771] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 90 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1794] - Group By Operator [GBY_1793] (rows=1 width=12) + <-Reducer 86 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1770] + Group By Operator [GBY_1769] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1792] (rows=254100 width=1436) + Select Operator [SEL_1768] (rows=362 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_1790] - <-Reducer 99 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1785] - Group By Operator [GBY_1784] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 63 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1719] - Group By Operator [GBY_1713] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1707] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1689] + Please refer to the previous Group By Operator [GBY_1766] <-Reducer 5 [CONTAINS] Reduce Output Operator [RS_1461] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_1460] (rows=2032776160 width=237) + Group By Operator [GBY_1460] (rows=304320 width=230) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3, 0L - Top N Key Operator [TNK_1459] (rows=406555232 width=237) + Top N Key Operator [TNK_1459] (rows=121728 width=220) keys:_col0, _col1, _col2, _col3, 0L,sort order:+++++,top n:100 - Select Operator [SEL_1457] (rows=232318249 width=217) + Select Operator [SEL_1457] (rows=40576 width=220) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_1456] (rows=232318249 width=217) + Filter Operator [FIL_1456] (rows=40576 width=243) predicate:(_col5 > _col1) - Merge Join Operator [MERGEJOIN_1455] (rows=696954748 width=217) + Merge Join Operator [MERGEJOIN_1455] (rows=121728 width=243) Conds:(Inner),(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 25 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1655] - Select Operator [SEL_1654] (rows=1 width=120) + Select Operator [SEL_1654] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_1653] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -1172,56 +1107,56 @@ Stage-0 Reduce Output Operator [RS_1511] Group By Operator [GBY_1510] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1509] (rows=1108786976 width=108) + Select Operator [SEL_1509] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1507] (rows=316788826 width=135) + Select Operator [SEL_1507] (rows=31836679 width=110) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1506] (rows=316788826 width=135) - Conds:RS_1827._col0=RS_1806._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1506] (rows=31836679 width=110) + Conds:RS_1803._col0=RS_1782._col0(Inner),Output:["_col1","_col2"] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1806] + SHUFFLE [RS_1782] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1803] + Please refer to the previous Select Operator [SEL_1779] <-Map 47 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1827] + SHUFFLE [RS_1803] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1826] + Please refer to the previous Select Operator [SEL_1802] <-Reducer 39 [CONTAINS] Reduce Output Operator [RS_1547] Group By Operator [GBY_1546] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1545] (rows=1108786976 width=108) + Select Operator [SEL_1545] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1543] (rows=158402938 width=135) + Select Operator [SEL_1543] (rows=15995224 width=115) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1542] (rows=158402938 width=135) - Conds:RS_1855._col0=RS_1834._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_1542] (rows=15995224 width=115) + Conds:RS_1831._col0=RS_1810._col0(Inner),Output:["_col1","_col2"] <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1834] + SHUFFLE [RS_1810] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1831] + Please refer to the previous Select Operator [SEL_1807] <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1855] + SHUFFLE [RS_1831] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1854] + Please refer to the previous Select Operator [SEL_1830] <-Reducer 44 [CONTAINS] Reduce Output Operator [RS_1565] Group By Operator [GBY_1564] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col0)","count(_col0)"] - Select Operator [SEL_1563] (rows=1108786976 width=108) + Select Operator [SEL_1563] (rows=108947337 width=88) Output:["_col0"] - Select Operator [SEL_1561] (rows=633595212 width=88) + Select Operator [SEL_1561] (rows=61115434 width=69) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_1560] (rows=633595212 width=88) - Conds:RS_1862._col0=RS_1624._col0(Inner),Output:["_col1","_col2"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1624] + Merge Join Operator [MERGEJOIN_1560] (rows=61115434 width=69) + Conds:RS_1838._col0=RS_1624._col0(Inner),Output:["_col1","_col2"] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1624] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1862] + SHUFFLE [RS_1838] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1861] + Please refer to the previous Select Operator [SEL_1837] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1652] Select Operator [SEL_1651] (rows=1 width=8) @@ -1237,32 +1172,32 @@ Stage-0 Reduce Output Operator [RS_1493] Group By Operator [GBY_1492] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1491] (rows=1108786976 width=108) + Select Operator [SEL_1491] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1489] (rows=316788826 width=135) + Select Operator [SEL_1489] (rows=31836679 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1488] (rows=316788826 width=135) - Conds:RS_1820._col0=RS_1804._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1488] (rows=31836679 width=3) + Conds:RS_1796._col0=RS_1780._col0(Inner),Output:["_col1"] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1804] + SHUFFLE [RS_1780] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1803] + Please refer to the previous Select Operator [SEL_1779] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1820] + SHUFFLE [RS_1796] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1819] + Please refer to the previous Select Operator [SEL_1795] <-Reducer 2 [CONTAINS] Reduce Output Operator [RS_1454] Group By Operator [GBY_1453] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1452] (rows=1108786976 width=108) + Select Operator [SEL_1452] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1450] (rows=633595212 width=88) + Select Operator [SEL_1450] (rows=61115434 width=2) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1449] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_1449] (rows=61115434 width=2) Conds:RS_1644._col0=RS_1622._col0(Inner),Output:["_col1"] - <-Map 102 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1622] + <-Map 96 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1622] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1615] <-Map 1 [SIMPLE_EDGE] vectorized @@ -1273,151 +1208,155 @@ Stage-0 Reduce Output Operator [RS_1529] Group By Operator [GBY_1528] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_1527] (rows=1108786976 width=108) + Select Operator [SEL_1527] (rows=108947337 width=3) Output:["_col0"] - Select Operator [SEL_1525] (rows=158402938 width=135) + Select Operator [SEL_1525] (rows=15995224 width=3) Output:["_col0"] - Merge Join Operator [MERGEJOIN_1524] (rows=158402938 width=135) - Conds:RS_1848._col0=RS_1832._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_1524] (rows=15995224 width=3) + Conds:RS_1824._col0=RS_1808._col0(Inner),Output:["_col1"] <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1832] + SHUFFLE [RS_1808] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1831] + Please refer to the previous Select Operator [SEL_1807] <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1848] + SHUFFLE [RS_1824] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1847] + Please refer to the previous Select Operator [SEL_1823] <-Reducer 52 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1737] - Group By Operator [GBY_1736] (rows=696954748 width=88) + PARTITION_ONLY_SHUFFLE [RS_1717] + Group By Operator [GBY_1716] (rows=121728 width=131) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 51 [SIMPLE_EDGE] SHUFFLE [RS_180] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_179] (rows=1393909496 width=88) + Group By Operator [GBY_179] (rows=1672000 width=131) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_177] (rows=1393909496 width=88) + Select Operator [SEL_177] (rows=3344000 width=2758185417719) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_1415] (rows=1393909496 width=88) - Conds:RS_173._col1=RS_1697._col0(Inner),RS_173._col1=RS_1727._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] + Merge Join Operator [MERGEJOIN_1415] (rows=3344000 width=2758185417719) + Conds:RS_173._col1=RS_1694._col0(Inner),RS_173._col1=RS_1707._col0(Inner),Output:["_col2","_col3","_col8","_col9","_col10"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1697] + SHUFFLE [RS_1694] PartitionCols:_col0 - Select Operator [SEL_1682] (rows=462000 width=1436) + Select Operator [SEL_1682] (rows=462000 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1673] (rows=462000 width=1436) + Filter Operator [FIL_1673] (rows=462000 width=15) predicate:i_item_sk is not null Please refer to the previous TableScan [TS_91] <-Reducer 65 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1727] + PARTITION_ONLY_SHUFFLE [RS_1707] PartitionCols:_col0 - Group By Operator [GBY_1726] (rows=254100 width=1436) + Group By Operator [GBY_1706] (rows=362 width=4) Output:["_col0"],keys:KEY._col0 <-Reducer 64 [SIMPLE_EDGE] SHUFFLE [RS_167] PartitionCols:_col0 - Group By Operator [GBY_166] (rows=508200 width=1436) + Group By Operator [GBY_166] (rows=362 width=4) Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_1414] (rows=508200 width=1436) - Conds:RS_1690._col1, _col2, _col3=RS_1725._col0, _col1, _col2(Inner),Output:["_col0"] + Merge Join Operator [MERGEJOIN_1414] (rows=724 width=4) + Conds:RS_1690._col1, _col2, _col3=RS_1705._col0, _col1, _col2(Inner),Output:["_col0"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1690] + SHUFFLE [RS_1690] PartitionCols:_col1, _col2, _col3 - Please refer to the previous Select Operator [SEL_1681] + Select Operator [SEL_1681] (rows=458612 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_1672] (rows=458612 width=15) + predicate:(i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null) + Please refer to the previous TableScan [TS_91] <-Reducer 70 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_1725] + FORWARD [RS_1705] PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_1724] (rows=1 width=108) + Select Operator [SEL_1704] (rows=1 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1723] (rows=1 width=108) + Filter Operator [FIL_1703] (rows=1 width=20) predicate:(_col3 = 3L) - Group By Operator [GBY_1722] (rows=304916424 width=108) + Group By Operator [GBY_1702] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 69 [SIMPLE_EDGE] <-Reducer 68 [CONTAINS] vectorized - Reduce Output Operator [RS_1874] + Reduce Output Operator [RS_1848] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1873] (rows=609832849 width=108) + Group By Operator [GBY_1847] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1872] (rows=348477374 width=88) + Group By Operator [GBY_1846] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 67 [SIMPLE_EDGE] SHUFFLE [RS_111] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_110] (rows=696954748 width=88) + Group By Operator [GBY_110] (rows=365184 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 - Merge Join Operator [MERGEJOIN_1409] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_1409] (rows=60667254 width=11) Conds:RS_106._col1=RS_1691._col0(Inner),Output:["_col5","_col6","_col7"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1691] + SHUFFLE [RS_1691] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1681] - <-Reducer 101 [SIMPLE_EDGE] + <-Reducer 95 [SIMPLE_EDGE] SHUFFLE [RS_106] PartitionCols:_col1 Please refer to the previous Merge Join Operator [MERGEJOIN_1408] - <-Reducer 73 [CONTAINS] vectorized - Reduce Output Operator [RS_1884] + <-Reducer 72 [CONTAINS] vectorized + Reduce Output Operator [RS_1856] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1883] (rows=609832849 width=108) + Group By Operator [GBY_1855] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1882] (rows=174233858 width=135) + Group By Operator [GBY_1854] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 72 [SIMPLE_EDGE] + <-Reducer 71 [SIMPLE_EDGE] SHUFFLE [RS_131] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_130] (rows=348467716 width=135) + Group By Operator [GBY_130] (rows=243456 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 - Merge Join Operator [MERGEJOIN_1411] (rows=348467716 width=135) - Conds:RS_126._col1=RS_1693._col0(Inner),Output:["_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_1411] (rows=31603210 width=11) + Conds:RS_126._col1=RS_1692._col0(Inner),Output:["_col5","_col6","_col7"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1693] + SHUFFLE [RS_1692] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1681] - <-Reducer 104 [SIMPLE_EDGE] + <-Reducer 98 [SIMPLE_EDGE] SHUFFLE [RS_126] PartitionCols:_col1 Please refer to the previous Merge Join Operator [MERGEJOIN_1410] - <-Reducer 76 [CONTAINS] vectorized - Reduce Output Operator [RS_1894] + <-Reducer 74 [CONTAINS] vectorized + Reduce Output Operator [RS_1864] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_1893] (rows=609832849 width=108) + Group By Operator [GBY_1863] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_1892] (rows=87121617 width=135) + Group By Operator [GBY_1862] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 75 [SIMPLE_EDGE] + <-Reducer 73 [SIMPLE_EDGE] SHUFFLE [RS_152] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_151] (rows=174243235 width=135) + Group By Operator [GBY_151] (rows=121728 width=19) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7 - Merge Join Operator [MERGEJOIN_1413] (rows=174243235 width=135) - Conds:RS_147._col1=RS_1695._col0(Inner),Output:["_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_1413] (rows=15877926 width=11) + Conds:RS_147._col1=RS_1693._col0(Inner),Output:["_col5","_col6","_col7"] <-Map 63 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1695] + SHUFFLE [RS_1693] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1681] - <-Reducer 106 [SIMPLE_EDGE] + <-Reducer 100 [SIMPLE_EDGE] SHUFFLE [RS_147] PartitionCols:_col1 Please refer to the previous Merge Join Operator [MERGEJOIN_1412] <-Reducer 50 [SIMPLE_EDGE] SHUFFLE [RS_173] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1407] (rows=633595212 width=88) - Conds:RS_1735._col0=RS_1658._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_1407] (rows=15062131 width=4) + Conds:RS_1715._col0=RS_1658._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1658] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1657] <-Map 49 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1735] + SHUFFLE [RS_1715] PartitionCols:_col0 - Select Operator [SEL_1734] (rows=575995635 width=88) + Select Operator [SEL_1714] (rows=550076554 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_1733] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_174_item_i_item_sk_min) AND DynamicValue(RS_174_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_174_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_175_item_i_item_sk_min) AND DynamicValue(RS_175_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_175_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_171_date_dim_d_date_sk_min) AND DynamicValue(RS_171_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_171_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_82] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_quantity","ss_list_price"] + Filter Operator [FIL_1713] (rows=550076554 width=118) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_175_item_i_item_sk_min) AND DynamicValue(RS_175_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_175_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_171_date_dim_d_date_sk_min) AND DynamicValue(RS_171_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_171_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_82] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_quantity","ss_list_price"] <-Reducer 54 [BROADCAST_EDGE] vectorized BROADCAST [RS_1671] Group By Operator [GBY_1670] (rows=1 width=12) @@ -1426,29 +1365,18 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_1667] Group By Operator [GBY_1664] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1659] (rows=18262 width=1119) + Select Operator [SEL_1659] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_1657] <-Reducer 66 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1732] - Group By Operator [GBY_1731] (rows=1 width=12) + BROADCAST [RS_1712] + Group By Operator [GBY_1711] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 65 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1730] - Group By Operator [GBY_1729] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1728] (rows=254100 width=1436) - Output:["_col0"] - Please refer to the previous Group By Operator [GBY_1726] - <-Reducer 78 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1721] - Group By Operator [GBY_1720] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 63 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1717] - Group By Operator [GBY_1711] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_1710] + Group By Operator [GBY_1709] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1698] (rows=462000 width=1436) + Select Operator [SEL_1708] (rows=362 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1682] + Please refer to the previous Group By Operator [GBY_1706] diff --git a/ql/src/test/results/clientpositive/perf/tez/query15.q.out b/ql/src/test/results/clientpositive/perf/tez/query15.q.out index e1eca99d95..c6edf997aa 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query15.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query15.q.out @@ -53,73 +53,73 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_99] - Limit [LIM_98] (rows=100 width=135) + Limit [LIM_98] (rows=100 width=201) Number of rows:100 - Select Operator [SEL_97] (rows=174233858 width=135) + Select Operator [SEL_97] (rows=2555 width=201) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_96] - Group By Operator [GBY_95] (rows=174233858 width=135) + Group By Operator [GBY_95] (rows=2555 width=201) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Group By Operator [GBY_24] (rows=348467716 width=135) + Group By Operator [GBY_24] (rows=56210 width=201) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col4 - Top N Key Operator [TNK_44] (rows=348467716 width=135) + Top N Key Operator [TNK_44] (rows=20154874 width=279) keys:_col4,sort order:+,top n:100 - Select Operator [SEL_23] (rows=348467716 width=135) + Select Operator [SEL_23] (rows=20154874 width=279) Output:["_col4","_col7"] - Filter Operator [FIL_22] (rows=348467716 width=135) + Filter Operator [FIL_22] (rows=20154874 width=279) predicate:((_col3 = 'CA') or (_col3 = 'GA') or (_col3 = 'WA') or (_col7 > 500) or (substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792')) - Merge Join Operator [MERGEJOIN_77] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_77] (rows=20154874 width=279) Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_75] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_75] (rows=80000000 width=179) Conds:RS_80._col1=RS_83._col0(Inner),Output:["_col0","_col3","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_80] PartitionCols:_col1 - Select Operator [SEL_79] (rows=80000000 width=860) + Select Operator [SEL_79] (rows=80000000 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_78] (rows=80000000 width=860) + Filter Operator [FIL_78] (rows=80000000 width=8) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] + TableScan [TS_0] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_83] PartitionCols:_col0 - Select Operator [SEL_82] (rows=40000000 width=1014) + Select Operator [SEL_82] (rows=40000000 width=179) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_81] (rows=40000000 width=1014) + Filter Operator [FIL_81] (rows=40000000 width=179) predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_zip"] + TableScan [TS_3] (rows=40000000 width=179) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_76] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_76] (rows=20154874 width=107) Conds:RS_94._col0=RS_86._col0(Inner),Output:["_col1","_col2"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_86] PartitionCols:_col0 - Select Operator [SEL_85] (rows=18262 width=1119) + Select Operator [SEL_85] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_84] (rows=18262 width=1119) + Filter Operator [FIL_84] (rows=130 width=12) predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + TableScan [TS_9] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_94] PartitionCols:_col0 - Select Operator [SEL_93] (rows=287989836 width=135) + Select Operator [SEL_93] (rows=285117831 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_92] (rows=287989836 width=135) + Filter Operator [FIL_92] (rows=285117831 width=119) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_6] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_sales_price"] + TableScan [TS_6] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_91] Group By Operator [GBY_90] (rows=1 width=12) @@ -128,7 +128,7 @@ Stage-0 SHUFFLE [RS_89] Group By Operator [GBY_88] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_87] (rows=18262 width=1119) + Select Operator [SEL_87] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_85] diff --git a/ql/src/test/results/clientpositive/perf/tez/query16.q.out b/ql/src/test/results/clientpositive/perf/tez/query16.q.out index cbbd1faea9..1dcd7018ec 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query16.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query16.q.out @@ -61,16 +61,18 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) -Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 18 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE) +Map 17 <- Reducer 10 (BROADCAST_EDGE) +Reducer 10 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 19 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) @@ -80,150 +82,161 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_176] - Limit [LIM_175] (rows=1 width=344) + File Output Operator [FS_178] + Limit [LIM_177] (rows=1 width=240) Number of rows:100 - Select Operator [SEL_174] (rows=1 width=344) + Select Operator [SEL_176] (rows=1 width=240) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_173] - Select Operator [SEL_172] (rows=1 width=344) + SHUFFLE [RS_175] + Select Operator [SEL_174] (rows=1 width=240) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_171] (rows=1 width=344) + Group By Operator [GBY_173] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_170] - Group By Operator [GBY_169] (rows=1 width=344) + PARTITION_ONLY_SHUFFLE [RS_172] + Group By Operator [GBY_171] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_168] (rows=231905279 width=135) + Group By Operator [GBY_170] (rows=1 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_74] PartitionCols:_col0 - Group By Operator [GBY_73] (rows=231905279 width=135) + Group By Operator [GBY_73] (rows=1 width=228) Output:["_col0","_col2","_col3"],aggregations:["sum(_col5)","sum(_col6)"],keys:_col4 - Select Operator [SEL_42] (rows=231905279 width=135) + Select Operator [SEL_42] (rows=1 width=232) Output:["_col4","_col5","_col6"] - Filter Operator [FIL_41] (rows=231905279 width=135) + Filter Operator [FIL_41] (rows=1 width=232) predicate:_col14 is null - Merge Join Operator [MERGEJOIN_130] (rows=463810558 width=135) - Conds:RS_38._col4=RS_167._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] - <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_167] + Merge Join Operator [MERGEJOIN_130] (rows=5150256 width=201) + Conds:RS_38._col4=RS_169._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] + <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_169] PartitionCols:_col0 - Select Operator [SEL_166] (rows=14399440 width=106) + Select Operator [SEL_168] (rows=18238808 width=8) Output:["_col0","_col1"] - Group By Operator [GBY_165] (rows=14399440 width=106) + Group By Operator [GBY_167] (rows=18238808 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_164] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_166] PartitionCols:_col0 - Group By Operator [GBY_163] (rows=28798881 width=106) + Group By Operator [GBY_165] (rows=28798881 width=4) Output:["_col0"],keys:cr_order_number - Filter Operator [FIL_162] (rows=28798881 width=106) + Filter Operator [FIL_164] (rows=28798881 width=4) predicate:cr_order_number is not null - TableScan [TS_25] (rows=28798881 width=106) - default@catalog_returns,cr1,Tbl:COMPLETE,Col:NONE,Output:["cr_order_number"] + TableScan [TS_25] (rows=28798881 width=4) + default@catalog_returns,cr1,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_order_number"] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_38] PartitionCols:_col4 - Select Operator [SEL_37] (rows=421645953 width=135) + Select Operator [SEL_37] (rows=5150256 width=200) Output:["_col4","_col5","_col6"] - Merge Join Operator [MERGEJOIN_129] (rows=421645953 width=135) - Conds:RS_34._col4=RS_161._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_161] - PartitionCols:_col0 - Group By Operator [GBY_160] (rows=287989836 width=135) - Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_159] (rows=287989836 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=287989836 width=135) - predicate:(cs_order_number is not null and cs_warehouse_sk is not null) - TableScan [TS_22] (rows=287989836 width=135) - default@catalog_sales,cs2,Tbl:COMPLETE,Col:NONE,Output:["cs_warehouse_sk","cs_order_number"] + Merge Join Operator [MERGEJOIN_129] (rows=5150256 width=202) + Conds:RS_34._col4=RS_163._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_128] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_128] (rows=5150256 width=200) Conds:RS_18._col2=RS_149._col0(Inner),Output:["_col3","_col4","_col5","_col6"] - <-Map 14 [SIMPLE_EDGE] vectorized + <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_149] PartitionCols:_col0 - Select Operator [SEL_148] (rows=60 width=2045) + Select Operator [SEL_148] (rows=10 width=102) Output:["_col0"] - Filter Operator [FIL_147] (rows=60 width=2045) + Filter Operator [FIL_147] (rows=10 width=102) predicate:((cc_county) IN ('Ziebach County', 'Levy County', 'Huron County', 'Franklin Parish', 'Daviess County') and cc_call_center_sk is not null) - TableScan [TS_9] (rows=60 width=2045) - default@call_center,call_center,Tbl:COMPLETE,Col:NONE,Output:["cc_call_center_sk","cc_county"] + TableScan [TS_9] (rows=60 width=102) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_county"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_127] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_127] (rows=30901534 width=230) Conds:RS_15._col1=RS_141._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] - <-Map 12 [SIMPLE_EDGE] vectorized + <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_141] PartitionCols:_col0 - Select Operator [SEL_140] (rows=20000000 width=1014) + Select Operator [SEL_140] (rows=784314 width=90) Output:["_col0"] - Filter Operator [FIL_139] (rows=20000000 width=1014) + Filter Operator [FIL_139] (rows=784314 width=90) predicate:((ca_state = 'NY') and ca_address_sk is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + TableScan [TS_6] (rows=40000000 width=90) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_126] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_126] (rows=31519516 width=234) Conds:RS_157._col0=RS_133._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] - <-Map 10 [SIMPLE_EDGE] vectorized + <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_133] PartitionCols:_col0 - Select Operator [SEL_132] (rows=8116 width=1119) + Select Operator [SEL_132] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_131] (rows=8116 width=1119) + Filter Operator [FIL_131] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-04-01 00:00:00' AND TIMESTAMP'2001-05-31 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_156] (rows=287989836 width=135) + Select Operator [SEL_156] (rows=283695062 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_155] (rows=287989836 width=135) + Filter Operator [FIL_155] (rows=283695062 width=243) predicate:((cs_call_center_sk BETWEEN DynamicValue(RS_19_call_center_cc_call_center_sk_min) AND DynamicValue(RS_19_call_center_cc_call_center_sk_max) and in_bloom_filter(cs_call_center_sk, DynamicValue(RS_19_call_center_cc_call_center_sk_bloom_filter))) and (cs_ship_addr_sk BETWEEN DynamicValue(RS_16_customer_address_ca_address_sk_min) AND DynamicValue(RS_16_customer_address_ca_address_sk_max) and in_bloom_filter(cs_ship_addr_sk, DynamicValue(RS_16_customer_address_ca_address_sk_bloom_filter))) and (cs_ship_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_call_center_sk is not null and cs_order_number is not null and cs_ship_addr_sk is not null and cs_ship_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,cs1,Tbl:COMPLETE,Col:NONE,Output:["cs_ship_date_sk","cs_ship_addr_sk","cs_call_center_sk","cs_warehouse_sk","cs_order_number","cs_ext_ship_cost","cs_net_profit"] - <-Reducer 11 [BROADCAST_EDGE] vectorized + TableScan [TS_0] (rows=287989836 width=243) + default@catalog_sales,cs1,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_ship_date_sk","cs_ship_addr_sk","cs_call_center_sk","cs_warehouse_sk","cs_order_number","cs_ext_ship_cost","cs_net_profit"] + <-Reducer 12 [BROADCAST_EDGE] vectorized BROADCAST [RS_138] Group By Operator [GBY_137] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_136] Group By Operator [GBY_135] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_134] (rows=8116 width=1119) + Select Operator [SEL_134] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_132] - <-Reducer 13 [BROADCAST_EDGE] vectorized + <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_146] Group By Operator [GBY_145] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_144] Group By Operator [GBY_143] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_142] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_142] (rows=784314 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_140] - <-Reducer 15 [BROADCAST_EDGE] vectorized + <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_154] Group By Operator [GBY_153] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_152] Group By Operator [GBY_151] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_150] (rows=60 width=2045) + Select Operator [SEL_150] (rows=10 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_148] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_163] + PartitionCols:_col0 + Group By Operator [GBY_162] (rows=286548719 width=7) + Output:["_col0","_col1"],keys:_col0, _col1 + Select Operator [SEL_161] (rows=286548719 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_160] (rows=286548719 width=7) + predicate:((cs_order_number BETWEEN DynamicValue(RS_34_cs1_cs_order_number_min) AND DynamicValue(RS_34_cs1_cs_order_number_max) and in_bloom_filter(cs_order_number, DynamicValue(RS_34_cs1_cs_order_number_bloom_filter))) and cs_order_number is not null and cs_warehouse_sk is not null) + TableScan [TS_22] (rows=287989836 width=7) + default@catalog_sales,cs2,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_warehouse_sk","cs_order_number"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_159] + Group By Operator [GBY_158] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_116] + Group By Operator [GBY_115] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_114] (rows=5150256 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_128] diff --git a/ql/src/test/results/clientpositive/perf/tez/query17.q.out b/ql/src/test/results/clientpositive/perf/tez/query17.q.out index 6b3549216c..7891f35f49 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query17.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query17.q.out @@ -89,20 +89,20 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 14 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Map 18 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Reducer 10 <- Map 18 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) -Reducer 12 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 19 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 12 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 20 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 3 <- Map 18 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 20 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 5 <- Map 21 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) @@ -112,192 +112,189 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_270] - Limit [LIM_269] (rows=100 width=88) + File Output Operator [FS_263] + Limit [LIM_262] (rows=100 width=466) Number of rows:100 - Select Operator [SEL_268] (rows=421657640 width=88) + Select Operator [SEL_261] (rows=4815969644 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_267] - Select Operator [SEL_266] (rows=421657640 width=88) + SHUFFLE [RS_260] + Select Operator [SEL_259] (rows=4815969644 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Group By Operator [GBY_265] (rows=421657640 width=88) + Group By Operator [GBY_258] (rows=4815969644 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","count(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_50] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_49] (rows=843315281 width=88) + Group By Operator [GBY_49] (rows=4815969644 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(_col3)","sum(_col3)","sum(_col7)","sum(_col6)","count(_col4)","sum(_col4)","sum(_col9)","sum(_col8)","count(_col5)","sum(_col5)","sum(_col11)","sum(_col10)"],keys:_col0, _col1, _col2 - Top N Key Operator [TNK_93] (rows=843315281 width=88) + Top N Key Operator [TNK_93] (rows=4815969644 width=381) keys:_col0, _col1, _col2,sort order:+++,top n:100 - Select Operator [SEL_47] (rows=843315281 width=88) + Select Operator [SEL_47] (rows=4815969644 width=381) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Merge Join Operator [MERGEJOIN_213] (rows=843315281 width=88) - Conds:RS_44._col3=RS_251._col0(Inner),Output:["_col5","_col9","_col10","_col14","_col21","_col25"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_251] + Merge Join Operator [MERGEJOIN_213] (rows=4815969644 width=381) + Conds:RS_44._col3=RS_257._col0(Inner),Output:["_col5","_col9","_col10","_col14","_col21","_col25"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_257] PartitionCols:_col0 - Select Operator [SEL_250] (rows=1704 width=1910) + Select Operator [SEL_256] (rows=1704 width=90) Output:["_col0","_col1"] - Filter Operator [FIL_249] (rows=1704 width=1910) + Filter Operator [FIL_255] (rows=1704 width=90) predicate:s_store_sk is not null - TableScan [TS_32] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] + TableScan [TS_32] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_212] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_212] (rows=4815969644 width=299) Conds:RS_41._col1, _col2, _col4=RS_42._col7, _col8, _col9(Inner),Output:["_col3","_col5","_col9","_col10","_col14","_col21"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col7, _col8, _col9 - Merge Join Operator [MERGEJOIN_211] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_211] (rows=540026342 width=19) Conds:RS_28._col2, _col1=RS_29._col1, _col2(Inner),Output:["_col3","_col7","_col8","_col9","_col10"] - <-Reducer 13 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_29] - PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_210] (rows=63350266 width=77) - Conds:RS_242._col0=RS_224._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_224] - PartitionCols:_col0 - Select Operator [SEL_219] (rows=73049 width=1119) - Output:["_col0"] - Filter Operator [FIL_216] (rows=73049 width=1119) - predicate:((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_quarter_name"] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_242] - PartitionCols:_col0 - Select Operator [SEL_241] (rows=57591150 width=77) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_240] (rows=57591150 width=77) - predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) - TableScan [TS_15] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_28] + PARTITION_ONLY_SHUFFLE [RS_28] PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_209] (rows=316788826 width=135) - Conds:RS_264._col0=RS_222._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_209] (rows=14254135 width=11) + Conds:RS_244._col0=RS_222._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_222] PartitionCols:_col0 - Select Operator [SEL_218] (rows=73049 width=1119) + Select Operator [SEL_218] (rows=3652 width=94) Output:["_col0"] - Filter Operator [FIL_215] (rows=73049 width=1119) + Filter Operator [FIL_215] (rows=3652 width=94) predicate:((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) - Please refer to the previous TableScan [TS_3] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_264] + TableScan [TS_3] (rows=73049 width=94) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_quarter_name"] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_244] PartitionCols:_col0 - Select Operator [SEL_263] (rows=287989836 width=135) + Select Operator [SEL_243] (rows=285117831 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_262] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_29_store_returns_sr_customer_sk_min) AND DynamicValue(RS_29_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_29_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_29_store_returns_sr_item_sk_min) AND DynamicValue(RS_29_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_29_store_returns_sr_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_26_d3_d_date_sk_min) AND DynamicValue(RS_26_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_26_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_9] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_245] - Group By Operator [GBY_243] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + Filter Operator [FIL_242] (rows=285117831 width=15) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_29_store_returns_sr_customer_sk_min) AND DynamicValue(RS_29_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_29_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_29_store_returns_sr_item_sk_min) AND DynamicValue(RS_29_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_29_store_returns_sr_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_26_d3_d_date_sk_min) AND DynamicValue(RS_26_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_26_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_9] (rows=287989836 width=15) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_236] + Group By Operator [GBY_234] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_111] Group By Operator [GBY_110] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_109] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_109] (rows=2681277 width=8) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_210] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_248] - Group By Operator [GBY_246] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + Merge Join Operator [MERGEJOIN_210] (rows=2681277 width=10) + Conds:RS_233._col0=RS_224._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_224] + PartitionCols:_col0 + Select Operator [SEL_219] (rows=3652 width=94) + Output:["_col0"] + Filter Operator [FIL_216] (rows=3652 width=94) + predicate:((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) + Please refer to the previous TableScan [TS_3] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_233] + PartitionCols:_col0 + Select Operator [SEL_232] (rows=53632139 width=19) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_231] (rows=53632139 width=19) + predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) + TableScan [TS_15] (rows=57591150 width=19) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_241] + Group By Operator [GBY_239] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_126] Group By Operator [GBY_125] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_124] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_124] (rows=2681277 width=2) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_210] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_239] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_238] Group By Operator [GBY_237] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_236] - Group By Operator [GBY_235] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_234] (rows=462000 width=1436) - Output:["_col0"] - Select Operator [SEL_232] (rows=462000 width=1436) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_231] (rows=462000 width=1436) - predicate:i_item_sk is not null - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_261] - Group By Operator [GBY_260] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_228] Group By Operator [GBY_226] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_223] (rows=73049 width=1119) + Select Operator [SEL_223] (rows=3652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_218] + <-Reducer 15 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_29] + PartitionCols:_col1, _col2 + Please refer to the previous Merge Join Operator [MERGEJOIN_210] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_208] (rows=696954748 width=88) - Conds:RS_38._col1=RS_233._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col9","_col10"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_233] + Merge Join Operator [MERGEJOIN_208] (rows=27749405 width=294) + Conds:RS_38._col1=RS_254._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col9","_col10"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_254] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_232] + Select Operator [SEL_253] (rows=462000 width=288) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_252] (rows=462000 width=288) + predicate:i_item_sk is not null + TableScan [TS_6] (rows=462000 width=288) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_207] (rows=633595212 width=88) - Conds:RS_259._col0=RS_220._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_207] (rows=27749405 width=10) + Conds:RS_251._col0=RS_220._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_220] PartitionCols:_col0 - Select Operator [SEL_217] (rows=36524 width=1119) + Select Operator [SEL_217] (rows=101 width=94) Output:["_col0"] - Filter Operator [FIL_214] (rows=36524 width=1119) + Filter Operator [FIL_214] (rows=101 width=94) predicate:((d_quarter_name = '2000Q1') and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_259] + SHUFFLE [RS_251] PartitionCols:_col0 - Select Operator [SEL_258] (rows=575995635 width=88) + Select Operator [SEL_250] (rows=501694138 width=23) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_257] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_29_store_returns_sr_customer_sk_min) AND DynamicValue(RS_29_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_29_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_store_returns_sr_item_sk_min) AND DynamicValue(RS_29_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_45_store_s_store_sk_min) AND DynamicValue(RS_45_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_45_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_244] - Please refer to the previous Group By Operator [GBY_243] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_247] - Please refer to the previous Group By Operator [GBY_246] + Filter Operator [FIL_249] (rows=501694138 width=23) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_28_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_28_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_28_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_29_store_returns_sr_customer_sk_min) AND DynamicValue(RS_29_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_29_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_28_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_28_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_28_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_store_returns_sr_item_sk_min) AND DynamicValue(RS_29_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_store_returns_sr_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_0] (rows=575995635 width=23) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_235] + Please refer to the previous Group By Operator [GBY_234] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_238] - Please refer to the previous Group By Operator [GBY_237] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_256] - Group By Operator [GBY_255] (rows=1 width=12) + BROADCAST [RS_240] + Please refer to the previous Group By Operator [GBY_239] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_246] + Group By Operator [GBY_245] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 10 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_116] + Group By Operator [GBY_115] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_114] (rows=14254135 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_209] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_248] + Group By Operator [GBY_247] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_254] - Group By Operator [GBY_253] (rows=1 width=12) + <-Reducer 10 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_131] + Group By Operator [GBY_130] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_252] (rows=1704 width=1910) + Select Operator [SEL_129] (rows=14254135 width=7) Output:["_col0"] - Please refer to the previous Select Operator [SEL_250] + Please refer to the previous Merge Join Operator [MERGEJOIN_209] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_230] Group By Operator [GBY_229] (rows=1 width=12) @@ -306,7 +303,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_227] Group By Operator [GBY_225] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_221] (rows=36524 width=1119) + Select Operator [SEL_221] (rows=101 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_217] diff --git a/ql/src/test/results/clientpositive/perf/tez/query18.q.out b/ql/src/test/results/clientpositive/perf/tez/query18.q.out index da5d3b1883..58b0940dfa 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query18.q.out @@ -67,165 +67,165 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 9 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE) -Reducer 10 <- Map 13 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 11 <- Map 15 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 17 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Map 10 <- Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 12 <- Map 16 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_187] - Limit [LIM_186] (rows=100 width=135) + File Output Operator [FS_184] + Limit [LIM_183] (rows=100 width=1165) Number of rows:100 - Select Operator [SEL_185] (rows=1054114882 width=135) + Select Operator [SEL_182] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_184] - Select Operator [SEL_183] (rows=1054114882 width=135) + SHUFFLE [RS_181] + Select Operator [SEL_180] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_182] (rows=1054114882 width=135) + Group By Operator [GBY_179] (rows=10969055 width=1229) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)","sum(VALUE._col8)","count(VALUE._col9)","sum(VALUE._col10)","count(VALUE._col11)","sum(VALUE._col12)","count(VALUE._col13)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_42] (rows=2108229765 width=135) + Group By Operator [GBY_42] (rows=10969055 width=1229) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col6)","count(_col6)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)","sum(_col9)","count(_col9)","sum(_col10)","count(_col10)"],keys:_col0, _col1, _col2, _col3, 0L - Select Operator [SEL_40] (rows=421645953 width=135) + Select Operator [SEL_40] (rows=2193811 width=618) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Merge Join Operator [MERGEJOIN_145] (rows=421645953 width=135) + Merge Join Operator [MERGEJOIN_145] (rows=2193811 width=618) Conds:RS_37._col0=RS_38._col3(Inner),Output:["_col4","_col6","_col7","_col8","_col11","_col16","_col17","_col18","_col19","_col20","_col26"] - <-Reducer 12 [SIMPLE_EDGE] + <-Reducer 3 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_37] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_141] (rows=4959744 width=287) + Conds:RS_34._col1=RS_154._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_154] + PartitionCols:_col0 + Select Operator [SEL_153] (rows=1861800 width=4) + Output:["_col0"] + Filter Operator [FIL_152] (rows=1861800 width=4) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=4) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_140] (rows=4890586 width=290) + Conds:RS_148._col2=RS_151._col0(Inner),Output:["_col0","_col1","_col4","_col6","_col7","_col8"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_148] + PartitionCols:_col2 + Select Operator [SEL_147] (rows=35631408 width=19) + Output:["_col0","_col1","_col2","_col4"] + Filter Operator [FIL_146] (rows=35631408 width=19) + predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=19) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] + PartitionCols:_col0 + Select Operator [SEL_150] (rows=5490196 width=285) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_149] (rows=5490196 width=285) + predicate:((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and ca_address_sk is not null) + TableScan [TS_3] (rows=40000000 width=285) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state","ca_country"] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col3 - Select Operator [SEL_30] (rows=383314495 width=135) + Select Operator [SEL_30] (rows=15983481 width=529) Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col16"] - Merge Join Operator [MERGEJOIN_144] (rows=383314495 width=135) - Conds:RS_27._col3=RS_173._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col14","_col16"] - <-Map 17 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_173] + Merge Join Operator [MERGEJOIN_144] (rows=15983481 width=529) + Conds:RS_27._col3=RS_178._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col14","_col16"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_178] PartitionCols:_col0 - Select Operator [SEL_172] (rows=462000 width=1436) + Select Operator [SEL_177] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_171] (rows=462000 width=1436) + Filter Operator [FIL_176] (rows=462000 width=104) predicate:i_item_sk is not null - TableScan [TS_18] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] - <-Reducer 11 [SIMPLE_EDGE] + TableScan [TS_18] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_143] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_143] (rows=15983481 width=433) Conds:RS_24._col2=RS_165._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col14"] - <-Map 15 [SIMPLE_EDGE] vectorized + <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_165] PartitionCols:_col0 - Select Operator [SEL_164] (rows=465450 width=385) + Select Operator [SEL_164] (rows=103433 width=184) Output:["_col0","_col3"] - Filter Operator [FIL_163] (rows=465450 width=385) + Filter Operator [FIL_163] (rows=103433 width=187) predicate:((cd_education_status = 'College') and (cd_gender = 'M') and cd_demo_sk is not null) - TableScan [TS_15] (rows=1861800 width=385) - default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] - <-Reducer 10 [SIMPLE_EDGE] + TableScan [TS_15] (rows=1861800 width=187) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_142] (rows=316788826 width=135) - Conds:RS_181._col0=RS_157._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 13 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_142] (rows=100578970 width=459) + Conds:RS_175._col0=RS_157._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 14 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_156] (rows=36524 width=1119) + Select Operator [SEL_156] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_155] (rows=36524 width=1119) + Filter Operator [FIL_155] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_12] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_181] + TableScan [TS_12] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_175] PartitionCols:_col0 - Select Operator [SEL_180] (rows=287989836 width=135) + Select Operator [SEL_174] (rows=283692098 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_179] (rows=287989836 width=135) - predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_25_cd1_cd_demo_sk_min) AND DynamicValue(RS_25_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_25_cd1_cd_demo_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_28_item_i_item_sk_min) AND DynamicValue(RS_28_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_28_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_9] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_bill_cdemo_sk","cs_item_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt","cs_net_profit"] - <-Reducer 14 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_173] (rows=283692098 width=466) + predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_25_cd1_cd_demo_sk_min) AND DynamicValue(RS_25_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_25_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_37_customer_c_customer_sk_min) AND DynamicValue(RS_37_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_37_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_9] (rows=287989836 width=466) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_bill_cdemo_sk","cs_item_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt","cs_net_profit"] + <-Reducer 15 [BROADCAST_EDGE] vectorized BROADCAST [RS_162] Group By Operator [GBY_161] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_160] Group By Operator [GBY_159] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_158] (rows=36524 width=1119) + Select Operator [SEL_158] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_156] - <-Reducer 16 [BROADCAST_EDGE] vectorized + <-Reducer 17 [BROADCAST_EDGE] vectorized BROADCAST [RS_170] Group By Operator [GBY_169] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_168] Group By Operator [GBY_167] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_166] (rows=465450 width=385) + Select Operator [SEL_166] (rows=103433 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_164] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_178] - Group By Operator [GBY_177] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_176] - Group By Operator [GBY_175] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_174] (rows=462000 width=1436) + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_172] + Group By Operator [GBY_171] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4890586)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_126] + Group By Operator [GBY_125] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4890586)"] + Select Operator [SEL_124] (rows=4959744 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_172] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_37] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_141] (rows=96800003 width=860) - Conds:RS_34._col1=RS_154._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_154] - PartitionCols:_col0 - Select Operator [SEL_153] (rows=1861800 width=385) - Output:["_col0"] - Filter Operator [FIL_152] (rows=1861800 width=385) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_140] (rows=88000001 width=860) - Conds:RS_148._col2=RS_151._col0(Inner),Output:["_col0","_col1","_col4","_col6","_col7","_col8"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] - PartitionCols:_col2 - Select Operator [SEL_147] (rows=80000000 width=860) - Output:["_col0","_col1","_col2","_col4"] - Filter Operator [FIL_146] (rows=80000000 width=860) - predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_151] - PartitionCols:_col0 - Select Operator [SEL_150] (rows=40000000 width=1014) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_149] (rows=40000000 width=1014) - predicate:((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_state","ca_country"] + Please refer to the previous Merge Join Operator [MERGEJOIN_141] diff --git a/ql/src/test/results/clientpositive/perf/tez/query19.q.out b/ql/src/test/results/clientpositive/perf/tez/query19.q.out index 7e7298d00f..ba566bdfb5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query19.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query19.q.out @@ -49,162 +49,138 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 9 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Reducer 10 <- Map 12 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 11 <- Map 14 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Map 8 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) +Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 11 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_164] - Limit [LIM_163] (rows=100 width=88) + File Output Operator [FS_157] + Limit [LIM_156] (rows=100 width=419) Number of rows:100 - Select Operator [SEL_162] (rows=421657640 width=88) + Select Operator [SEL_155] (rows=2098703 width=418) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_161] - Select Operator [SEL_160] (rows=421657640 width=88) + SHUFFLE [RS_154] + Select Operator [SEL_153] (rows=2098703 width=418) Output:["_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_159] (rows=421657640 width=88) + Group By Operator [GBY_152] (rows=2098703 width=314) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_36] (rows=843315281 width=88) + Group By Operator [GBY_36] (rows=2098703 width=314) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col8)"],keys:_col14, _col13, _col15, _col16 - Select Operator [SEL_35] (rows=843315281 width=88) + Select Operator [SEL_35] (rows=2098703 width=380) Output:["_col8","_col13","_col14","_col15","_col16"] - Filter Operator [FIL_34] (rows=843315281 width=88) + Filter Operator [FIL_34] (rows=2098703 width=380) predicate:(substr(_col3, 1, 5) <> substr(_col19, 1, 5)) - Merge Join Operator [MERGEJOIN_123] (rows=843315281 width=88) - Conds:RS_31._col7=RS_150._col0(Inner),Output:["_col3","_col8","_col13","_col14","_col15","_col16","_col19"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_150] + Merge Join Operator [MERGEJOIN_123] (rows=2098703 width=380) + Conds:RS_31._col7=RS_151._col0(Inner),Output:["_col3","_col8","_col13","_col14","_col15","_col16","_col19"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] PartitionCols:_col0 - Select Operator [SEL_149] (rows=1704 width=1910) + Select Operator [SEL_150] (rows=1704 width=93) Output:["_col0","_col1"] - Filter Operator [FIL_148] (rows=1704 width=1910) + Filter Operator [FIL_149] (rows=1704 width=93) predicate:s_store_sk is not null - TableScan [TS_22] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_zip"] + TableScan [TS_22] (rows=1704 width=93) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_zip"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_122] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_122] (rows=2098703 width=291) Conds:RS_28._col0=RS_29._col2(Inner),Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col16"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_28] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_119] (rows=88000001 width=860) - Conds:RS_126._col1=RS_129._col0(Inner),Output:["_col0","_col3"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] - PartitionCols:_col1 - Select Operator [SEL_125] (rows=80000000 width=860) - Output:["_col0","_col1"] - Filter Operator [FIL_124] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_129] - PartitionCols:_col0 - Select Operator [SEL_128] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_127] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_zip"] - <-Reducer 11 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_121] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_121] (rows=2098703 width=202) Conds:RS_18._col1=RS_140._col0(Inner),Output:["_col2","_col3","_col4","_col9","_col10","_col11","_col12"] - <-Map 14 [SIMPLE_EDGE] vectorized + <-Map 13 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_140] PartitionCols:_col0 - Select Operator [SEL_139] (rows=231000 width=1436) + Select Operator [SEL_139] (rows=7333 width=210) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_138] (rows=231000 width=1436) + Filter Operator [FIL_138] (rows=7333 width=210) predicate:((i_manager_id = 7) and i_item_sk is not null) - TableScan [TS_12] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id","i_manufact","i_manager_id"] - <-Reducer 10 [SIMPLE_EDGE] + TableScan [TS_12] (rows=462000 width=210) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id","i_manufact","i_manager_id"] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_120] (rows=633595212 width=88) - Conds:RS_158._col0=RS_132._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 12 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_132] + Merge Join Operator [MERGEJOIN_120] (rows=13737330 width=4) + Conds:RS_148._col0=RS_132._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_132] PartitionCols:_col0 - Select Operator [SEL_131] (rows=18262 width=1119) + Select Operator [SEL_131] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_130] (rows=18262 width=1119) + Filter Operator [FIL_130] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_158] + TableScan [TS_9] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_148] PartitionCols:_col0 - Select Operator [SEL_157] (rows=575995635 width=88) + Select Operator [SEL_147] (rows=501694138 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_156] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_28_customer_c_customer_sk_min) AND DynamicValue(RS_28_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_28_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_32_store_s_store_sk_min) AND DynamicValue(RS_32_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_32_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ext_sales_price"] - <-Reducer 13 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_146] (rows=501694138 width=122) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ext_sales_price"] + <-Reducer 12 [BROADCAST_EDGE] vectorized BROADCAST [RS_137] Group By Operator [GBY_136] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_135] + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_135] Group By Operator [GBY_134] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_133] (rows=18262 width=1119) + Select Operator [SEL_133] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_131] - <-Reducer 15 [BROADCAST_EDGE] vectorized + <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_145] Group By Operator [GBY_144] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_143] Group By Operator [GBY_142] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_141] (rows=231000 width=1436) + Select Operator [SEL_141] (rows=7333 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_139] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_155] - Group By Operator [GBY_154] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_153] - Group By Operator [GBY_152] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_151] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_149] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_147] - Group By Operator [GBY_146] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_96] - Group By Operator [GBY_95] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] - Select Operator [SEL_94] (rows=88000001 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_119] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_28] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_119] (rows=80000000 width=93) + Conds:RS_126._col1=RS_129._col0(Inner),Output:["_col0","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_126] + PartitionCols:_col1 + Select Operator [SEL_125] (rows=80000000 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_124] (rows=80000000 width=8) + predicate:(c_current_addr_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_129] + PartitionCols:_col0 + Select Operator [SEL_128] (rows=40000000 width=93) + Output:["_col0","_col1"] + Filter Operator [FIL_127] (rows=40000000 width=93) + predicate:ca_address_sk is not null + TableScan [TS_3] (rows=40000000 width=93) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_zip"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query2.q.out b/ql/src/test/results/clientpositive/perf/tez/query2.q.out index e2021f9b5f..052d312afc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query2.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query2.q.out @@ -119,161 +119,94 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 9 (BROADCAST_EDGE), Union 2 (CONTAINS) -Map 15 <- Reducer 13 (BROADCAST_EDGE), Union 16 (CONTAINS) -Map 17 <- Reducer 13 (BROADCAST_EDGE), Union 16 (CONTAINS) -Map 7 <- Reducer 9 (BROADCAST_EDGE), Union 2 (CONTAINS) -Reducer 10 <- Map 8 (SIMPLE_EDGE), Union 16 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 14 (SIMPLE_EDGE), Reducer 11 (ONE_TO_ONE_EDGE) -Reducer 13 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 8 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) +Map 1 <- Union 2 (CONTAINS) +Map 8 <- Union 2 (CONTAINS) +Reducer 3 <- Map 9 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) +Reducer 5 <- Map 10 (SIMPLE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 10 (SIMPLE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_189] - Select Operator [SEL_188] (rows=574982057 width=135) + File Output Operator [FS_168] + Select Operator [SEL_167] (rows=652 width=788) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_55] - Select Operator [SEL_54] (rows=574982057 width=135) + Select Operator [SEL_54] (rows=652 width=788) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_141] (rows=574982057 width=135) - Conds:RS_179._col0=RS_186._col0(Inner),RS_179._col0=RS_52.(_col0 - 53)(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_186] + Merge Join Operator [MERGEJOIN_141] (rows=652 width=1572) + Conds:RS_159._col0=RS_165._col0(Inner),RS_159._col0=RS_52.(_col0 - 53)(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_165] PartitionCols:_col0 - Select Operator [SEL_184] (rows=36524 width=1119) + Select Operator [SEL_163] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_182] (rows=36524 width=1119) + Filter Operator [FIL_161] (rows=652 width=8) predicate:((d_year = 2001) and d_week_seq is not null) - TableScan [TS_20] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_week_seq","d_year"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_52] - PartitionCols:(_col0 - 53) - Merge Join Operator [MERGEJOIN_140] (rows=261355475 width=135) - Conds:RS_181._col0=RS_187._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_187] - PartitionCols:_col0 - Select Operator [SEL_185] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_183] (rows=36524 width=1119) - predicate:((d_year = 2002) and d_week_seq is not null) - Please refer to the previous TableScan [TS_20] - <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_181] - PartitionCols:_col0 - Group By Operator [GBY_180] (rows=237595882 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0 - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_40] - PartitionCols:_col0 - Group By Operator [GBY_39] (rows=475191764 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)"],keys:_col0 - Select Operator [SEL_37] (rows=475191764 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_139] (rows=475191764 width=135) - Conds:Union 16._col0=RS_166._col0(Inner),Output:["_col1","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_166] - PartitionCols:_col0 - Select Operator [SEL_163] (rows=73049 width=1119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_162] (rows=73049 width=1119) - predicate:(d_date_sk is not null and d_week_seq is not null) - TableScan [TS_8] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_week_seq","d_day_name"] - <-Union 16 [SIMPLE_EDGE] - <-Map 15 [CONTAINS] vectorized - Reduce Output Operator [RS_198] - PartitionCols:_col0 - Select Operator [SEL_197] (rows=144002668 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_196] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) - TableScan [TS_152] (rows=144002668 width=135) - Output:["ws_sold_date_sk","ws_ext_sales_price"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_194] - Group By Operator [GBY_193] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_171] - Group By Operator [GBY_169] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_167] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_163] - <-Map 17 [CONTAINS] vectorized - Reduce Output Operator [RS_201] - PartitionCols:_col0 - Select Operator [SEL_200] (rows=287989836 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_199] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_157] (rows=287989836 width=135) - Output:["cs_sold_date_sk","cs_ext_sales_price"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_195] - Please refer to the previous Group By Operator [GBY_193] + TableScan [TS_20] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_week_seq","d_year"] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_179] + FORWARD [RS_159] PartitionCols:_col0 - Group By Operator [GBY_178] (rows=237595882 width=135) + Group By Operator [GBY_158] (rows=13152 width=788) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=475191764 width=135) + Group By Operator [GBY_16] (rows=4576896 width=788) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)"],keys:_col0 - Select Operator [SEL_14] (rows=475191764 width=135) + Select Operator [SEL_14] (rows=430516591 width=206) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_138] (rows=475191764 width=135) - Conds:Union 2._col0=RS_164._col0(Inner),Output:["_col1","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_164] + Merge Join Operator [MERGEJOIN_138] (rows=430516591 width=206) + Conds:Union 2._col0=RS_157._col0(Inner),Output:["_col1","_col3","_col4"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_157] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_163] + Select Operator [SEL_156] (rows=73049 width=99) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_155] (rows=73049 width=99) + predicate:(d_date_sk is not null and d_week_seq is not null) + TableScan [TS_8] (rows=73049 width=99) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq","d_day_name"] <-Union 2 [SIMPLE_EDGE] <-Map 1 [CONTAINS] vectorized - Reduce Output Operator [RS_177] + Reduce Output Operator [RS_154] PartitionCols:_col0 - Select Operator [SEL_176] (rows=144002668 width=135) + Select Operator [SEL_153] (rows=143966864 width=115) Output:["_col0","_col1"] - Filter Operator [FIL_175] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_12_date_dim_d_date_sk_min) AND DynamicValue(RS_12_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_12_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) - TableScan [TS_142] (rows=144002668 width=135) + Filter Operator [FIL_152] (rows=143966864 width=115) + predicate:ws_sold_date_sk is not null + TableScan [TS_142] (rows=144002668 width=115) Output:["ws_sold_date_sk","ws_ext_sales_price"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_173] - Group By Operator [GBY_172] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_170] - Group By Operator [GBY_168] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_165] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_163] - <-Map 7 [CONTAINS] vectorized - Reduce Output Operator [RS_192] + <-Map 8 [CONTAINS] vectorized + Reduce Output Operator [RS_171] PartitionCols:_col0 - Select Operator [SEL_191] (rows=287989836 width=135) + Select Operator [SEL_170] (rows=286549727 width=115) Output:["_col0","_col1"] - Filter Operator [FIL_190] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_12_date_dim_d_date_sk_min) AND DynamicValue(RS_12_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_12_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_147] (rows=287989836 width=135) + Filter Operator [FIL_169] (rows=286549727 width=115) + predicate:cs_sold_date_sk is not null + TableScan [TS_147] (rows=287989836 width=115) Output:["cs_sold_date_sk","cs_ext_sales_price"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_174] - Please refer to the previous Group By Operator [GBY_172] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:(_col0 - 53) + Merge Join Operator [MERGEJOIN_140] (rows=652 width=788) + Conds:RS_160._col0=RS_166._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_166] + PartitionCols:_col0 + Select Operator [SEL_164] (rows=652 width=8) + Output:["_col0"] + Filter Operator [FIL_162] (rows=652 width=8) + predicate:((d_year = 2002) and d_week_seq is not null) + Please refer to the previous TableScan [TS_20] + <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_160] + PartitionCols:_col0 + Please refer to the previous Group By Operator [GBY_158] diff --git a/ql/src/test/results/clientpositive/perf/tez/query20.q.out b/ql/src/test/results/clientpositive/perf/tez/query20.q.out index cfa58f15ed..d9dd14a8e1 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query20.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query20.q.out @@ -72,62 +72,62 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_86] - Limit [LIM_85] (rows=100 width=135) + Limit [LIM_85] (rows=100 width=802) Number of rows:100 - Select Operator [SEL_84] (rows=174233858 width=135) + Select Operator [SEL_84] (rows=9551005 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_83] - Select Operator [SEL_82] (rows=174233858 width=135) + Select Operator [SEL_82] (rows=9551005 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_81] (rows=174233858 width=135) + PTF Operator [PTF_81] (rows=9551005 width=689) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"_col1"}] - Select Operator [SEL_80] (rows=174233858 width=135) + Select Operator [SEL_80] (rows=9551005 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_79] PartitionCols:_col1 - Group By Operator [GBY_78] (rows=174233858 width=135) + Group By Operator [GBY_78] (rows=9551005 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_16] (rows=348467716 width=135) + Group By Operator [GBY_16] (rows=9551005 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8 - Merge Join Operator [MERGEJOIN_58] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_58] (rows=9551005 width=673) Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_69] PartitionCols:_col0 - Select Operator [SEL_68] (rows=462000 width=1436) + Select Operator [SEL_68] (rows=138600 width=581) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_67] (rows=462000 width=1436) + Filter Operator [FIL_67] (rows=138600 width=581) predicate:((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] + TableScan [TS_6] (rows=462000 width=581) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_57] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_57] (rows=31836679 width=110) Conds:RS_77._col0=RS_61._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Select Operator [SEL_60] (rows=8116 width=1119) + Select Operator [SEL_60] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_59] (rows=8116 width=1119) + Filter Operator [FIL_59] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_77] PartitionCols:_col0 - Select Operator [SEL_76] (rows=287989836 width=135) + Select Operator [SEL_76] (rows=286549727 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_75] (rows=287989836 width=135) + Filter Operator [FIL_75] (rows=286549727 width=119) predicate:((cs_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] + TableScan [TS_0] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_74] Group By Operator [GBY_73] (rows=1 width=12) @@ -136,7 +136,7 @@ Stage-0 SHUFFLE [RS_72] Group By Operator [GBY_71] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_70] (rows=462000 width=1436) + Select Operator [SEL_70] (rows=138600 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_68] <-Reducer 8 [BROADCAST_EDGE] vectorized @@ -147,7 +147,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_64] Group By Operator [GBY_63] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_62] (rows=8116 width=1119) + Select Operator [SEL_62] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_60] diff --git a/ql/src/test/results/clientpositive/perf/tez/query21.q.out b/ql/src/test/results/clientpositive/perf/tez/query21.q.out index 377c20ae13..3f7f52c3be 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query21.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query21.q.out @@ -71,52 +71,52 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_95] - Limit [LIM_94] (rows=100 width=15) + Limit [LIM_94] (rows=100 width=216) Number of rows:100 - Select Operator [SEL_93] (rows=12506076 width=15) + Select Operator [SEL_93] (rows=231983 width=216) Output:["_col0","_col1","_col2","_col3"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_92] - Filter Operator [FIL_91] (rows=12506076 width=15) + Filter Operator [FIL_91] (rows=231983 width=216) predicate:CASE WHEN ((_col2 > 0L)) THEN ((UDFToDouble(_col3) / UDFToDouble(_col2)) BETWEEN 0.666667D AND 1.5D) ELSE (null) END - Group By Operator [GBY_90] (rows=25012152 width=15) + Group By Operator [GBY_90] (rows=463966 width=216) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col0, _col1 - Group By Operator [GBY_23] (rows=50024305 width=15) + Group By Operator [GBY_23] (rows=463966 width=216) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col0, _col1 - Select Operator [SEL_21] (rows=50024305 width=15) + Select Operator [SEL_21] (rows=463966 width=294) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_77] (rows=50024305 width=15) + Merge Join Operator [MERGEJOIN_77] (rows=463966 width=294) Conds:RS_18._col2=RS_89._col0(Inner),Output:["_col3","_col5","_col7","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_89] PartitionCols:_col0 - Select Operator [SEL_88] (rows=27 width=1029) + Select Operator [SEL_88] (rows=27 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_87] (rows=27 width=1029) + Filter Operator [FIL_87] (rows=27 width=104) predicate:w_warehouse_sk is not null - TableScan [TS_9] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"] + TableScan [TS_9] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_76] (rows=45476640 width=15) + Merge Join Operator [MERGEJOIN_76] (rows=463966 width=198) Conds:RS_15._col1=RS_86._col0(Inner),Output:["_col2","_col3","_col5","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_86] PartitionCols:_col0 - Select Operator [SEL_85] (rows=51333 width=1436) + Select Operator [SEL_85] (rows=51333 width=215) Output:["_col0","_col1"] - Filter Operator [FIL_84] (rows=51333 width=1436) + Filter Operator [FIL_84] (rows=51333 width=215) predicate:(i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_current_price"] + TableScan [TS_6] (rows=462000 width=215) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_current_price"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_75] (rows=41342400 width=15) + Merge Join Operator [MERGEJOIN_75] (rows=4175715 width=104) Conds:RS_80._col0=RS_83._col0(Inner),Output:["_col1","_col2","_col3","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_80] @@ -126,14 +126,14 @@ Stage-0 Filter Operator [FIL_78] (rows=37584000 width=15) predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) TableScan [TS_0] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] + default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_83] PartitionCols:_col0 - Select Operator [SEL_82] (rows=8116 width=1119) + Select Operator [SEL_82] (rows=8116 width=98) Output:["_col0","_col1"] - Filter Operator [FIL_81] (rows=8116 width=1119) + Filter Operator [FIL_81] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query22.q.out b/ql/src/test/results/clientpositive/perf/tez/query22.q.out index cfe780a270..17b9ce34ec 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query22.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query22.q.out @@ -55,50 +55,50 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_93] - Limit [LIM_92] (rows=100 width=15) + Limit [LIM_92] (rows=100 width=397) Number of rows:100 - Select Operator [SEL_91] (rows=125060762 width=15) + Select Operator [SEL_91] (rows=20878575 width=397) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_90] - Select Operator [SEL_89] (rows=125060762 width=15) + Select Operator [SEL_89] (rows=20878575 width=397) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_88] (rows=125060762 width=15) + Group By Operator [GBY_88] (rows=20878575 width=413) Output:["_col0","_col1","_col2","_col3","_col5","_col6"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_22] (rows=250121525 width=15) + Group By Operator [GBY_22] (rows=20878575 width=413) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)","count(_col3)"],keys:_col8, _col9, _col10, _col11, 0L - Merge Join Operator [MERGEJOIN_75] (rows=50024305 width=15) + Merge Join Operator [MERGEJOIN_75] (rows=4175715 width=391) Conds:RS_18._col1=RS_87._col0(Inner),Output:["_col3","_col8","_col9","_col10","_col11"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=462000 width=1436) + Select Operator [SEL_86] (rows=462000 width=393) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_85] (rows=462000 width=1436) + Filter Operator [FIL_85] (rows=462000 width=393) predicate:i_item_sk is not null - TableScan [TS_9] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_product_name"] + TableScan [TS_9] (rows=462000 width=393) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category","i_product_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_74] (rows=45476640 width=15) + Merge Join Operator [MERGEJOIN_74] (rows=4175715 width=6) Conds:RS_15._col2=RS_84._col0(Inner),Output:["_col1","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_84] PartitionCols:_col0 - Select Operator [SEL_83] (rows=27 width=1029) + Select Operator [SEL_83] (rows=27 width=4) Output:["_col0"] - Filter Operator [FIL_82] (rows=27 width=1029) + Filter Operator [FIL_82] (rows=27 width=4) predicate:w_warehouse_sk is not null - TableScan [TS_6] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk"] + TableScan [TS_6] (rows=27 width=4) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_73] (rows=41342400 width=15) + Merge Join Operator [MERGEJOIN_73] (rows=4175715 width=10) Conds:RS_78._col0=RS_81._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_78] @@ -108,14 +108,14 @@ Stage-0 Filter Operator [FIL_76] (rows=37584000 width=15) predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) TableScan [TS_0] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] + default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_81] PartitionCols:_col0 - Select Operator [SEL_80] (rows=8116 width=1119) + Select Operator [SEL_80] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_79] (rows=8116 width=1119) + Filter Operator [FIL_79] (rows=8116 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query23.q.out b/ql/src/test/results/clientpositive/perf/tez/query23.q.out index 4d8e319486..8f7dff0aa2 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query23.q.out @@ -1,5 +1,5 @@ -Warning: Shuffle Join MERGEJOIN[585][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 28' is a cross product -Warning: Shuffle Join MERGEJOIN[587][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 36' is a cross product +Warning: Shuffle Join MERGEJOIN[585][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 29' is a cross product +Warning: Shuffle Join MERGEJOIN[587][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 32' is a cross product PREHOOK: query: explain with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt @@ -105,443 +105,434 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 17 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 13 <- Reducer 19 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE) -Map 23 <- Reducer 31 (BROADCAST_EDGE) -Map 43 <- Reducer 12 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE) -Map 44 <- Reducer 38 (BROADCAST_EDGE) -Reducer 10 <- Reducer 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 12 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 18 (SIMPLE_EDGE) -Reducer 15 <- Map 20 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (SIMPLE_EDGE) -Reducer 17 <- Reducer 16 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 24 <- Map 23 (SIMPLE_EDGE), Map 30 (SIMPLE_EDGE) -Reducer 25 <- Map 42 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) -Reducer 26 <- Reducer 25 (SIMPLE_EDGE) -Reducer 27 <- Reducer 26 (CUSTOM_SIMPLE_EDGE) -Reducer 28 <- Reducer 27 (CUSTOM_SIMPLE_EDGE), Reducer 29 (CUSTOM_SIMPLE_EDGE), Reducer 41 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Reducer 26 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 31 <- Map 30 (CUSTOM_SIMPLE_EDGE) -Reducer 32 <- Map 30 (SIMPLE_EDGE), Map 44 (SIMPLE_EDGE) -Reducer 33 <- Map 42 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE) -Reducer 34 <- Reducer 33 (SIMPLE_EDGE) -Reducer 35 <- Reducer 34 (CUSTOM_SIMPLE_EDGE) -Reducer 36 <- Reducer 35 (CUSTOM_SIMPLE_EDGE), Reducer 37 (CUSTOM_SIMPLE_EDGE), Reducer 41 (CUSTOM_SIMPLE_EDGE) -Reducer 37 <- Reducer 34 (CUSTOM_SIMPLE_EDGE) -Reducer 38 <- Map 30 (CUSTOM_SIMPLE_EDGE) -Reducer 4 <- Reducer 28 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 40 <- Map 39 (SIMPLE_EDGE), Map 42 (SIMPLE_EDGE) +Map 1 <- Reducer 19 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 15 <- Reducer 22 (BROADCAST_EDGE) +Map 24 <- Reducer 35 (BROADCAST_EDGE) +Map 36 <- Reducer 7 (BROADCAST_EDGE) +Map 42 <- Reducer 14 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) +Map 43 <- Reducer 13 (BROADCAST_EDGE) +Reducer 10 <- Map 42 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 13 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 17 <- Map 23 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (SIMPLE_EDGE) +Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 20 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) +Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) +Reducer 25 <- Map 24 (SIMPLE_EDGE), Map 34 (SIMPLE_EDGE) +Reducer 26 <- Map 39 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) +Reducer 27 <- Reducer 26 (SIMPLE_EDGE) +Reducer 28 <- Reducer 27 (CUSTOM_SIMPLE_EDGE) +Reducer 29 <- Reducer 28 (CUSTOM_SIMPLE_EDGE), Reducer 30 (CUSTOM_SIMPLE_EDGE), Reducer 38 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 18 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 30 <- Reducer 27 (CUSTOM_SIMPLE_EDGE) +Reducer 31 <- Reducer 27 (CUSTOM_SIMPLE_EDGE) +Reducer 32 <- Reducer 31 (CUSTOM_SIMPLE_EDGE), Reducer 33 (CUSTOM_SIMPLE_EDGE), Reducer 41 (CUSTOM_SIMPLE_EDGE) +Reducer 33 <- Reducer 27 (CUSTOM_SIMPLE_EDGE) +Reducer 35 <- Map 34 (CUSTOM_SIMPLE_EDGE) +Reducer 37 <- Map 36 (SIMPLE_EDGE), Map 39 (SIMPLE_EDGE) +Reducer 38 <- Reducer 37 (SIMPLE_EDGE) +Reducer 4 <- Reducer 29 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 40 <- Map 39 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE) Reducer 41 <- Reducer 40 (SIMPLE_EDGE) Reducer 6 <- Union 5 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 43 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_691] - Limit [LIM_690] (rows=1 width=112) + File Output Operator [FS_689] + Limit [LIM_688] (rows=1 width=112) Number of rows:100 - Group By Operator [GBY_689] (rows=1 width=112) + Group By Operator [GBY_687] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Union 5 [CUSTOM_SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] + <-Reducer 12 [CONTAINS] Reduce Output Operator [RS_598] Group By Operator [GBY_597] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_595] (rows=191667562 width=135) + Select Operator [SEL_595] (rows=52 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_594] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_594] (rows=52 width=2) Conds:RS_244._col2=RS_245._col0(Inner),Output:["_col3","_col4"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_244] + <-Reducer 11 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_244] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_584] (rows=174243235 width=135) - Conds:RS_241._col1=RS_640._col0(Inner),Output:["_col2","_col3","_col4"] - <-Reducer 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_640] + Merge Join Operator [MERGEJOIN_584] (rows=155 width=0) + Conds:RS_241._col1=RS_632._col0(Inner),Output:["_col2","_col3","_col4"] + <-Reducer 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_632] PartitionCols:_col0 - Group By Operator [GBY_637] (rows=58079562 width=88) + Group By Operator [GBY_629] (rows=2235 width=4) Output:["_col0"],keys:_col1 - Select Operator [SEL_636] (rows=116159124 width=88) + Select Operator [SEL_628] (rows=6548799 width=12) Output:["_col1"] - Filter Operator [FIL_635] (rows=116159124 width=88) + Filter Operator [FIL_627] (rows=6548799 width=12) predicate:(_col3 > 4L) - Select Operator [SEL_634] (rows=348477374 width=88) + Select Operator [SEL_626] (rows=19646398 width=12) Output:["_col0","_col3"] - Group By Operator [GBY_633] (rows=348477374 width=88) + Group By Operator [GBY_625] (rows=19646398 width=290) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 15 [SIMPLE_EDGE] + <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col0 - Group By Operator [GBY_23] (rows=696954748 width=88) + Group By Operator [GBY_23] (rows=19646398 width=290) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_21] (rows=696954748 width=88) + Select Operator [SEL_21] (rows=19646398 width=282) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_569] (rows=696954748 width=88) - Conds:RS_18._col1=RS_621._col0(Inner),Output:["_col3","_col5","_col6"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_621] + Merge Join Operator [MERGEJOIN_569] (rows=19646398 width=282) + Conds:RS_18._col1=RS_624._col0(Inner),Output:["_col3","_col5","_col6"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_624] PartitionCols:_col0 - Select Operator [SEL_620] (rows=462000 width=1436) + Select Operator [SEL_623] (rows=462000 width=188) Output:["_col0","_col1"] - Filter Operator [FIL_619] (rows=462000 width=1436) + Filter Operator [FIL_622] (rows=462000 width=188) predicate:i_item_sk is not null - TableScan [TS_12] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"] - <-Reducer 14 [SIMPLE_EDGE] + TableScan [TS_12] (rows=462000 width=188) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] + <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_568] (rows=633595212 width=88) - Conds:RS_632._col0=RS_613._col0(Inner),Output:["_col1","_col3"] - <-Map 18 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_568] (rows=19646398 width=98) + Conds:RS_621._col0=RS_613._col0(Inner),Output:["_col1","_col3"] + <-Map 21 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_613] PartitionCols:_col0 - Select Operator [SEL_612] (rows=73049 width=1119) + Select Operator [SEL_612] (rows=2609 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_611] (rows=73049 width=1119) + Filter Operator [FIL_611] (rows=2609 width=102) predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_year"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_632] + TableScan [TS_9] (rows=73049 width=102) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_year"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_621] PartitionCols:_col0 - Select Operator [SEL_631] (rows=575995635 width=88) + Select Operator [SEL_620] (rows=550076554 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_630] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"] - <-Reducer 19 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_619] (rows=550076554 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_6] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] + <-Reducer 22 [BROADCAST_EDGE] vectorized BROADCAST [RS_618] Group By Operator [GBY_617] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_616] Group By Operator [GBY_615] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_614] (rows=73049 width=1119) + Select Operator [SEL_614] (rows=2609 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_612] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_629] - Group By Operator [GBY_628] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_626] - Group By Operator [GBY_624] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_622] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_620] - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_241] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_575] (rows=158402938 width=135) - Conds:RS_698._col0=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_603] + Merge Join Operator [MERGEJOIN_575] (rows=3941102 width=122) + Conds:RS_696._col0=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_603] PartitionCols:_col0 - Select Operator [SEL_600] (rows=18262 width=1119) + Select Operator [SEL_600] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_599] (rows=18262 width=1119) + Filter Operator [FIL_599] (rows=50 width=12) predicate:((d_moy = 1) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_698] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 42 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_696] PartitionCols:_col0 - Select Operator [SEL_697] (rows=144002668 width=135) + Select Operator [SEL_695] (rows=143930993 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_696] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_143_item_i_item_sk_min) AND DynamicValue(RS_143_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_143_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_239_date_dim_d_date_sk_min) AND DynamicValue(RS_239_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_239_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_124] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_693] - Group By Operator [GBY_692] (rows=1 width=12) + Filter Operator [FIL_694] (rows=143930993 width=127) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_242_item_i_item_sk_min) AND DynamicValue(RS_242_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_242_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_239_date_dim_d_date_sk_min) AND DynamicValue(RS_239_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_239_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_124] (rows=144002668 width=127) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_691] + Group By Operator [GBY_690] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_608] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_608] Group By Operator [GBY_606] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_604] (rows=18262 width=1119) + Select Operator [SEL_604] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_600] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_695] - Group By Operator [GBY_694] (rows=1 width=12) + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_693] + Group By Operator [GBY_692] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_627] - Group By Operator [GBY_625] (rows=1 width=12) + <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_637] + Group By Operator [GBY_635] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_623] (rows=462000 width=1436) + Select Operator [SEL_633] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_620] - <-Reducer 36 [SIMPLE_EDGE] + Please refer to the previous Group By Operator [GBY_629] + <-Reducer 32 [SIMPLE_EDGE] SHUFFLE [RS_245] PartitionCols:_col0 - Select Operator [SEL_237] (rows=105599202 width=433) + Select Operator [SEL_237] (rows=471875 width=4) Output:["_col0"] - Filter Operator [FIL_236] (rows=105599202 width=433) + Filter Operator [FIL_236] (rows=471875 width=228) predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_587] (rows=316797606 width=433) + Merge Join Operator [MERGEJOIN_587] (rows=1415625 width=228) Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"] - <-Reducer 41 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_688] - Group By Operator [GBY_686] (rows=316797606 width=88) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 40 [SIMPLE_EDGE] - SHUFFLE [RS_105] - PartitionCols:_col0 - Group By Operator [GBY_104] (rows=633595212 width=88) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_102] (rows=633595212 width=88) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_574] (rows=633595212 width=88) - Conds:RS_685._col0=RS_665._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 42 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_665] - PartitionCols:_col0 - Select Operator [SEL_664] (rows=80000000 width=860) - Output:["_col0"] - Filter Operator [FIL_663] (rows=80000000 width=860) - predicate:c_customer_sk is not null - TableScan [TS_96] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"] - <-Map 39 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_685] - PartitionCols:_col0 - Select Operator [SEL_684] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_683] (rows=575995635 width=88) - predicate:ss_customer_sk is not null - TableScan [TS_93] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_716] - Select Operator [SEL_715] (rows=1 width=120) - Filter Operator [FIL_714] (rows=1 width=120) + <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_702] + Select Operator [SEL_701] (rows=1 width=8) + Filter Operator [FIL_700] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_713] (rows=1 width=120) + Group By Operator [GBY_699] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_712] (rows=1 width=120) - Group By Operator [GBY_711] (rows=1 width=120) + Select Operator [SEL_698] (rows=1 width=8) + Group By Operator [GBY_697] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_709] - Group By Operator [GBY_707] (rows=1 width=120) + <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_670] + Group By Operator [GBY_666] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_705] (rows=348477374 width=88) + Select Operator [SEL_662] (rows=11859 width=116) Output:["_col0"] - Group By Operator [GBY_704] (rows=348477374 width=88) + Group By Operator [GBY_659] (rows=11859 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 33 [SIMPLE_EDGE] - SHUFFLE [RS_175] + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_51] PartitionCols:_col0 - Group By Operator [GBY_174] (rows=696954748 width=88) + Group By Operator [GBY_50] (rows=11859 width=116) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_172] (rows=696954748 width=88) + Select Operator [SEL_48] (rows=18762463 width=4) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_579] (rows=696954748 width=88) - Conds:RS_169._col1=RS_667._col0(Inner),Output:["_col2","_col3","_col6"] - <-Map 42 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_667] + Merge Join Operator [MERGEJOIN_571] (rows=18762463 width=4) + Conds:RS_45._col1=RS_657._col0(Inner),Output:["_col2","_col3","_col6"] + <-Map 39 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_657] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_664] - <-Reducer 32 [SIMPLE_EDGE] - SHUFFLE [RS_169] + Select Operator [SEL_655] (rows=80000000 width=4) + Output:["_col0"] + Filter Operator [FIL_654] (rows=80000000 width=4) + predicate:c_customer_sk is not null + TableScan [TS_96] (rows=80000000 width=4) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk"] + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_45] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_578] (rows=633595212 width=88) - Conds:RS_703._col0=RS_652._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 30 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_652] + Merge Join Operator [MERGEJOIN_570] (rows=18762463 width=0) + Conds:RS_653._col0=RS_645._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 34 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_645] PartitionCols:_col0 - Select Operator [SEL_649] (rows=73049 width=1119) + Select Operator [SEL_644] (rows=2609 width=8) Output:["_col0"] - Filter Operator [FIL_648] (rows=73049 width=1119) + Filter Operator [FIL_643] (rows=2609 width=8) predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) - TableScan [TS_36] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Map 44 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_703] + TableScan [TS_36] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_653] PartitionCols:_col0 - Select Operator [SEL_702] (rows=575995635 width=88) + Select Operator [SEL_652] (rows=525327388 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_701] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_167_date_dim_d_date_sk_min) AND DynamicValue(RS_167_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_167_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_157] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 38 [BROADCAST_EDGE] vectorized - BROADCAST [RS_700] - Group By Operator [GBY_699] (rows=1 width=12) + Filter Operator [FIL_651] (rows=525327388 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_33] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 35 [BROADCAST_EDGE] vectorized + BROADCAST [RS_650] + Group By Operator [GBY_649] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_657] - Group By Operator [GBY_655] (rows=1 width=12) + <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_648] + Group By Operator [GBY_647] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_653] (rows=73049 width=1119) + Select Operator [SEL_646] (rows=2609 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_649] - <-Reducer 37 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_718] - Group By Operator [GBY_717] (rows=1 width=224) + Please refer to the previous Select Operator [SEL_644] + <-Reducer 33 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_704] + Group By Operator [GBY_703] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] - <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_710] - Group By Operator [GBY_708] (rows=1 width=224) + <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_671] + Group By Operator [GBY_667] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_706] (rows=348477374 width=88) + Select Operator [SEL_663] (rows=11859 width=116) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_704] + Please refer to the previous Group By Operator [GBY_659] + <-Reducer 41 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_711] + Group By Operator [GBY_710] (rows=1415625 width=116) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 40 [SIMPLE_EDGE] + SHUFFLE [RS_229] + PartitionCols:_col0 + Group By Operator [GBY_228] (rows=550080312 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 + Select Operator [SEL_226] (rows=550080312 width=114) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_582] (rows=550080312 width=114) + Conds:RS_709._col0=RS_658._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 39 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_658] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_655] + <-Map 43 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_709] + PartitionCols:_col0 + Select Operator [SEL_708] (rows=550080312 width=114) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_707] (rows=550080312 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_244_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_244_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_244_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) + TableScan [TS_217] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_706] + Group By Operator [GBY_705] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_558] + Group By Operator [GBY_557] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_556] (rows=155 width=0) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_584] <-Reducer 4 [CONTAINS] Reduce Output Operator [RS_593] Group By Operator [GBY_592] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_590] (rows=383314495 width=135) + Select Operator [SEL_590] (rows=102 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_589] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_589] (rows=102 width=1) Conds:RS_120._col1=RS_121._col0(Inner),Output:["_col3","_col4"] - <-Reducer 28 [SIMPLE_EDGE] - SHUFFLE [RS_121] - PartitionCols:_col0 - Select Operator [SEL_113] (rows=105599202 width=433) - Output:["_col0"] - Filter Operator [FIL_112] (rows=105599202 width=433) - predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_585] (rows=316797606 width=433) - Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"] - <-Reducer 41 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_687] - Please refer to the previous Group By Operator [GBY_686] - <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_680] - Select Operator [SEL_679] (rows=1 width=120) - Filter Operator [FIL_678] (rows=1 width=120) - predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_677] (rows=1 width=120) - Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_676] (rows=1 width=120) - Group By Operator [GBY_675] (rows=1 width=120) - Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_673] - Group By Operator [GBY_671] (rows=1 width=120) - Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_669] (rows=348477374 width=88) - Output:["_col0"] - Group By Operator [GBY_668] (rows=348477374 width=88) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_51] - PartitionCols:_col0 - Group By Operator [GBY_50] (rows=696954748 width=88) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_48] (rows=696954748 width=88) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_571] (rows=696954748 width=88) - Conds:RS_45._col1=RS_666._col0(Inner),Output:["_col2","_col3","_col6"] - <-Map 42 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_666] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_664] - <-Reducer 24 [SIMPLE_EDGE] - SHUFFLE [RS_45] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_570] (rows=633595212 width=88) - Conds:RS_662._col0=RS_650._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 30 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_650] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_649] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_662] - PartitionCols:_col0 - Select Operator [SEL_661] (rows=575995635 width=88) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_660] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_33] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_659] - Group By Operator [GBY_658] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_656] - Group By Operator [GBY_654] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_651] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_649] - <-Reducer 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_682] - Group By Operator [GBY_681] (rows=1 width=224) - Output:["_col0"],aggregations:["max(VALUE._col0)"] - <-Reducer 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_674] - Group By Operator [GBY_672] (rows=1 width=224) - Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_670] (rows=348477374 width=88) - Output:["_col1"] - Please refer to the previous Group By Operator [GBY_668] <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_120] + PARTITION_ONLY_SHUFFLE [RS_120] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_583] (rows=348467716 width=135) - Conds:RS_117._col2=RS_638._col0(Inner),Output:["_col1","_col3","_col4"] - <-Reducer 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_638] + Merge Join Operator [MERGEJOIN_583] (rows=304 width=0) + Conds:RS_117._col2=RS_630._col0(Inner),Output:["_col1","_col3","_col4"] + <-Reducer 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_630] PartitionCols:_col0 - Please refer to the previous Group By Operator [GBY_637] + Please refer to the previous Group By Operator [GBY_629] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_117] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_567] (rows=316788826 width=135) - Conds:RS_647._col0=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_601] + Merge Join Operator [MERGEJOIN_567] (rows=7751875 width=101) + Conds:RS_642._col0=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_601] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_600] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_647] + SHUFFLE [RS_642] PartitionCols:_col0 - Select Operator [SEL_646] (rows=287989836 width=135) + Select Operator [SEL_641] (rows=285117831 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_645] (rows=287989836 width=135) + Filter Operator [FIL_640] (rows=285117831 width=127) predicate:((cs_item_sk BETWEEN DynamicValue(RS_118_item_i_item_sk_min) AND DynamicValue(RS_118_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_118_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_115_date_dim_d_date_sk_min) AND DynamicValue(RS_115_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_115_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_644] - Group By Operator [GBY_643] (rows=1 width=20) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=58079560)"] - <-Reducer 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_642] - Group By Operator [GBY_641] (rows=1 width=20) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=58079560)"] - Select Operator [SEL_639] (rows=58079562 width=88) + TableScan [TS_0] (rows=287989836 width=127) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_639] + Group By Operator [GBY_638] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_636] + Group By Operator [GBY_634] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_631] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_637] - <-Reducer 8 [BROADCAST_EDGE] vectorized + Please refer to the previous Group By Operator [GBY_629] + <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_610] Group By Operator [GBY_609] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_607] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_607] Group By Operator [GBY_605] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_602] (rows=18262 width=1119) + Select Operator [SEL_602] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_600] + <-Reducer 29 [SIMPLE_EDGE] + SHUFFLE [RS_121] + PartitionCols:_col0 + Select Operator [SEL_113] (rows=471875 width=4) + Output:["_col0"] + Filter Operator [FIL_112] (rows=471875 width=228) + predicate:(_col3 > (0.95 * _col1)) + Merge Join Operator [MERGEJOIN_585] (rows=1415625 width=228) + Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"] + <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_677] + Select Operator [SEL_676] (rows=1 width=8) + Filter Operator [FIL_675] (rows=1 width=8) + predicate:(sq_count_check(_col0) <= 1) + Group By Operator [GBY_674] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] + Select Operator [SEL_673] (rows=1 width=8) + Group By Operator [GBY_672] (rows=1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_668] + Group By Operator [GBY_664] (rows=1 width=8) + Output:["_col0"],aggregations:["count(_col0)"] + Select Operator [SEL_660] (rows=11859 width=116) + Output:["_col0"] + Please refer to the previous Group By Operator [GBY_659] + <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_679] + Group By Operator [GBY_678] (rows=1 width=112) + Output:["_col0"],aggregations:["max(VALUE._col0)"] + <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_669] + Group By Operator [GBY_665] (rows=1 width=112) + Output:["_col0"],aggregations:["max(_col1)"] + Select Operator [SEL_661] (rows=11859 width=116) + Output:["_col1"] + Please refer to the previous Group By Operator [GBY_659] + <-Reducer 38 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_686] + Group By Operator [GBY_685] (rows=1415625 width=116) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 37 [SIMPLE_EDGE] + SHUFFLE [RS_105] + PartitionCols:_col0 + Group By Operator [GBY_104] (rows=550080312 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 + Select Operator [SEL_102] (rows=550080312 width=114) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_574] (rows=550080312 width=114) + Conds:RS_684._col0=RS_656._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 39 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_656] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_655] + <-Map 36 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_684] + PartitionCols:_col0 + Select Operator [SEL_683] (rows=550080312 width=114) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_682] (rows=550080312 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_120_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_120_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_120_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) + TableScan [TS_93] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_681] + Group By Operator [GBY_680] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_454] + Group By Operator [GBY_453] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_452] (rows=304 width=0) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_583] diff --git a/ql/src/test/results/clientpositive/perf/tez/query24.q.out b/ql/src/test/results/clientpositive/perf/tez/query24.q.out index 349d429ab3..bb97602964 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query24.q.out @@ -100,30 +100,23 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE) -Map 31 <- Reducer 16 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 24 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Map 24 <- Reducer 20 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Map 9 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) -Reducer 12 <- Map 25 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 30 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 11 <- Map 9 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 12 <- Map 22 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 23 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Reducer 13 (SIMPLE_EDGE) Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 16 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) +Reducer 19 <- Map 21 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 20 <- Map 22 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) -Reducer 21 <- Map 17 (CUSTOM_SIMPLE_EDGE) -Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) -Reducer 24 <- Map 22 (CUSTOM_SIMPLE_EDGE) -Reducer 26 <- Map 25 (CUSTOM_SIMPLE_EDGE) -Reducer 27 <- Map 25 (CUSTOM_SIMPLE_EDGE) -Reducer 28 <- Map 25 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Map 25 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 22 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 25 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Map 30 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 20 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 22 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Map 23 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) @@ -133,285 +126,208 @@ Stage-0 Stage-1 Reducer 8 File Output Operator [FS_91] - Select Operator [SEL_90] (rows=77303902 width=321) + Select Operator [SEL_90] (rows=78393744 width=380) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_89] (rows=77303902 width=321) + Filter Operator [FIL_89] (rows=78393744 width=492) predicate:(_col3 > _col4) - Merge Join Operator [MERGEJOIN_290] (rows=231911707 width=321) + Merge Join Operator [MERGEJOIN_290] (rows=235181232 width=492) Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_380] - Select Operator [SEL_379] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_345] + Select Operator [SEL_344] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_378] (rows=1 width=232) + Group By Operator [GBY_343] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Reducer 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_377] - Group By Operator [GBY_376] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_342] + Group By Operator [GBY_341] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col10)","count(_col10)"] - Select Operator [SEL_375] (rows=463823414 width=88) + Select Operator [SEL_340] (rows=2121289008973 width=932) Output:["_col10"] - Group By Operator [GBY_374] (rows=463823414 width=88) + Group By Operator [GBY_339] (rows=2121289008973 width=932) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_78] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Group By Operator [GBY_77] (rows=927646829 width=88) + Group By Operator [GBY_77] (rows=2121289008973 width=932) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col4)"],keys:_col11, _col12, _col6, _col8, _col15, _col16, _col17, _col18, _col19, _col22 - Merge Join Operator [MERGEJOIN_289] (rows=927646829 width=88) - Conds:RS_73._col9, _col13=RS_355._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col22"] - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_355] + Merge Join Operator [MERGEJOIN_289] (rows=2121289008973 width=932) + Conds:RS_73._col9, _col13=RS_328._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col22"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_328] PartitionCols:_col1, upper(_col2) - Select Operator [SEL_353] (rows=40000000 width=1014) + Select Operator [SEL_326] (rows=40000000 width=272) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_352] (rows=40000000 width=1014) + Filter Operator [FIL_325] (rows=40000000 width=272) predicate:(ca_zip is not null and upper(ca_country) is not null) - TableScan [TS_15] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_state","ca_zip","ca_country"] + TableScan [TS_15] (rows=40000000 width=272) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_state","ca_zip","ca_country"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_73] PartitionCols:_col9, _col13 - Merge Join Operator [MERGEJOIN_288] (rows=843315281 width=88) - Conds:RS_70._col0, _col3=RS_334._col0, _col1(Inner),Output:["_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] - <-Map 25 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_334] + Merge Join Operator [MERGEJOIN_288] (rows=537799796 width=1023) + Conds:RS_70._col0, _col3=RS_324._col0, _col1(Inner),Output:["_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_324] PartitionCols:_col0, _col1 - Select Operator [SEL_330] (rows=57591150 width=77) + Select Operator [SEL_322] (rows=57591150 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_329] (rows=57591150 width=77) + Filter Operator [FIL_321] (rows=57591150 width=8) predicate:(sr_item_sk is not null and sr_ticket_number is not null) - TableScan [TS_12] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"] + TableScan [TS_12] (rows=57591150 width=8) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_70] PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_287] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_287] (rows=385681992 width=1029) Conds:RS_67._col0=RS_297._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_297] PartitionCols:_col0 - Select Operator [SEL_294] (rows=462000 width=1436) + Select Operator [SEL_294] (rows=462000 width=384) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_292] (rows=462000 width=1436) + Filter Operator [FIL_292] (rows=462000 width=384) predicate:i_item_sk is not null - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] - <-Reducer 20 [SIMPLE_EDGE] + TableScan [TS_3] (rows=462000 width=384) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] + <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_286] (rows=696954748 width=88) - Conds:RS_64._col1=RS_321._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] + Merge Join Operator [MERGEJOIN_286] (rows=385681992 width=648) + Conds:RS_64._col1=RS_320._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_320] PartitionCols:_col0 - Select Operator [SEL_318] (rows=80000000 width=860) + Select Operator [SEL_318] (rows=80000000 width=276) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_317] (rows=80000000 width=860) + Filter Operator [FIL_317] (rows=80000000 width=276) predicate:(c_birth_country is not null and c_customer_sk is not null) - TableScan [TS_9] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"] - <-Reducer 19 [SIMPLE_EDGE] + TableScan [TS_9] (rows=80000000 width=276) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"] + <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_285] (rows=633595212 width=88) - Conds:RS_373._col2=RS_309._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col8","_col9"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_309] + Merge Join Operator [MERGEJOIN_285] (rows=385681992 width=379) + Conds:RS_338._col2=RS_306._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col8","_col9"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_306] PartitionCols:_col0 - Select Operator [SEL_306] (rows=852 width=1910) + Select Operator [SEL_303] (rows=155 width=271) Output:["_col0","_col1","_col3","_col4"] - Filter Operator [FIL_305] (rows=852 width=1910) + Filter Operator [FIL_302] (rows=155 width=271) predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null) - TableScan [TS_6] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] - <-Map 31 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_373] + TableScan [TS_6] (rows=1704 width=270) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_338] PartitionCols:_col2 - Select Operator [SEL_372] (rows=575995635 width=88) + Select Operator [SEL_337] (rows=525333486 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_371] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_65_customer_c_customer_sk_min) AND DynamicValue(RS_65_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_65_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_68_item_i_item_sk_min) AND DynamicValue(RS_68_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_68_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_71_store_returns_sr_item_sk_min) AND DynamicValue(RS_71_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_71_store_returns_sr_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_62_store_s_store_sk_min) AND DynamicValue(RS_62_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_62_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_71_store_returns_sr_ticket_number_min) AND DynamicValue(RS_71_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_71_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_43] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_366] - Group By Operator [GBY_365] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_302] - Group By Operator [GBY_300] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_298] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_294] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_362] - Group By Operator [GBY_361] (rows=1 width=12) + Filter Operator [FIL_336] (rows=525333486 width=122) + predicate:((ss_store_sk BETWEEN DynamicValue(RS_62_store_s_store_sk_min) AND DynamicValue(RS_62_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_62_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_43] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_335] + Group By Operator [GBY_334] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_314] - Group By Operator [GBY_312] (rows=1 width=12) + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_311] + Group By Operator [GBY_309] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_310] (rows=852 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_306] - <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_364] - Group By Operator [GBY_363] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_326] - Group By Operator [GBY_324] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_322] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_318] - <-Reducer 28 [BROADCAST_EDGE] vectorized - BROADCAST [RS_368] - Group By Operator [GBY_367] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_343] - Group By Operator [GBY_339] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_335] (rows=57591150 width=77) + Select Operator [SEL_307] (rows=155 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_330] - <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_370] - Group By Operator [GBY_369] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_344] - Group By Operator [GBY_340] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_336] (rows=57591150 width=77) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_330] + Please refer to the previous Select Operator [SEL_303] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_360] - Select Operator [SEL_359] (rows=231911707 width=88) + PARTITION_ONLY_SHUFFLE [RS_333] + Select Operator [SEL_332] (rows=235181232 width=380) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_358] (rows=231911707 width=88) + Group By Operator [GBY_331] (rows=235181232 width=380) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col1, _col2, _col7 - Select Operator [SEL_357] (rows=463823414 width=88) + Select Operator [SEL_330] (rows=365777643230 width=843) Output:["_col1","_col2","_col7","_col9"] - Group By Operator [GBY_356] (rows=463823414 width=88) + Group By Operator [GBY_329] (rows=365777643230 width=843) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_34] (rows=927646829 width=88) + Group By Operator [GBY_34] (rows=365777643230 width=843) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col17, _col18, _col12, _col22, _col6, _col7, _col9, _col10, _col14 - Merge Join Operator [MERGEJOIN_284] (rows=927646829 width=88) - Conds:RS_30._col15, _col19=RS_354._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col17","_col18","_col22"] - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_354] + Merge Join Operator [MERGEJOIN_284] (rows=365777643230 width=843) + Conds:RS_30._col15, _col19=RS_327._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col17","_col18","_col22"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_327] PartitionCols:_col1, upper(_col2) - Please refer to the previous Select Operator [SEL_353] + Please refer to the previous Select Operator [SEL_326] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col15, _col19 - Merge Join Operator [MERGEJOIN_283] (rows=843315281 width=88) - Conds:RS_27._col0, _col3=RS_331._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] - <-Map 25 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_331] + Merge Join Operator [MERGEJOIN_283] (rows=92733777 width=910) + Conds:RS_27._col0, _col3=RS_323._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_323] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_330] + Please refer to the previous Select Operator [SEL_322] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_282] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_282] (rows=56246341 width=899) Conds:RS_24._col1=RS_319._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] - <-Map 22 [SIMPLE_EDGE] vectorized + <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_319] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_318] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_281] (rows=696954748 width=88) - Conds:RS_21._col2=RS_307._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_307] + Merge Join Operator [MERGEJOIN_281] (rows=56246341 width=630) + Conds:RS_21._col2=RS_304._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_304] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_306] + Please refer to the previous Select Operator [SEL_303] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_280] (rows=633595212 width=88) - Conds:RS_351._col0=RS_295._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] + Merge Join Operator [MERGEJOIN_280] (rows=76612563 width=382) + Conds:RS_316._col0=RS_295._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_295] PartitionCols:_col0 - Select Operator [SEL_293] (rows=231000 width=1436) + Select Operator [SEL_293] (rows=7000 width=385) Output:["_col0","_col1","_col2","_col4","_col5"] - Filter Operator [FIL_291] (rows=231000 width=1436) + Filter Operator [FIL_291] (rows=7000 width=384) predicate:((i_color = 'orchid') and i_item_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_351] + SHUFFLE [RS_316] PartitionCols:_col0 - Select Operator [SEL_350] (rows=575995635 width=88) + Select Operator [SEL_315] (rows=525333486 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_349] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_25_customer_c_customer_sk_min) AND DynamicValue(RS_25_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_25_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_28_store_returns_sr_item_sk_min) AND DynamicValue(RS_28_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_28_store_returns_sr_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_28_store_returns_sr_ticket_number_min) AND DynamicValue(RS_28_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_28_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + Filter Operator [FIL_314] (rows=525333486 width=122) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_0] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_304] - Group By Operator [GBY_303] (rows=1 width=12) + BROADCAST [RS_301] + Group By Operator [GBY_300] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_301] - Group By Operator [GBY_299] (rows=1 width=12) + SHUFFLE [RS_299] + Group By Operator [GBY_298] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_296] (rows=231000 width=1436) + Select Operator [SEL_296] (rows=7000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_293] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_316] - Group By Operator [GBY_315] (rows=1 width=12) + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_313] + Group By Operator [GBY_312] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_313] - Group By Operator [GBY_311] (rows=1 width=12) + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_310] + Group By Operator [GBY_308] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_308] (rows=852 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_306] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_328] - Group By Operator [GBY_327] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_325] - Group By Operator [GBY_323] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_320] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_318] - <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_346] - Group By Operator [GBY_345] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_341] - Group By Operator [GBY_337] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_332] (rows=57591150 width=77) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_330] - <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_348] - Group By Operator [GBY_347] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_342] - Group By Operator [GBY_338] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_333] (rows=57591150 width=77) + Select Operator [SEL_305] (rows=155 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_330] + Please refer to the previous Select Operator [SEL_303] diff --git a/ql/src/test/results/clientpositive/perf/tez/query25.q.out b/ql/src/test/results/clientpositive/perf/tez/query25.q.out index b68c54aef7..e69b6d622e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query25.q.out @@ -95,20 +95,20 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 14 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Map 16 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE) -Reducer 10 <- Map 16 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) -Reducer 12 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 17 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 18 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Map 18 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 12 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 18 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 20 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 20 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 21 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) @@ -118,188 +118,185 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_270] - Limit [LIM_269] (rows=100 width=88) + File Output Operator [FS_263] + Limit [LIM_262] (rows=100 width=808) Number of rows:100 - Select Operator [SEL_268] (rows=421657640 width=88) + Select Operator [SEL_261] (rows=3464398292 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_267] - Group By Operator [GBY_266] (rows=421657640 width=88) + SHUFFLE [RS_260] + Group By Operator [GBY_259] (rows=3464398292 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_48] (rows=843315281 width=88) + Group By Operator [GBY_48] (rows=3464398292 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col20)","sum(_col12)"],keys:_col25, _col26, _col28, _col29 - Top N Key Operator [TNK_95] (rows=843315281 width=88) + Top N Key Operator [TNK_95] (rows=3464398292 width=807) keys:_col25, _col26, _col28, _col29,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_214] (rows=843315281 width=88) - Conds:RS_44._col3=RS_252._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_252] + Merge Join Operator [MERGEJOIN_214] (rows=3464398292 width=807) + Conds:RS_44._col3=RS_258._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_258] PartitionCols:_col0 - Select Operator [SEL_251] (rows=1704 width=1910) + Select Operator [SEL_257] (rows=1704 width=192) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_250] (rows=1704 width=1910) + Filter Operator [FIL_256] (rows=1704 width=192) predicate:s_store_sk is not null - TableScan [TS_32] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"] + TableScan [TS_32] (rows=1704 width=192) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_213] (rows=766650239 width=88) - Conds:RS_41._col1=RS_243._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_243] + Merge Join Operator [MERGEJOIN_213] (rows=3464398292 width=623) + Conds:RS_41._col1=RS_255._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_255] PartitionCols:_col0 - Select Operator [SEL_242] (rows=462000 width=1436) + Select Operator [SEL_254] (rows=462000 width=288) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_241] (rows=462000 width=1436) + Filter Operator [FIL_253] (rows=462000 width=288) predicate:i_item_sk is not null - TableScan [TS_29] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"] + TableScan [TS_29] (rows=462000 width=288) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_212] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_212] (rows=3464398292 width=343) Conds:RS_38._col1, _col2, _col4=RS_39._col8, _col9, _col10(Inner),Output:["_col1","_col3","_col5","_col12","_col20"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col8, _col9, _col10 - Merge Join Operator [MERGEJOIN_211] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_211] (rows=388471350 width=235) Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col8","_col9","_col10","_col11"] - <-Reducer 13 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_26] - PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_210] (rows=63350266 width=77) - Conds:RS_234._col0=RS_225._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_225] - PartitionCols:_col0 - Select Operator [SEL_220] (rows=4058 width=1119) - Output:["_col0"] - Filter Operator [FIL_217] (rows=4058 width=1119) - predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_234] - PartitionCols:_col0 - Select Operator [SEL_233] (rows=57591150 width=77) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_232] (rows=57591150 width=77) - predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) - TableScan [TS_12] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"] <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_25] + PARTITION_ONLY_SHUFFLE [RS_25] PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_209] (rows=316788826 width=135) - Conds:RS_265._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_209] (rows=11162699 width=119) + Conds:RS_245._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_223] PartitionCols:_col0 - Select Operator [SEL_219] (rows=4058 width=1119) + Select Operator [SEL_219] (rows=72 width=12) Output:["_col0"] - Filter Operator [FIL_216] (rows=4058 width=1119) + Filter Operator [FIL_216] (rows=72 width=12) predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) - Please refer to the previous TableScan [TS_3] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_265] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_245] PartitionCols:_col0 - Select Operator [SEL_264] (rows=287989836 width=135) + Select Operator [SEL_244] (rows=285117831 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_263] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_23_d3_d_date_sk_min) AND DynamicValue(RS_23_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_23_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_6] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"] - <-Reducer 14 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_243] (rows=285117831 width=123) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_23_d3_d_date_sk_min) AND DynamicValue(RS_23_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_23_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_6] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"] + <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_237] Group By Operator [GBY_235] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_108] Group By Operator [GBY_107] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_106] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_106] (rows=1928802 width=8) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_210] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_240] - Group By Operator [GBY_238] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + Merge Join Operator [MERGEJOIN_210] (rows=1928802 width=11) + Conds:RS_234._col0=RS_225._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_225] + PartitionCols:_col0 + Select Operator [SEL_220] (rows=72 width=12) + Output:["_col0"] + Filter Operator [FIL_217] (rows=72 width=12) + predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) + Please refer to the previous TableScan [TS_3] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_234] + PartitionCols:_col0 + Select Operator [SEL_233] (rows=53632139 width=123) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_232] (rows=53632139 width=123) + predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) + TableScan [TS_12] (rows=57591150 width=123) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_242] + Group By Operator [GBY_240] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_123] Group By Operator [GBY_122] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_121] (rows=63350266 width=77) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_210] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_249] - Group By Operator [GBY_247] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_246] - Group By Operator [GBY_245] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_244] (rows=462000 width=1436) + Select Operator [SEL_121] (rows=1928802 width=0) Output:["_col0"] - Please refer to the previous Select Operator [SEL_242] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_262] - Group By Operator [GBY_261] (rows=1 width=12) + Please refer to the previous Merge Join Operator [MERGEJOIN_210] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_239] + Group By Operator [GBY_238] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_229] Group By Operator [GBY_227] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_224] (rows=4058 width=1119) + Select Operator [SEL_224] (rows=72 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_219] + <-Reducer 15 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_26] + PartitionCols:_col1, _col2 + Please refer to the previous Merge Join Operator [MERGEJOIN_210] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_208] (rows=633595212 width=88) - Conds:RS_260._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_208] (rows=13737330 width=8) + Conds:RS_252._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_218] (rows=18262 width=1119) + Select Operator [SEL_218] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_215] (rows=18262 width=1119) + Filter Operator [FIL_215] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_260] + SHUFFLE [RS_252] PartitionCols:_col0 - Select Operator [SEL_259] (rows=575995635 width=88) + Select Operator [SEL_251] (rows=501694138 width=126) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_258] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_45_store_s_store_sk_min) AND DynamicValue(RS_45_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_45_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"] - <-Reducer 14 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_250] (rows=501694138 width=126) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_25_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_25_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_25_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_25_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_0] (rows=575995635 width=126) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"] + <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_236] Please refer to the previous Group By Operator [GBY_235] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_239] - Please refer to the previous Group By Operator [GBY_238] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_248] - Please refer to the previous Group By Operator [GBY_247] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_257] - Group By Operator [GBY_256] (rows=1 width=12) + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_241] + Please refer to the previous Group By Operator [GBY_240] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_247] + Group By Operator [GBY_246] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 10 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_113] + Group By Operator [GBY_112] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_111] (rows=11162699 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_209] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_249] + Group By Operator [GBY_248] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_255] - Group By Operator [GBY_254] (rows=1 width=12) + <-Reducer 10 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_128] + Group By Operator [GBY_127] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_253] (rows=1704 width=1910) + Select Operator [SEL_126] (rows=11162699 width=6) Output:["_col0"] - Please refer to the previous Select Operator [SEL_251] + Please refer to the previous Merge Join Operator [MERGEJOIN_209] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_231] Group By Operator [GBY_230] (rows=1 width=12) @@ -308,7 +305,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_228] Group By Operator [GBY_226] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_222] (rows=18262 width=1119) + Select Operator [SEL_222] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_218] diff --git a/ql/src/test/results/clientpositive/perf/tez/query26.q.out b/ql/src/test/results/clientpositive/perf/tez/query26.q.out index a90e09f61b..687c318304 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query26.q.out @@ -41,14 +41,12 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) @@ -58,86 +56,86 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_140] - Limit [LIM_139] (rows=100 width=135) + File Output Operator [FS_130] + Limit [LIM_129] (rows=100 width=444) Number of rows:100 - Select Operator [SEL_138] (rows=210822976 width=135) + Select Operator [SEL_128] (rows=310774 width=444) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_137] - Select Operator [SEL_136] (rows=210822976 width=135) + SHUFFLE [RS_127] + Select Operator [SEL_126] (rows=310774 width=444) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_135] (rows=210822976 width=135) + Group By Operator [GBY_125] (rows=310774 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 - Group By Operator [GBY_28] (rows=421645953 width=135) + Group By Operator [GBY_28] (rows=809521 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18 - Top N Key Operator [TNK_55] (rows=421645953 width=135) + Top N Key Operator [TNK_55] (rows=809521 width=100) keys:_col18,sort order:+,top n:100 - Merge Join Operator [MERGEJOIN_99] (rows=421645953 width=135) - Conds:RS_24._col2=RS_126._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] + Merge Join Operator [MERGEJOIN_99] (rows=809521 width=100) + Conds:RS_24._col2=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_124] PartitionCols:_col0 - Select Operator [SEL_125] (rows=462000 width=1436) + Select Operator [SEL_123] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_124] (rows=462000 width=1436) + Filter Operator [FIL_122] (rows=462000 width=104) predicate:i_item_sk is not null - TableScan [TS_12] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + TableScan [TS_12] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_98] (rows=383314495 width=135) - Conds:RS_21._col3=RS_118._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_98] (rows=809521 width=4) + Conds:RS_21._col3=RS_121._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] + SHUFFLE [RS_121] PartitionCols:_col0 - Select Operator [SEL_117] (rows=2300 width=1179) + Select Operator [SEL_120] (rows=2300 width=174) Output:["_col0"] - Filter Operator [FIL_116] (rows=2300 width=1179) + Filter Operator [FIL_119] (rows=2300 width=174) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) - TableScan [TS_9] (rows=2300 width=1179) - default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"] + TableScan [TS_9] (rows=2300 width=174) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk","p_channel_email","p_channel_event"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_97] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_97] (rows=809521 width=4) Conds:RS_18._col0=RS_110._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=36524 width=1119) + Select Operator [SEL_109] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_108] (rows=36524 width=1119) + Filter Operator [FIL_108] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_6] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_96] (rows=316788826 width=135) - Conds:RS_134._col1=RS_102._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_96] (rows=2283326 width=135) + Conds:RS_118._col1=RS_102._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] PartitionCols:_col0 - Select Operator [SEL_101] (rows=232725 width=385) + Select Operator [SEL_101] (rows=14776 width=265) Output:["_col0"] - Filter Operator [FIL_100] (rows=232725 width=385) + Filter Operator [FIL_100] (rows=14776 width=268) predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) - TableScan [TS_3] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] + TableScan [TS_3] (rows=1861800 width=268) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_134] + SHUFFLE [RS_118] PartitionCols:_col1 - Select Operator [SEL_133] (rows=287989836 width=135) + Select Operator [SEL_117] (rows=283691050 width=354) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_132] (rows=287989836 width=135) - predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (cs_promo_sk BETWEEN DynamicValue(RS_22_promotion_p_promo_sk_min) AND DynamicValue(RS_22_promotion_p_promo_sk_max) and in_bloom_filter(cs_promo_sk, DynamicValue(RS_22_promotion_p_promo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_cdemo_sk","cs_item_sk","cs_promo_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt"] + Filter Operator [FIL_116] (rows=283691050 width=354) + predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=354) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_cdemo_sk","cs_item_sk","cs_promo_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_115] Group By Operator [GBY_114] (rows=1 width=12) @@ -146,31 +144,9 @@ Stage-0 SHUFFLE [RS_113] Group By Operator [GBY_112] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_111] (rows=36524 width=1119) + Select Operator [SEL_111] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_109] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] - Group By Operator [GBY_120] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_119] (rows=2300 width=1179) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_117] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_131] - Group By Operator [GBY_130] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_129] - Group By Operator [GBY_128] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_127] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_125] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_107] Group By Operator [GBY_106] (rows=1 width=12) @@ -179,7 +155,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_105] Group By Operator [GBY_104] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_103] (rows=232725 width=385) + Select Operator [SEL_103] (rows=14776 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_101] diff --git a/ql/src/test/results/clientpositive/perf/tez/query27.q.out b/ql/src/test/results/clientpositive/perf/tez/query27.q.out index 20da0af5cc..9b49658ed8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query27.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query27.q.out @@ -45,10 +45,9 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) @@ -62,88 +61,88 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_141] - Limit [LIM_140] (rows=100 width=88) + File Output Operator [FS_136] + Limit [LIM_135] (rows=100 width=538) Number of rows:100 - Select Operator [SEL_139] (rows=1264972921 width=88) + Select Operator [SEL_134] (rows=4281825 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_138] - Select Operator [SEL_137] (rows=1264972921 width=88) + SHUFFLE [RS_133] + Select Operator [SEL_132] (rows=4281825 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_136] (rows=1264972921 width=88) + Group By Operator [GBY_131] (rows=4281825 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_29] (rows=2529945843 width=88) + Group By Operator [GBY_29] (rows=4281825 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col2)","count(_col2)","sum(_col3)","count(_col3)","sum(_col4)","count(_col4)","sum(_col5)","count(_col5)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_56] (rows=843315281 width=88) + Top N Key Operator [TNK_56] (rows=1427275 width=186) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_27] (rows=843315281 width=88) + Select Operator [SEL_27] (rows=1427275 width=186) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_100] (rows=843315281 width=88) - Conds:RS_24._col1=RS_127._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col15","_col17"] + Merge Join Operator [MERGEJOIN_100] (rows=1427275 width=186) + Conds:RS_24._col1=RS_130._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col15","_col17"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_127] + SHUFFLE [RS_130] PartitionCols:_col0 - Select Operator [SEL_126] (rows=462000 width=1436) + Select Operator [SEL_129] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_125] (rows=462000 width=1436) + Filter Operator [FIL_128] (rows=462000 width=104) predicate:i_item_sk is not null - TableScan [TS_12] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + TableScan [TS_12] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_99] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_99] (rows=1427275 width=90) Conds:RS_21._col3=RS_119._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col15"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_119] PartitionCols:_col0 - Select Operator [SEL_118] (rows=1704 width=1910) + Select Operator [SEL_118] (rows=209 width=90) Output:["_col0","_col1"] - Filter Operator [FIL_117] (rows=1704 width=1910) + Filter Operator [FIL_117] (rows=209 width=90) predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null) - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] + TableScan [TS_9] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_98] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_98] (rows=1441779 width=4) Conds:RS_18._col0=RS_111._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_111] PartitionCols:_col0 - Select Operator [SEL_110] (rows=36524 width=1119) + Select Operator [SEL_110] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_109] (rows=36524 width=1119) + Filter Operator [FIL_109] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_6] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_97] (rows=633595212 width=88) - Conds:RS_135._col2=RS_103._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_97] (rows=4037920 width=4) + Conds:RS_127._col2=RS_103._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_102] (rows=232725 width=385) + Select Operator [SEL_102] (rows=14776 width=269) Output:["_col0"] - Filter Operator [FIL_101] (rows=232725 width=385) + Filter Operator [FIL_101] (rows=14776 width=268) predicate:((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null) - TableScan [TS_3] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] + TableScan [TS_3] (rows=1861800 width=268) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] + SHUFFLE [RS_127] PartitionCols:_col2 - Select Operator [SEL_134] (rows=575995635 width=88) + Select Operator [SEL_126] (rows=501690006 width=340) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_133] (rows=575995635 width=88) - predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] + Filter Operator [FIL_125] (rows=501690006 width=340) + predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=340) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_116] Group By Operator [GBY_115] (rows=1 width=12) @@ -152,7 +151,7 @@ Stage-0 SHUFFLE [RS_114] Group By Operator [GBY_113] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_112] (rows=36524 width=1119) + Select Operator [SEL_112] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_110] <-Reducer 13 [BROADCAST_EDGE] vectorized @@ -163,20 +162,9 @@ Stage-0 SHUFFLE [RS_122] Group By Operator [GBY_121] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_120] (rows=1704 width=1910) + Select Operator [SEL_120] (rows=209 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_118] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_132] - Group By Operator [GBY_131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_130] - Group By Operator [GBY_129] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_128] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_126] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_108] Group By Operator [GBY_107] (rows=1 width=12) @@ -185,7 +173,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_106] Group By Operator [GBY_105] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_104] (rows=232725 width=385) + Select Operator [SEL_104] (rows=14776 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_102] diff --git a/ql/src/test/results/clientpositive/perf/tez/query28.q.out b/ql/src/test/results/clientpositive/perf/tez/query28.q.out index ca0bf37abf..f9ee08275f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query28.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query28.q.out @@ -126,143 +126,143 @@ Stage-0 Stage-1 Reducer 4 File Output Operator [FS_51] - Limit [LIM_50] (rows=1 width=1393) + Limit [LIM_50] (rows=1 width=768) Number of rows:100 - Select Operator [SEL_49] (rows=1 width=1393) + Select Operator [SEL_49] (rows=1 width=768) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] - Merge Join Operator [MERGEJOIN_94] (rows=1 width=1393) + Merge Join Operator [MERGEJOIN_94] (rows=1 width=768) Conds:(Inner),(Inner),(Inner),(Inner),(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] <-Reducer 10 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_142] - Select Operator [SEL_141] (rows=1 width=232) + Select Operator [SEL_141] (rows=1 width=128) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_140] (rows=1 width=232) + Group By Operator [GBY_140] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] <-Reducer 9 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_139] - Group By Operator [GBY_138] (rows=1 width=232) + Group By Operator [GBY_138] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_137] (rows=21333171 width=88) + Group By Operator [GBY_137] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_116] PartitionCols:_col0 - Group By Operator [GBY_110] (rows=21333171 width=88) + Group By Operator [GBY_110] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_104] (rows=21333171 width=88) + Select Operator [SEL_104] (rows=21333171 width=324) Output:["ss_list_price"] - Filter Operator [FIL_98] (rows=21333171 width=88) + Filter Operator [FIL_98] (rows=21333171 width=324) predicate:((ss_list_price BETWEEN 142 AND 152 or ss_coupon_amt BETWEEN 3054 AND 4054 or ss_wholesale_cost BETWEEN 80 AND 100) and ss_quantity BETWEEN 16 AND 20) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] + TableScan [TS_0] (rows=575995635 width=324) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_148] - Select Operator [SEL_147] (rows=1 width=232) + Select Operator [SEL_147] (rows=1 width=128) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_146] (rows=1 width=232) + Group By Operator [GBY_146] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_145] - Group By Operator [GBY_144] (rows=1 width=232) + Group By Operator [GBY_144] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_143] (rows=21333171 width=88) + Group By Operator [GBY_143] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_117] PartitionCols:_col0 - Group By Operator [GBY_111] (rows=21333171 width=88) + Group By Operator [GBY_111] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_105] (rows=21333171 width=88) + Select Operator [SEL_105] (rows=21333171 width=324) Output:["ss_list_price"] - Filter Operator [FIL_99] (rows=21333171 width=88) + Filter Operator [FIL_99] (rows=21333171 width=324) predicate:((ss_list_price BETWEEN 66 AND 76 or ss_coupon_amt BETWEEN 920 AND 1920 or ss_wholesale_cost BETWEEN 4 AND 24) and ss_quantity BETWEEN 11 AND 15) Please refer to the previous TableScan [TS_0] <-Reducer 14 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_154] - Select Operator [SEL_153] (rows=1 width=232) + Select Operator [SEL_153] (rows=1 width=128) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_152] (rows=1 width=232) + Group By Operator [GBY_152] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_151] - Group By Operator [GBY_150] (rows=1 width=232) + Group By Operator [GBY_150] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_149] (rows=21333171 width=88) + Group By Operator [GBY_149] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_118] PartitionCols:_col0 - Group By Operator [GBY_112] (rows=21333171 width=88) + Group By Operator [GBY_112] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_106] (rows=21333171 width=88) + Select Operator [SEL_106] (rows=21333171 width=324) Output:["ss_list_price"] - Filter Operator [FIL_100] (rows=21333171 width=88) + Filter Operator [FIL_100] (rows=21333171 width=324) predicate:((ss_list_price BETWEEN 91 AND 101 or ss_coupon_amt BETWEEN 1430 AND 2430 or ss_wholesale_cost BETWEEN 32 AND 52) and ss_quantity BETWEEN 6 AND 10) Please refer to the previous TableScan [TS_0] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_124] - Select Operator [SEL_123] (rows=1 width=232) + Select Operator [SEL_123] (rows=1 width=128) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_122] (rows=1 width=232) + Group By Operator [GBY_122] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_121] - Group By Operator [GBY_120] (rows=1 width=232) + Group By Operator [GBY_120] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_119] (rows=21333171 width=88) + Group By Operator [GBY_119] (rows=12468667 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_113] PartitionCols:_col0 - Group By Operator [GBY_107] (rows=21333171 width=88) + Group By Operator [GBY_107] (rows=12468667 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_101] (rows=21333171 width=88) + Select Operator [SEL_101] (rows=63999513 width=324) Output:["ss_list_price"] - Filter Operator [FIL_95] (rows=21333171 width=88) + Filter Operator [FIL_95] (rows=63999513 width=324) predicate:((ss_list_price BETWEEN 11 AND 21 or ss_coupon_amt BETWEEN 460 AND 1460 or ss_wholesale_cost BETWEEN 14 AND 34) and ss_quantity BETWEEN 0 AND 5) Please refer to the previous TableScan [TS_0] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_130] - Select Operator [SEL_129] (rows=1 width=232) + Select Operator [SEL_129] (rows=1 width=128) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_128] (rows=1 width=232) + Group By Operator [GBY_128] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_127] - Group By Operator [GBY_126] (rows=1 width=232) + Group By Operator [GBY_126] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_125] (rows=21333171 width=88) + Group By Operator [GBY_125] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_114] PartitionCols:_col0 - Group By Operator [GBY_108] (rows=21333171 width=88) + Group By Operator [GBY_108] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_102] (rows=21333171 width=88) + Select Operator [SEL_102] (rows=21333171 width=324) Output:["ss_list_price"] - Filter Operator [FIL_96] (rows=21333171 width=88) + Filter Operator [FIL_96] (rows=21333171 width=324) predicate:((ss_list_price BETWEEN 28 AND 38 or ss_coupon_amt BETWEEN 2513 AND 3513 or ss_wholesale_cost BETWEEN 42 AND 62) and ss_quantity BETWEEN 26 AND 30) Please refer to the previous TableScan [TS_0] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_136] - Select Operator [SEL_135] (rows=1 width=232) + Select Operator [SEL_135] (rows=1 width=128) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_134] (rows=1 width=232) + Group By Operator [GBY_134] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_133] - Group By Operator [GBY_132] (rows=1 width=232) + Group By Operator [GBY_132] (rows=1 width=128) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col2)","count(_col0)"] - Group By Operator [GBY_131] (rows=21333171 width=88) + Group By Operator [GBY_131] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_115] PartitionCols:_col0 - Group By Operator [GBY_109] (rows=21333171 width=88) + Group By Operator [GBY_109] (rows=10666585 width=226) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_list_price)","count(ss_list_price)"],keys:ss_list_price - Select Operator [SEL_103] (rows=21333171 width=88) + Select Operator [SEL_103] (rows=21333171 width=324) Output:["ss_list_price"] - Filter Operator [FIL_97] (rows=21333171 width=88) + Filter Operator [FIL_97] (rows=21333171 width=324) predicate:((ss_list_price BETWEEN 135 AND 145 or ss_coupon_amt BETWEEN 14180 AND 15180 or ss_wholesale_cost BETWEEN 38 AND 58) and ss_quantity BETWEEN 21 AND 25) Please refer to the previous TableScan [TS_0] diff --git a/ql/src/test/results/clientpositive/perf/tez/query29.q.out b/ql/src/test/results/clientpositive/perf/tez/query29.q.out index b05162282c..cc6b163a59 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query29.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query29.q.out @@ -93,226 +93,226 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 7 (BROADCAST_EDGE) -Map 8 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE) -Reducer 10 <- Reducer 15 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 20 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 22 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 13 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) +Map 10 <- Reducer 16 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) +Reducer 13 <- Map 22 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 14 <- Map 23 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 20 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 13 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 5 vectorized - File Output Operator [FS_260] - Limit [LIM_259] (rows=100 width=88) + File Output Operator [FS_254] + Limit [LIM_253] (rows=100 width=496) Number of rows:100 - Select Operator [SEL_258] (rows=463823414 width=88) + Select Operator [SEL_252] (rows=3389534374 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_257] - Group By Operator [GBY_256] (rows=463823414 width=88) + SHUFFLE [RS_251] + Group By Operator [GBY_250] (rows=3389534374 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_48] (rows=927646829 width=88) + Group By Operator [GBY_48] (rows=3389534374 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col14)","sum(_col22)","sum(_col3)"],keys:_col7, _col8, _col27, _col28 - Top N Key Operator [TNK_93] (rows=927646829 width=88) + Top N Key Operator [TNK_93] (rows=3389534374 width=483) keys:_col7, _col8, _col27, _col28,sort order:++++,top n:100 - Merge Join Operator [MERGEJOIN_205] (rows=927646829 width=88) + Merge Join Operator [MERGEJOIN_205] (rows=3389534374 width=483) Conds:RS_44._col1, _col2=RS_45._col14, _col13(Inner),Output:["_col3","_col7","_col8","_col14","_col22","_col27","_col28"] - <-Reducer 12 [SIMPLE_EDGE] + <-Reducer 2 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_44] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_199] (rows=7638375 width=10) + Conds:RS_216._col0=RS_208._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_208] + PartitionCols:_col0 + Select Operator [SEL_207] (rows=1957 width=8) + Output:["_col0"] + Filter Operator [FIL_206] (rows=1957 width=8) + predicate:((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_216] + PartitionCols:_col0 + Select Operator [SEL_215] (rows=285117831 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_214] (rows=285117831 width=15) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=15) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_213] + Group By Operator [GBY_212] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_211] + Group By Operator [GBY_210] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_209] (rows=1957 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_207] + <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col14, _col13 - Select Operator [SEL_40] (rows=843315281 width=88) + Select Operator [SEL_40] (rows=17201109 width=483) Output:["_col1","_col2","_col8","_col13","_col14","_col16","_col21","_col22"] - Merge Join Operator [MERGEJOIN_204] (rows=843315281 width=88) - Conds:RS_37._col3=RS_247._col0(Inner),Output:["_col5","_col10","_col11","_col13","_col18","_col19","_col21","_col22"] - <-Map 22 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_247] + Merge Join Operator [MERGEJOIN_204] (rows=17201109 width=483) + Conds:RS_37._col3=RS_249._col0(Inner),Output:["_col5","_col10","_col11","_col13","_col18","_col19","_col21","_col22"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_249] PartitionCols:_col0 - Select Operator [SEL_246] (rows=1704 width=1910) + Select Operator [SEL_248] (rows=1704 width=192) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_245] (rows=1704 width=1910) + Filter Operator [FIL_247] (rows=1704 width=192) predicate:s_store_sk is not null - TableScan [TS_25] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"] - <-Reducer 11 [SIMPLE_EDGE] + TableScan [TS_25] (rows=1704 width=192) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_203] (rows=766650239 width=88) - Conds:RS_34._col1=RS_239._col0(Inner),Output:["_col3","_col5","_col10","_col11","_col13","_col18","_col19"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_239] + Merge Join Operator [MERGEJOIN_203] (rows=17201109 width=296) + Conds:RS_34._col1=RS_246._col0(Inner),Output:["_col3","_col5","_col10","_col11","_col13","_col18","_col19"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_246] PartitionCols:_col0 - Select Operator [SEL_238] (rows=462000 width=1436) + Select Operator [SEL_245] (rows=462000 width=288) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_237] (rows=462000 width=1436) + Filter Operator [FIL_244] (rows=462000 width=288) predicate:i_item_sk is not null - TableScan [TS_22] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"] - <-Reducer 10 [SIMPLE_EDGE] + TableScan [TS_22] (rows=462000 width=288) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_202] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_202] (rows=17201109 width=16) Conds:RS_31._col1, _col2, _col4=RS_32._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col10","_col11","_col13"] - <-Reducer 15 [SIMPLE_EDGE] + <-Reducer 17 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_32] PartitionCols:_col1, _col2, _col3 - Merge Join Operator [MERGEJOIN_201] (rows=63350266 width=77) + Merge Join Operator [MERGEJOIN_201] (rows=1928802 width=8) Conds:RS_230._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 13 [SIMPLE_EDGE] vectorized + <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_223] PartitionCols:_col0 - Select Operator [SEL_220] (rows=4058 width=1119) + Select Operator [SEL_220] (rows=72 width=12) Output:["_col0"] - Filter Operator [FIL_218] (rows=4058 width=1119) + Filter Operator [FIL_218] (rows=72 width=12) predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 19 [SIMPLE_EDGE] vectorized + TableScan [TS_9] (rows=73049 width=12) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_230] PartitionCols:_col0 - Select Operator [SEL_229] (rows=57591150 width=77) + Select Operator [SEL_229] (rows=53632139 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_228] (rows=57591150 width=77) + Filter Operator [FIL_228] (rows=53632139 width=19) predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) - TableScan [TS_12] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] - <-Reducer 9 [SIMPLE_EDGE] + TableScan [TS_12] (rows=57591150 width=19) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_200] (rows=633595212 width=88) - Conds:RS_255._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 13 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_200] (rows=13737330 width=8) + Conds:RS_243._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_219] (rows=18262 width=1119) + Select Operator [SEL_219] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_217] (rows=18262 width=1119) + Filter Operator [FIL_217] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) Please refer to the previous TableScan [TS_9] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_255] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_243] PartitionCols:_col0 - Select Operator [SEL_254] (rows=575995635 width=88) + Select Operator [SEL_242] (rows=501694138 width=23) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_253] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_32_store_returns_sr_customer_sk_min) AND DynamicValue(RS_32_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_32_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_32_store_returns_sr_item_sk_min) AND DynamicValue(RS_32_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_32_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_35_item_i_item_sk_min) AND DynamicValue(RS_35_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_35_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_29_d1_d_date_sk_min) AND DynamicValue(RS_29_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_38_store_s_store_sk_min) AND DynamicValue(RS_38_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_38_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_32_store_returns_sr_ticket_number_min) AND DynamicValue(RS_32_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_32_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] - <-Reducer 14 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_241] (rows=501694138 width=23) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_32_store_returns_sr_customer_sk_min) AND DynamicValue(RS_32_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_32_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_44_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_44_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_44_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_32_store_returns_sr_item_sk_min) AND DynamicValue(RS_32_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_32_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_44_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_44_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_44_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_29_d1_d_date_sk_min) AND DynamicValue(RS_29_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_32_store_returns_sr_ticket_number_min) AND DynamicValue(RS_32_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_32_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_6] (rows=575995635 width=23) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] + <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_227] Group By Operator [GBY_226] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_225] Group By Operator [GBY_224] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_222] (rows=18262 width=1119) + Select Operator [SEL_222] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_219] - <-Reducer 16 [BROADCAST_EDGE] vectorized + <-Reducer 18 [BROADCAST_EDGE] vectorized BROADCAST [RS_232] Group By Operator [GBY_231] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 17 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_121] Group By Operator [GBY_120] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_119] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_119] (rows=1928802 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_201] - <-Reducer 17 [BROADCAST_EDGE] vectorized + <-Reducer 19 [BROADCAST_EDGE] vectorized BROADCAST [RS_234] Group By Operator [GBY_233] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 17 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_126] Group By Operator [GBY_125] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_124] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_124] (rows=1928802 width=0) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_201] - <-Reducer 18 [BROADCAST_EDGE] vectorized + <-Reducer 20 [BROADCAST_EDGE] vectorized BROADCAST [RS_236] Group By Operator [GBY_235] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1256246)"] + <-Reducer 17 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_131] Group By Operator [GBY_130] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_129] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1256246)"] + Select Operator [SEL_129] (rows=1928802 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_201] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_244] - Group By Operator [GBY_243] (rows=1 width=12) + <-Reducer 6 [BROADCAST_EDGE] vectorized + BROADCAST [RS_238] + Group By Operator [GBY_237] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_242] - Group By Operator [GBY_241] (rows=1 width=12) + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_146] + Group By Operator [GBY_145] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_240] (rows=462000 width=1436) + Select Operator [SEL_144] (rows=7638375 width=6) Output:["_col0"] - Please refer to the previous Select Operator [SEL_238] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_252] - Group By Operator [GBY_251] (rows=1 width=12) + Please refer to the previous Merge Join Operator [MERGEJOIN_199] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_240] + Group By Operator [GBY_239] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_250] - Group By Operator [GBY_249] (rows=1 width=12) + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_151] + Group By Operator [GBY_150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_248] (rows=1704 width=1910) + Select Operator [SEL_149] (rows=7638375 width=8) Output:["_col0"] - Please refer to the previous Select Operator [SEL_246] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_44] - PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_199] (rows=316788826 width=135) - Conds:RS_216._col0=RS_208._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 6 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_208] - PartitionCols:_col0 - Select Operator [SEL_207] (rows=73049 width=1119) - Output:["_col0"] - Filter Operator [FIL_206] (rows=73049 width=1119) - predicate:((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] - PartitionCols:_col0 - Select Operator [SEL_215] (rows=287989836 width=135) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_214] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_213] - Group By Operator [GBY_212] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_211] - Group By Operator [GBY_210] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_209] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_207] + Please refer to the previous Merge Join Operator [MERGEJOIN_199] diff --git a/ql/src/test/results/clientpositive/perf/tez/query3.q.out b/ql/src/test/results/clientpositive/perf/tez/query3.q.out index 801b4f94ac..19f7ffbc4a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query3.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query3.q.out @@ -55,53 +55,53 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_77] - Limit [LIM_76] (rows=100 width=88) + Limit [LIM_76] (rows=100 width=220) Number of rows:100 - Select Operator [SEL_75] (rows=348477374 width=88) + Select Operator [SEL_75] (rows=274400 width=220) Output:["_col0","_col1","_col2","_col3"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_74] - Group By Operator [GBY_73] (rows=348477374 width=88) + Group By Operator [GBY_73] (rows=274400 width=220) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=274400 width=220) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col8, _col4, _col5 - Merge Join Operator [MERGEJOIN_53] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_53] (rows=589741 width=108) Conds:RS_12._col0=RS_64._col0(Inner),Output:["_col2","_col4","_col5","_col8"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_64] PartitionCols:_col0 - Select Operator [SEL_63] (rows=36524 width=1119) + Select Operator [SEL_63] (rows=5619 width=12) Output:["_col0","_col1"] - Filter Operator [FIL_62] (rows=36524 width=1119) + Filter Operator [FIL_62] (rows=5619 width=12) predicate:((d_moy = 12) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,dt,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,dt,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_52] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_52] (rows=7666836 width=104) Conds:RS_72._col1=RS_56._col0(Inner),Output:["_col0","_col2","_col4","_col5"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_56] PartitionCols:_col0 - Select Operator [SEL_55] (rows=231000 width=1436) + Select Operator [SEL_55] (rows=669 width=111) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_54] (rows=231000 width=1436) + Filter Operator [FIL_54] (rows=669 width=111) predicate:((i_manufact_id = 436) and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id"] + TableScan [TS_3] (rows=462000 width=111) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_72] PartitionCols:_col1 - Select Operator [SEL_71] (rows=575995635 width=88) + Select Operator [SEL_71] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_70] (rows=575995635 width=88) + Filter Operator [FIL_70] (rows=550076554 width=114) predicate:((ss_item_sk BETWEEN DynamicValue(RS_10_item_i_item_sk_min) AND DynamicValue(RS_10_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_10_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_13_dt_d_date_sk_min) AND DynamicValue(RS_13_dt_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_dt_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_61] Group By Operator [GBY_60] (rows=1 width=12) @@ -110,7 +110,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_59] Group By Operator [GBY_58] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_57] (rows=231000 width=1436) + Select Operator [SEL_57] (rows=669 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_55] <-Reducer 9 [BROADCAST_EDGE] vectorized @@ -121,7 +121,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_67] Group By Operator [GBY_66] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_65] (rows=36524 width=1119) + Select Operator [SEL_65] (rows=5619 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_63] diff --git a/ql/src/test/results/clientpositive/perf/tez/query30.q.out b/ql/src/test/results/clientpositive/perf/tez/query30.q.out index 802a6e7dd0..d74d844f64 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query30.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query30.q.out @@ -78,130 +78,130 @@ Stage-0 Stage-1 Reducer 4 vectorized File Output Operator [FS_210] - Limit [LIM_209] (rows=100 width=860) + Limit [LIM_209] (rows=100 width=942) Number of rows:100 - Select Operator [SEL_208] (rows=96800003 width=860) + Select Operator [SEL_208] (rows=691171 width=942) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_63] - Select Operator [SEL_62] (rows=96800003 width=860) + Select Operator [SEL_62] (rows=691171 width=942) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - Merge Join Operator [MERGEJOIN_177] (rows=96800003 width=860) + Merge Join Operator [MERGEJOIN_177] (rows=691171 width=942) Conds:RS_59._col0=RS_60._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col18"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_171] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_171] (rows=1568628 width=834) Conds:RS_180._col2=RS_187._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_187] PartitionCols:_col0 - Select Operator [SEL_184] (rows=20000000 width=1014) + Select Operator [SEL_184] (rows=784314 width=90) Output:["_col0"] - Filter Operator [FIL_181] (rows=20000000 width=1014) + Filter Operator [FIL_181] (rows=784314 width=90) predicate:((ca_state = 'IL') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + TableScan [TS_3] (rows=40000000 width=90) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_180] PartitionCols:_col2 - Select Operator [SEL_179] (rows=80000000 width=860) + Select Operator [SEL_179] (rows=80000000 width=849) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Filter Operator [FIL_178] (rows=80000000 width=860) + Filter Operator [FIL_178] (rows=80000000 width=849) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_day","c_birth_month","c_birth_year","c_birth_country","c_login","c_email_address","c_last_review_date"] + TableScan [TS_0] (rows=80000000 width=849) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_day","c_birth_month","c_birth_year","c_birth_country","c_login","c_email_address","c_last_review_date"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_60] PartitionCols:_col0 - Select Operator [SEL_55] (rows=8066666 width=1014) + Select Operator [SEL_55] (rows=704993 width=227) Output:["_col0","_col2"] - Filter Operator [FIL_54] (rows=8066666 width=1014) + Filter Operator [FIL_54] (rows=704993 width=227) predicate:(_col2 > _col3) - Merge Join Operator [MERGEJOIN_176] (rows=24200000 width=1014) + Merge Join Operator [MERGEJOIN_176] (rows=2114980 width=227) Conds:RS_202._col1=RS_207._col1(Inner),Output:["_col0","_col2","_col3"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_207] PartitionCols:_col1 - Select Operator [SEL_206] (rows=11000000 width=1014) + Select Operator [SEL_206] (rows=6 width=198) Output:["_col0","_col1"] - Group By Operator [GBY_205] (rows=11000000 width=1014) + Group By Operator [GBY_205] (rows=6 width=206) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col0 - Select Operator [SEL_204] (rows=22000000 width=1014) + Select Operator [SEL_204] (rows=2537976 width=201) Output:["_col0","_col2"] - Group By Operator [GBY_203] (rows=22000000 width=1014) + Group By Operator [GBY_203] (rows=2537976 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0 - Group By Operator [GBY_42] (rows=44000000 width=1014) + Group By Operator [GBY_42] (rows=3923529 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_175] (rows=44000000 width=1014) + Merge Join Operator [MERGEJOIN_175] (rows=3923529 width=184) Conds:RS_38._col2=RS_189._col0(Inner),Output:["_col1","_col3","_col7"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_189] PartitionCols:_col0 - Select Operator [SEL_186] (rows=40000000 width=1014) + Select Operator [SEL_186] (rows=40000000 width=90) Output:["_col0","_col1"] - Filter Operator [FIL_183] (rows=40000000 width=1014) + Filter Operator [FIL_183] (rows=40000000 width=90) predicate:(ca_address_sk is not null and ca_state is not null) Please refer to the previous TableScan [TS_3] <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_174] (rows=15838314 width=92) + Merge Join Operator [MERGEJOIN_174] (rows=3923529 width=101) Conds:RS_195._col0=RS_199._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_195] PartitionCols:_col0 - Select Operator [SEL_193] (rows=14398467 width=92) + Select Operator [SEL_193] (rows=13130761 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_191] (rows=14398467 width=92) + Filter Operator [FIL_191] (rows=13130761 width=118) predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null) - TableScan [TS_6] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"] + TableScan [TS_6] (rows=14398467 width=118) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_199] PartitionCols:_col0 - Select Operator [SEL_197] (rows=36524 width=1119) + Select Operator [SEL_197] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_196] (rows=36524 width=1119) + Filter Operator [FIL_196] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_9] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_202] PartitionCols:_col1 - Select Operator [SEL_201] (rows=22000000 width=1014) + Select Operator [SEL_201] (rows=2114980 width=201) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_200] (rows=22000000 width=1014) + Group By Operator [GBY_200] (rows=2114980 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0, _col1 - Group By Operator [GBY_22] (rows=44000000 width=1014) + Group By Operator [GBY_22] (rows=3746772 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_173] (rows=44000000 width=1014) + Merge Join Operator [MERGEJOIN_173] (rows=3746772 width=184) Conds:RS_18._col2=RS_188._col0(Inner),Output:["_col1","_col3","_col7"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_188] PartitionCols:_col0 - Select Operator [SEL_185] (rows=40000000 width=1014) + Select Operator [SEL_185] (rows=40000000 width=90) Output:["_col0","_col1"] - Filter Operator [FIL_182] (rows=40000000 width=1014) + Filter Operator [FIL_182] (rows=40000000 width=90) predicate:(ca_address_sk is not null and ca_state is not null) Please refer to the previous TableScan [TS_3] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_172] (rows=15838314 width=92) + Merge Join Operator [MERGEJOIN_172] (rows=3746772 width=101) Conds:RS_194._col0=RS_198._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] PartitionCols:_col0 - Select Operator [SEL_192] (rows=14398467 width=92) + Select Operator [SEL_192] (rows=12539215 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_190] (rows=14398467 width=92) + Filter Operator [FIL_190] (rows=12539215 width=118) predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null and wr_returning_customer_sk is not null) Please refer to the previous TableScan [TS_6] <-Map 14 [SIMPLE_EDGE] vectorized diff --git a/ql/src/test/results/clientpositive/perf/tez/query31.q.out b/ql/src/test/results/clientpositive/perf/tez/query31.q.out index 22aee37ca4..cef8e0693f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query31.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query31.q.out @@ -103,43 +103,37 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 30 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Map 36 <- Reducer 11 (BROADCAST_EDGE), Reducer 31 (BROADCAST_EDGE) -Map 37 <- Reducer 15 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE) -Map 38 <- Reducer 20 (BROADCAST_EDGE), Reducer 33 (BROADCAST_EDGE) -Map 39 <- Reducer 24 (BROADCAST_EDGE), Reducer 34 (BROADCAST_EDGE) -Map 40 <- Reducer 28 (BROADCAST_EDGE), Reducer 35 (BROADCAST_EDGE) +Map 1 <- Reducer 7 (BROADCAST_EDGE) +Map 30 <- Reducer 11 (BROADCAST_EDGE) +Map 31 <- Reducer 15 (BROADCAST_EDGE) +Map 32 <- Reducer 20 (BROADCAST_EDGE) +Map 33 <- Reducer 24 (BROADCAST_EDGE) +Map 34 <- Reducer 28 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 11 <- Map 6 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 37 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 12 <- Map 31 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 13 <- Map 29 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Reducer 13 (SIMPLE_EDGE) Reducer 15 <- Map 6 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 38 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 16 <- Map 32 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 17 <- Map 29 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) Reducer 18 <- Reducer 17 (SIMPLE_EDGE) Reducer 19 <- Reducer 18 (ONE_TO_ONE_EDGE), Reducer 23 (ONE_TO_ONE_EDGE), Reducer 27 (ONE_TO_ONE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 20 <- Map 6 (CUSTOM_SIMPLE_EDGE) -Reducer 21 <- Map 39 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 21 <- Map 33 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 22 <- Map 29 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) Reducer 23 <- Reducer 22 (SIMPLE_EDGE) Reducer 24 <- Map 6 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 40 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 25 <- Map 34 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 26 <- Map 29 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) Reducer 27 <- Reducer 26 (SIMPLE_EDGE) Reducer 28 <- Map 6 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 29 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 30 <- Map 29 (CUSTOM_SIMPLE_EDGE) -Reducer 31 <- Map 29 (CUSTOM_SIMPLE_EDGE) -Reducer 32 <- Map 29 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 29 (CUSTOM_SIMPLE_EDGE) -Reducer 34 <- Map 29 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Map 29 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 10 (ONE_TO_ONE_EDGE), Reducer 14 (ONE_TO_ONE_EDGE), Reducer 19 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Map 36 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 8 <- Map 30 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 9 <- Map 29 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 @@ -148,372 +142,306 @@ Stage-0 Stage-1 Reducer 5 File Output Operator [FS_133] - Select Operator [SEL_132] (rows=287493839 width=88) + Select Operator [SEL_132] (rows=110 width=550) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_130] (rows=287493839 width=88) + Filter Operator [FIL_130] (rows=110 width=770) predicate:(CASE WHEN ((_col1 > 0)) THEN (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > (_col5 / _col1))) ELSE ((null > (_col5 / _col1))) END) ELSE (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > null)) ELSE (null) END) END and CASE WHEN ((_col3 > 0)) THEN (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > (_col1 / _col3))) ELSE ((null > (_col1 / _col3))) END) ELSE (CASE WHEN ((_col7 > 0)) THEN (((_col9 / _col7) > null)) ELSE (null) END) END) - Merge Join Operator [MERGEJOIN_448] (rows=1149975359 width=88) - Conds:RS_519._col0=RS_528._col0(Inner),RS_519._col0=RS_537._col0(Inner),RS_519._col0=RS_128._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col7","_col9","_col11"] + Merge Join Operator [MERGEJOIN_448] (rows=440 width=770) + Conds:RS_499._col0=RS_506._col0(Inner),RS_499._col0=RS_513._col0(Inner),RS_499._col0=RS_128._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col7","_col9","_col11"] <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_528] + FORWARD [RS_506] PartitionCols:_col0 - Group By Operator [GBY_527] (rows=348477374 width=88) + Group By Operator [GBY_505] (rows=1605 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 - Group By Operator [GBY_36] (rows=696954748 width=88) + Group By Operator [GBY_36] (rows=33705 width=210) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_438] (rows=696954748 width=88) - Conds:RS_32._col1=RS_491._col0(Inner),Output:["_col2","_col7"] + Merge Join Operator [MERGEJOIN_438] (rows=37399561 width=139) + Conds:RS_32._col1=RS_493._col0(Inner),Output:["_col2","_col7"] <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_491] + SHUFFLE [RS_493] PartitionCols:_col0 - Select Operator [SEL_488] (rows=40000000 width=1014) + Select Operator [SEL_491] (rows=40000000 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_487] (rows=40000000 width=1014) + Filter Operator [FIL_490] (rows=40000000 width=102) predicate:(ca_address_sk is not null and ca_county is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county"] + TableScan [TS_6] (rows=40000000 width=102) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_437] (rows=633595212 width=88) - Conds:RS_526._col0=RS_463._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_437] (rows=37399561 width=42) + Conds:RS_504._col0=RS_463._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_463] PartitionCols:_col0 - Select Operator [SEL_456] (rows=18262 width=1119) + Select Operator [SEL_456] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_450] (rows=18262 width=1119) + Filter Operator [FIL_450] (rows=130 width=12) predicate:((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 36 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_526] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_504] PartitionCols:_col0 - Select Operator [SEL_525] (rows=575995635 width=88) + Select Operator [SEL_503] (rows=525327191 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_524] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_33_customer_address_ca_address_sk_min) AND DynamicValue(RS_33_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_33_customer_address_ca_address_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_20] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] + Filter Operator [FIL_502] (rows=525327191 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_20] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_521] - Group By Operator [GBY_520] (rows=1 width=12) + BROADCAST [RS_501] + Group By Operator [GBY_500] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_480] Group By Operator [GBY_474] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_464] (rows=18262 width=1119) + Select Operator [SEL_464] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_456] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_523] - Group By Operator [GBY_522] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_508] - Group By Operator [GBY_502] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_492] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_488] <-Reducer 14 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_537] + FORWARD [RS_513] PartitionCols:_col0 - Group By Operator [GBY_536] (rows=348477374 width=88) + Group By Operator [GBY_512] (rows=1605 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col0 - Group By Operator [GBY_56] (rows=696954748 width=88) + Group By Operator [GBY_56] (rows=33705 width=210) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_440] (rows=696954748 width=88) - Conds:RS_52._col1=RS_493._col0(Inner),Output:["_col2","_col7"] + Merge Join Operator [MERGEJOIN_440] (rows=37399561 width=139) + Conds:RS_52._col1=RS_494._col0(Inner),Output:["_col2","_col7"] <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_493] + SHUFFLE [RS_494] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_488] + Please refer to the previous Select Operator [SEL_491] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_439] (rows=633595212 width=88) - Conds:RS_535._col0=RS_465._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_439] (rows=37399561 width=42) + Conds:RS_511._col0=RS_465._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_465] PartitionCols:_col0 - Select Operator [SEL_457] (rows=18262 width=1119) + Select Operator [SEL_457] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_451] (rows=18262 width=1119) + Filter Operator [FIL_451] (rows=130 width=12) predicate:((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_535] + <-Map 31 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_511] PartitionCols:_col0 - Select Operator [SEL_534] (rows=575995635 width=88) + Select Operator [SEL_510] (rows=525327191 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_533] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_53_customer_address_ca_address_sk_min) AND DynamicValue(RS_53_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_53_customer_address_ca_address_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_40] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] + Filter Operator [FIL_509] (rows=525327191 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_40] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_530] - Group By Operator [GBY_529] (rows=1 width=12) + BROADCAST [RS_508] + Group By Operator [GBY_507] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_481] Group By Operator [GBY_475] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_466] (rows=18262 width=1119) + Select Operator [SEL_466] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_457] - <-Reducer 32 [BROADCAST_EDGE] vectorized - BROADCAST [RS_532] - Group By Operator [GBY_531] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_509] - Group By Operator [GBY_503] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_494] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_488] <-Reducer 19 [ONE_TO_ONE_EDGE] FORWARD [RS_128] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_447] (rows=191667561 width=135) - Conds:RS_546._col0=RS_555._col0(Inner),RS_546._col0=RS_564._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + Merge Join Operator [MERGEJOIN_447] (rows=440 width=434) + Conds:RS_520._col0=RS_527._col0(Inner),RS_520._col0=RS_534._col0(Inner),Output:["_col0","_col1","_col3","_col5"] <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_546] + FORWARD [RS_520] PartitionCols:_col0 - Group By Operator [GBY_545] (rows=87121617 width=135) + Group By Operator [GBY_519] (rows=440 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col0 - Group By Operator [GBY_76] (rows=174243235 width=135) + Group By Operator [GBY_76] (rows=3960 width=210) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_442] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_442] (rows=10246882 width=209) Conds:RS_72._col1=RS_495._col0(Inner),Output:["_col2","_col7"] <-Map 29 [SIMPLE_EDGE] vectorized SHUFFLE [RS_495] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_488] + Please refer to the previous Select Operator [SEL_491] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_72] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_441] (rows=158402938 width=135) - Conds:RS_544._col0=RS_467._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_441] (rows=10246882 width=115) + Conds:RS_518._col0=RS_467._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_467] PartitionCols:_col0 - Select Operator [SEL_458] (rows=18262 width=1119) + Select Operator [SEL_458] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_452] (rows=18262 width=1119) + Filter Operator [FIL_452] (rows=130 width=12) predicate:((d_qoy = 1) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_544] + <-Map 32 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_518] PartitionCols:_col0 - Select Operator [SEL_543] (rows=144002668 width=135) + Select Operator [SEL_517] (rows=143931246 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_542] (rows=144002668 width=135) - predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_73_customer_address_ca_address_sk_min) AND DynamicValue(RS_73_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_73_customer_address_ca_address_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_70_date_dim_d_date_sk_min) AND DynamicValue(RS_70_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_70_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_60] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + Filter Operator [FIL_516] (rows=143931246 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_70_date_dim_d_date_sk_min) AND DynamicValue(RS_70_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_70_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_60] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_539] - Group By Operator [GBY_538] (rows=1 width=12) + BROADCAST [RS_515] + Group By Operator [GBY_514] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_482] Group By Operator [GBY_476] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_468] (rows=18262 width=1119) + Select Operator [SEL_468] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_458] - <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_541] - Group By Operator [GBY_540] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_510] - Group By Operator [GBY_504] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_496] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_488] <-Reducer 23 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_555] + FORWARD [RS_527] PartitionCols:_col0 - Group By Operator [GBY_554] (rows=87121617 width=135) + Group By Operator [GBY_526] (rows=440 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col0 - Group By Operator [GBY_96] (rows=174243235 width=135) + Group By Operator [GBY_96] (rows=3960 width=210) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_444] (rows=174243235 width=135) - Conds:RS_92._col1=RS_497._col0(Inner),Output:["_col2","_col7"] + Merge Join Operator [MERGEJOIN_444] (rows=10246882 width=209) + Conds:RS_92._col1=RS_496._col0(Inner),Output:["_col2","_col7"] <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_497] + SHUFFLE [RS_496] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_488] + Please refer to the previous Select Operator [SEL_491] <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_92] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_443] (rows=158402938 width=135) - Conds:RS_553._col0=RS_469._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_443] (rows=10246882 width=115) + Conds:RS_525._col0=RS_469._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_469] PartitionCols:_col0 - Select Operator [SEL_459] (rows=18262 width=1119) + Select Operator [SEL_459] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_453] (rows=18262 width=1119) + Filter Operator [FIL_453] (rows=130 width=12) predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 39 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_553] + <-Map 33 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_525] PartitionCols:_col0 - Select Operator [SEL_552] (rows=144002668 width=135) + Select Operator [SEL_524] (rows=143931246 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_551] (rows=144002668 width=135) - predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_93_customer_address_ca_address_sk_min) AND DynamicValue(RS_93_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_93_customer_address_ca_address_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_90_date_dim_d_date_sk_min) AND DynamicValue(RS_90_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_90_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_80] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + Filter Operator [FIL_523] (rows=143931246 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_90_date_dim_d_date_sk_min) AND DynamicValue(RS_90_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_90_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_80] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_548] - Group By Operator [GBY_547] (rows=1 width=12) + BROADCAST [RS_522] + Group By Operator [GBY_521] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_483] Group By Operator [GBY_477] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_470] (rows=18262 width=1119) + Select Operator [SEL_470] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_459] - <-Reducer 34 [BROADCAST_EDGE] vectorized - BROADCAST [RS_550] - Group By Operator [GBY_549] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_511] - Group By Operator [GBY_505] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_498] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_488] <-Reducer 27 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_564] + FORWARD [RS_534] PartitionCols:_col0 - Group By Operator [GBY_563] (rows=87121617 width=135) + Group By Operator [GBY_533] (rows=440 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_117] PartitionCols:_col0 - Group By Operator [GBY_116] (rows=174243235 width=135) + Group By Operator [GBY_116] (rows=3960 width=210) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_446] (rows=174243235 width=135) - Conds:RS_112._col1=RS_499._col0(Inner),Output:["_col2","_col7"] + Merge Join Operator [MERGEJOIN_446] (rows=10246882 width=209) + Conds:RS_112._col1=RS_497._col0(Inner),Output:["_col2","_col7"] <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_499] + SHUFFLE [RS_497] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_488] + Please refer to the previous Select Operator [SEL_491] <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_112] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_445] (rows=158402938 width=135) - Conds:RS_562._col0=RS_471._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_445] (rows=10246882 width=115) + Conds:RS_532._col0=RS_471._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_471] PartitionCols:_col0 - Select Operator [SEL_460] (rows=18262 width=1119) + Select Operator [SEL_460] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_454] (rows=18262 width=1119) + Filter Operator [FIL_454] (rows=130 width=12) predicate:((d_qoy = 3) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_562] + <-Map 34 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_532] PartitionCols:_col0 - Select Operator [SEL_561] (rows=144002668 width=135) + Select Operator [SEL_531] (rows=143931246 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_560] (rows=144002668 width=135) - predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_113_customer_address_ca_address_sk_min) AND DynamicValue(RS_113_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_113_customer_address_ca_address_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_110_date_dim_d_date_sk_min) AND DynamicValue(RS_110_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_110_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_100] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] + Filter Operator [FIL_530] (rows=143931246 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_110_date_dim_d_date_sk_min) AND DynamicValue(RS_110_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_110_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_100] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 28 [BROADCAST_EDGE] vectorized - BROADCAST [RS_557] - Group By Operator [GBY_556] (rows=1 width=12) + BROADCAST [RS_529] + Group By Operator [GBY_528] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_484] Group By Operator [GBY_478] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_472] (rows=18262 width=1119) + Select Operator [SEL_472] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_460] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_559] - Group By Operator [GBY_558] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_512] - Group By Operator [GBY_506] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_500] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_488] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_519] + FORWARD [RS_499] PartitionCols:_col0 - Group By Operator [GBY_518] (rows=348477374 width=88) + Group By Operator [GBY_498] (rows=1605 width=210) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=33705 width=210) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col7 - Merge Join Operator [MERGEJOIN_436] (rows=696954748 width=88) - Conds:RS_12._col1=RS_489._col0(Inner),Output:["_col2","_col7"] + Merge Join Operator [MERGEJOIN_436] (rows=37399561 width=139) + Conds:RS_12._col1=RS_492._col0(Inner),Output:["_col2","_col7"] <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_489] + SHUFFLE [RS_492] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_488] + Please refer to the previous Select Operator [SEL_491] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_435] (rows=633595212 width=88) - Conds:RS_517._col0=RS_461._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_435] (rows=37399561 width=42) + Conds:RS_489._col0=RS_461._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_461] PartitionCols:_col0 - Select Operator [SEL_455] (rows=18262 width=1119) + Select Operator [SEL_455] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_449] (rows=18262 width=1119) + Filter Operator [FIL_449] (rows=130 width=12) predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_517] + SHUFFLE [RS_489] PartitionCols:_col0 - Select Operator [SEL_516] (rows=575995635 width=88) + Select Operator [SEL_488] (rows=525327191 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_515] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_13_customer_address_ca_address_sk_min) AND DynamicValue(RS_13_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_13_customer_address_ca_address_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_514] - Group By Operator [GBY_513] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_507] - Group By Operator [GBY_501] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_490] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_488] + Filter Operator [FIL_487] (rows=525327191 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_486] Group By Operator [GBY_485] (rows=1 width=12) @@ -522,7 +450,7 @@ Stage-0 SHUFFLE [RS_479] Group By Operator [GBY_473] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_462] (rows=18262 width=1119) + Select Operator [SEL_462] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_455] diff --git a/ql/src/test/results/clientpositive/perf/tez/query32.q.out b/ql/src/test/results/clientpositive/perf/tez/query32.q.out index 2a472c1f55..ab0db24494 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query32.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query32.q.out @@ -55,105 +55,148 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (ONE_TO_ONE_EDGE) +Map 1 <- Reducer 14 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Map 12 <- Reducer 11 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 5 (BROADCAST_EDGE) +Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (ONE_TO_ONE_EDGE) +Reducer 11 <- Map 6 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 10 (ONE_TO_ONE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) -Reducer 5 <- Reducer 2 (SIMPLE_EDGE) -Reducer 6 <- Map 9 (SIMPLE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) -Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 12 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_129] - Limit [LIM_128] (rows=1 width=112) + File Output Operator [FS_141] + Limit [LIM_140] (rows=1 width=112) Number of rows:100 - Group By Operator [GBY_127] (rows=1 width=112) + Group By Operator [GBY_139] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_36] Group By Operator [GBY_35] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col2)"] - Select Operator [SEL_34] (rows=116155905 width=135) + Select Operator [SEL_34] (rows=2478 width=112) Output:["_col2"] - Filter Operator [FIL_33] (rows=116155905 width=135) + Filter Operator [FIL_33] (rows=2478 width=112) predicate:(_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) - Merge Join Operator [MERGEJOIN_104] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_104] (rows=7434 width=112) Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col6"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_30] + PARTITION_ONLY_SHUFFLE [RS_30] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_101] (rows=316788826 width=135) - Conds:RS_123._col0=RS_107._col0(Inner),Output:["_col1","_col2"] - <-Map 7 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_107] + Merge Join Operator [MERGEJOIN_101] (rows=31836679 width=110) + Conds:RS_128._col0=RS_107._col0(Inner),Output:["_col1","_col2"] + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_107] PartitionCols:_col0 - Select Operator [SEL_106] (rows=8116 width=1119) + Select Operator [SEL_106] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_105] (rows=8116 width=1119) + Filter Operator [FIL_105] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] + SHUFFLE [RS_128] PartitionCols:_col0 - Select Operator [SEL_122] (rows=287989836 width=135) + Select Operator [SEL_127] (rows=286549727 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_121] (rows=287989836 width=135) + Filter Operator [FIL_126] (rows=286549727 width=119) predicate:((cs_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_120] - Group By Operator [GBY_119] (rows=1 width=12) + TableScan [TS_0] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_124] + Group By Operator [GBY_123] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] - Group By Operator [GBY_117] (rows=1 width=12) + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_122] + Group By Operator [GBY_121] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_116] (rows=231000 width=1436) + Select Operator [SEL_120] (rows=669 width=4) Output:["_col0"] - Select Operator [SEL_114] (rows=231000 width=1436) + Select Operator [SEL_118] (rows=669 width=8) Output:["_col0"] - Filter Operator [FIL_113] (rows=231000 width=1436) + Filter Operator [FIL_117] (rows=669 width=7) predicate:((i_manufact_id = 269) and i_item_sk is not null) - TableScan [TS_20] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_112] - Group By Operator [GBY_111] (rows=1 width=12) + TableScan [TS_20] (rows=462000 width=7) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_manufact_id"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_116] + Group By Operator [GBY_115] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_110] - Group By Operator [GBY_109] (rows=1 width=12) + <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_113] + Group By Operator [GBY_111] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_108] (rows=8116 width=1119) + Select Operator [SEL_108] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_106] - <-Reducer 6 [ONE_TO_ONE_EDGE] + <-Reducer 10 [ONE_TO_ONE_EDGE] FORWARD [RS_31] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_103] (rows=174233858 width=135) - Conds:RS_126._col0=RS_115._col0(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_115] + Merge Join Operator [MERGEJOIN_103] (rows=97 width=116) + Conds:RS_138._col0=RS_119._col0(Inner),Output:["_col1","_col2"] + <-Map 13 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_119] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_114] - <-Reducer 5 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_126] + Please refer to the previous Select Operator [SEL_118] + <-Reducer 9 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_138] PartitionCols:_col0 - Select Operator [SEL_125] (rows=158394413 width=135) + Select Operator [SEL_137] (rows=6951 width=116) Output:["_col0","_col1"] - Group By Operator [GBY_124] (rows=158394413 width=135) + Group By Operator [GBY_136] (rows=6951 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 - <-Reducer 2 [SIMPLE_EDGE] + <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=316788826 width=135) + Group By Operator [GBY_16] (rows=97314 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Please refer to the previous Merge Join Operator [MERGEJOIN_101] + Merge Join Operator [MERGEJOIN_102] (rows=31836679 width=110) + Conds:RS_135._col0=RS_109._col0(Inner),Output:["_col1","_col2"] + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_109] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_106] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_135] + PartitionCols:_col0 + Select Operator [SEL_134] (rows=286549727 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_133] (rows=286549727 width=119) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_30_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_30_catalog_sales_cs_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_30_catalog_sales_cs_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_6] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_discount_amt"] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_125] + Please refer to the previous Group By Operator [GBY_123] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_130] + Group By Operator [GBY_129] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] + Group By Operator [GBY_112] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_110] (rows=8116 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_106] + <-Reducer 5 [BROADCAST_EDGE] vectorized + BROADCAST [RS_132] + Group By Operator [GBY_131] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_91] + Group By Operator [GBY_90] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_89] (rows=31836679 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_101] diff --git a/ql/src/test/results/clientpositive/perf/tez/query33.q.out b/ql/src/test/results/clientpositive/perf/tez/query33.q.out index 30871e5490..84d5f9ba33 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query33.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query33.q.out @@ -149,324 +149,288 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 17 <- Reducer 21 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 32 <- Reducer 11 (BROADCAST_EDGE), Reducer 24 (BROADCAST_EDGE), Reducer 30 (BROADCAST_EDGE) -Map 33 <- Reducer 14 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 31 (BROADCAST_EDGE) -Reducer 10 <- Reducer 9 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 11 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Reducer 2 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 14 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 19 <- Map 28 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 16 (ONE_TO_ONE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 20 (SIMPLE_EDGE), Map 32 (SIMPLE_EDGE) -Reducer 23 <- Map 28 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) -Reducer 24 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 20 (SIMPLE_EDGE), Map 33 (SIMPLE_EDGE) -Reducer 26 <- Map 28 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) -Reducer 27 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 19 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 30 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 31 <- Map 28 (CUSTOM_SIMPLE_EDGE) +Map 14 <- Reducer 18 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE) +Map 29 <- Reducer 21 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE) +Map 30 <- Reducer 24 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE) +Reducer 10 <- Reducer 2 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 13 <- Map 12 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 16 <- Map 25 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 29 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 13 (ONE_TO_ONE_EDGE) +Reducer 20 <- Map 25 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 21 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 22 <- Map 17 (SIMPLE_EDGE), Map 30 (SIMPLE_EDGE) +Reducer 23 <- Map 25 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 24 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 26 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 27 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 28 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Reducer 2 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 5 (CONTAINS) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_370] - Limit [LIM_369] (rows=100 width=108) + File Output Operator [FS_368] + Limit [LIM_367] (rows=59 width=115) Number of rows:100 - Select Operator [SEL_368] (rows=335408073 width=108) + Select Operator [SEL_366] (rows=59 width=115) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_367] - Group By Operator [GBY_366] (rows=335408073 width=108) + SHUFFLE [RS_365] + Group By Operator [GBY_364] (rows=59 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] - <-Reducer 10 [CONTAINS] vectorized - Reduce Output Operator [RS_382] + <-Reducer 11 [CONTAINS] vectorized + Reduce Output Operator [RS_388] PartitionCols:_col0 - Group By Operator [GBY_381] (rows=670816147 width=108) + Group By Operator [GBY_387] (rows=59 width=115) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_380] (rows=191657247 width=135) + Group By Operator [GBY_386] (rows=19 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_71] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_109] PartitionCols:_col0 - Group By Operator [GBY_70] (rows=383314495 width=135) + Group By Operator [GBY_108] (rows=19 width=115) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_303] (rows=383314495 width=135) - Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] + Merge Join Operator [MERGEJOIN_304] (rows=11364 width=3) + Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_66] + SHUFFLE [RS_104] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_293] (rows=508200 width=1436) + Merge Join Operator [MERGEJOIN_293] (rows=461514 width=7) Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_319] PartitionCols:_col1 - Select Operator [SEL_318] (rows=462000 width=1436) + Select Operator [SEL_318] (rows=460848 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_317] (rows=462000 width=1436) + Filter Operator [FIL_317] (rows=460848 width=7) predicate:(i_item_sk is not null and i_manufact_id is not null) - TableScan [TS_0] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"] - <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized + TableScan [TS_0] (rows=462000 width=7) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_manufact_id"] + <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_325] PartitionCols:_col0 - Group By Operator [GBY_324] (rows=115500 width=1436) + Group By Operator [GBY_324] (rows=692 width=3) Output:["_col0"],keys:KEY._col0 - <-Map 15 [SIMPLE_EDGE] vectorized + <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_322] (rows=231000 width=1436) + Group By Operator [GBY_322] (rows=692 width=3) Output:["_col0"],keys:i_manufact_id - Select Operator [SEL_321] (rows=231000 width=1436) + Select Operator [SEL_321] (rows=46085 width=93) Output:["i_manufact_id"] - Filter Operator [FIL_320] (rows=231000 width=1436) + Filter Operator [FIL_320] (rows=46085 width=93) predicate:((i_category = 'Books') and i_manufact_id is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_category","i_manufact_id"] + TableScan [TS_3] (rows=462000 width=93) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_category","i_manufact_id"] <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_67] - PartitionCols:_col4 - Select Operator [SEL_62] (rows=348467716 width=135) - Output:["_col4","_col5"] - Merge Join Operator [MERGEJOIN_298] (rows=348467716 width=135) - Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_346] - PartitionCols:_col0 - Select Operator [SEL_343] (rows=20000000 width=1014) - Output:["_col0"] - Filter Operator [FIL_342] (rows=20000000 width=1014) - predicate:((ca_gmt_offset = -6) and ca_address_sk is not null) - TableScan [TS_16] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"] - <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_59] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_297] (rows=316788826 width=135) - Conds:RS_379._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_330] - PartitionCols:_col0 - Select Operator [SEL_327] (rows=18262 width=1119) - Output:["_col0"] - Filter Operator [FIL_326] (rows=18262 width=1119) - predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_13] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_379] - PartitionCols:_col0 - Select Operator [SEL_378] (rows=287989836 width=135) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_377] (rows=287989836 width=135) - predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_66_item_i_item_sk_min) AND DynamicValue(RS_66_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_66_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_47] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_376] - Group By Operator [GBY_375] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_240] - Group By Operator [GBY_239] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_238] (rows=508200 width=1436) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_293] - <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_372] - Group By Operator [GBY_371] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_338] - Group By Operator [GBY_335] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_331] (rows=18262 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_327] - <-Reducer 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_374] - Group By Operator [GBY_373] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_354] - Group By Operator [GBY_351] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_347] (rows=20000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_343] - <-Reducer 13 [CONTAINS] vectorized - Reduce Output Operator [RS_394] - PartitionCols:_col0 - Group By Operator [GBY_393] (rows=670816147 width=108) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_392] (rows=95833781 width=135) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_109] - PartitionCols:_col0 - Group By Operator [GBY_108] (rows=191667562 width=135) - Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=191667562 width=135) - Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_104] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_293] - <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_105] PartitionCols:_col3 - Select Operator [SEL_100] (rows=174243235 width=135) + Select Operator [SEL_100] (rows=788222 width=110) Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_301] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_301] (rows=788222 width=110) Conds:RS_97._col2=RS_348._col0(Inner),Output:["_col1","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized + <-Map 25 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_348] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_343] - <-Reducer 25 [SIMPLE_EDGE] + Select Operator [SEL_343] (rows=8000000 width=116) + Output:["_col0"] + Filter Operator [FIL_342] (rows=8000000 width=112) + predicate:((ca_gmt_offset = -6) and ca_address_sk is not null) + TableScan [TS_16] (rows=40000000 width=112) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] + <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_300] (rows=158402938 width=135) - Conds:RS_391._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_300] (rows=3941109 width=118) + Conds:RS_385._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_332] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_327] - <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_391] + Select Operator [SEL_327] (rows=50 width=12) + Output:["_col0"] + Filter Operator [FIL_326] (rows=50 width=12) + predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) + TableScan [TS_13] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_385] PartitionCols:_col0 - Select Operator [SEL_390] (rows=144002668 width=135) + Select Operator [SEL_384] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_389] (rows=144002668 width=135) - predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_85] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_388] - Group By Operator [GBY_387] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_280] - Group By Operator [GBY_279] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_278] (rows=508200 width=1436) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_293] - <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_384] - Group By Operator [GBY_383] (rows=1 width=12) + Filter Operator [FIL_383] (rows=143931246 width=123) + predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_85] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] + <-Reducer 24 [BROADCAST_EDGE] vectorized + BROADCAST [RS_380] + Group By Operator [GBY_379] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_339] Group By Operator [GBY_336] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_333] (rows=18262 width=1119) + Select Operator [SEL_333] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_327] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_386] - Group By Operator [GBY_385] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized + <-Reducer 28 [BROADCAST_EDGE] vectorized + BROADCAST [RS_382] + Group By Operator [GBY_381] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_355] Group By Operator [GBY_352] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_349] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_349] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_343] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_365] + Reduce Output Operator [RS_363] PartitionCols:_col0 - Group By Operator [GBY_364] (rows=670816147 width=108) + Group By Operator [GBY_362] (rows=59 width=115) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_363] (rows=383325119 width=88) + Group By Operator [GBY_361] (rows=64 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Group By Operator [GBY_33] (rows=766650239 width=88) + Group By Operator [GBY_33] (rows=64 width=115) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_302] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_302] (rows=41476 width=3) Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_293] - <-Reducer 19 [SIMPLE_EDGE] + <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col3 - Select Operator [SEL_25] (rows=696954748 width=88) + Select Operator [SEL_25] (rows=2876890 width=4) Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_295] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_295] (rows=2876890 width=4) Conds:RS_22._col2=RS_344._col0(Inner),Output:["_col1","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized + <-Map 25 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_344] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_343] - <-Reducer 18 [SIMPLE_EDGE] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_294] (rows=633595212 width=88) - Conds:RS_362._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_294] (rows=14384447 width=4) + Conds:RS_360._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_328] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_327] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_362] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_360] PartitionCols:_col0 - Select Operator [SEL_361] (rows=575995635 width=88) + Select Operator [SEL_359] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_360] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_10] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 21 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_358] (rows=525327191 width=118) + predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_10] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] + <-Reducer 18 [BROADCAST_EDGE] vectorized BROADCAST [RS_341] Group By Operator [GBY_340] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_337] Group By Operator [GBY_334] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_329] (rows=18262 width=1119) + Select Operator [SEL_329] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_327] - <-Reducer 29 [BROADCAST_EDGE] vectorized + <-Reducer 26 [BROADCAST_EDGE] vectorized BROADCAST [RS_357] Group By Operator [GBY_356] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_353] Group By Operator [GBY_350] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_345] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_345] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_343] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_359] - Group By Operator [GBY_358] (rows=1 width=12) + <-Reducer 9 [CONTAINS] vectorized + Reduce Output Operator [RS_378] + PartitionCols:_col0 + Group By Operator [GBY_377] (rows=59 width=115) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 + Group By Operator [GBY_376] (rows=35 width=115) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_71] + PartitionCols:_col0 + Group By Operator [GBY_70] (rows=35 width=115) + Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 + Merge Join Operator [MERGEJOIN_303] (rows=22352 width=3) + Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_66] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_293] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_67] + PartitionCols:_col4 + Select Operator [SEL_62] (rows=1550375 width=13) + Output:["_col4","_col5"] + Merge Join Operator [MERGEJOIN_298] (rows=1550375 width=13) + Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"] + <-Map 25 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_346] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_343] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_59] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_297] (rows=7751872 width=98) + Conds:RS_375._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_330] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_327] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_375] + PartitionCols:_col0 + Select Operator [SEL_374] (rows=285117733 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_373] (rows=285117733 width=123) + predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_47] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_370] + Group By Operator [GBY_369] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_200] - Group By Operator [GBY_199] (rows=1 width=12) + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_338] + Group By Operator [GBY_335] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_198] (rows=508200 width=1436) + Select Operator [SEL_331] (rows=50 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_327] + <-Reducer 27 [BROADCAST_EDGE] vectorized + BROADCAST [RS_372] + Group By Operator [GBY_371] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_354] + Group By Operator [GBY_351] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_347] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_293] + Please refer to the previous Select Operator [SEL_343] diff --git a/ql/src/test/results/clientpositive/perf/tez/query34.q.out b/ql/src/test/results/clientpositive/perf/tez/query34.q.out index 7d140921d9..c6b64dfda0 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query34.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query34.q.out @@ -61,145 +61,133 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 5 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 4 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Map 4 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Map 10 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) -Reducer 7 <- Map 12 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Map 14 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 6 <- Map 11 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 13 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_141] - Select Operator [SEL_140] (rows=88000001 width=860) + File Output Operator [FS_136] + Select Operator [SEL_135] (rows=895995 width=364) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_35] - Select Operator [SEL_34] (rows=88000001 width=860) + Select Operator [SEL_34] (rows=895995 width=364) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_100] (rows=88000001 width=860) - Conds:RS_103._col0=RS_139._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] + Merge Join Operator [MERGEJOIN_100] (rows=895995 width=364) + Conds:RS_103._col0=RS_134._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_103] + SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_102] (rows=80000000 width=860) + Select Operator [SEL_102] (rows=80000000 width=356) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_101] (rows=80000000 width=860) + Filter Operator [FIL_101] (rows=80000000 width=356) predicate:c_customer_sk is not null - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag"] - <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_139] + TableScan [TS_0] (rows=80000000 width=356) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag"] + <-Reducer 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_134] PartitionCols:_col1 - Filter Operator [FIL_138] (rows=42591679 width=88) + Filter Operator [FIL_133] (rows=895995 width=12) predicate:_col2 BETWEEN 15 AND 20 - Select Operator [SEL_137] (rows=383325119 width=88) + Select Operator [SEL_132] (rows=8063963 width=12) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_136] (rows=383325119 width=88) + Group By Operator [GBY_131] (rows=8063963 width=12) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 8 [SIMPLE_EDGE] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1 - Group By Operator [GBY_25] (rows=766650239 width=88) + Group By Operator [GBY_25] (rows=8063963 width=12) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_99] (rows=766650239 width=88) - Conds:RS_21._col3=RS_125._col0(Inner),Output:["_col1","_col4"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] + Merge Join Operator [MERGEJOIN_99] (rows=8063963 width=4) + Conds:RS_21._col3=RS_122._col0(Inner),Output:["_col1","_col4"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] PartitionCols:_col0 - Select Operator [SEL_124] (rows=1704 width=1910) + Select Operator [SEL_121] (rows=112 width=102) Output:["_col0"] - Filter Operator [FIL_123] (rows=1704 width=1910) + Filter Operator [FIL_120] (rows=112 width=102) predicate:((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') and s_store_sk is not null) - TableScan [TS_12] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_county"] - <-Reducer 7 [SIMPLE_EDGE] + TableScan [TS_12] (rows=1704 width=102) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_county"] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_98] (rows=696954748 width=88) - Conds:RS_18._col2=RS_117._col0(Inner),Output:["_col1","_col3","_col4"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] + Merge Join Operator [MERGEJOIN_98] (rows=15200851 width=4) + Conds:RS_18._col2=RS_114._col0(Inner),Output:["_col1","_col3","_col4"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_116] (rows=1200 width=107) + Select Operator [SEL_113] (rows=480 width=104) Output:["_col0"] - Filter Operator [FIL_115] (rows=1200 width=107) + Filter Operator [FIL_112] (rows=480 width=104) predicate:((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (null) END and hd_demo_sk is not null) - TableScan [TS_9] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] - <-Reducer 6 [SIMPLE_EDGE] + TableScan [TS_9] (rows=7200 width=104) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_97] (rows=633595212 width=88) - Conds:RS_135._col0=RS_109._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_109] + Merge Join Operator [MERGEJOIN_97] (rows=228012750 width=14) + Conds:RS_130._col0=RS_106._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_108] (rows=16232 width=1119) + Select Operator [SEL_105] (rows=869 width=12) Output:["_col0"] - Filter Operator [FIL_107] (rows=16232 width=1119) + Filter Operator [FIL_104] (rows=869 width=12) predicate:((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (2000, 2001, 2002) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dom"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dom"] + <-Map 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_130] PartitionCols:_col0 - Select Operator [SEL_134] (rows=575995635 width=88) + Select Operator [SEL_129] (rows=479121995 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_133] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_31_customer_c_customer_sk_min) AND DynamicValue(RS_31_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_31_customer_c_customer_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_114] - Group By Operator [GBY_113] (rows=1 width=12) + Filter Operator [FIL_128] (rows=479121995 width=19) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_3] (rows=575995635 width=19) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_111] + Group By Operator [GBY_110] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] - Group By Operator [GBY_111] (rows=1 width=12) + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_109] + Group By Operator [GBY_108] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_110] (rows=16232 width=1119) + Select Operator [SEL_107] (rows=869 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_108] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_122] - Group By Operator [GBY_121] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_105] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_119] + Group By Operator [GBY_118] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] - Group By Operator [GBY_119] (rows=1 width=12) + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_117] + Group By Operator [GBY_116] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_118] (rows=1200 width=107) + Select Operator [SEL_115] (rows=480 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_116] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_130] - Group By Operator [GBY_129] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_113] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_127] + Group By Operator [GBY_126] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_128] - Group By Operator [GBY_127] (rows=1 width=12) + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] + Group By Operator [GBY_124] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_126] (rows=1704 width=1910) + Select Operator [SEL_123] (rows=112 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_124] - <-Reducer 4 [BROADCAST_EDGE] vectorized - BROADCAST [RS_132] - Group By Operator [GBY_131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_104] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] + Please refer to the previous Select Operator [SEL_121] diff --git a/ql/src/test/results/clientpositive/perf/tez/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/query35.q.out index 4ad92c2fed..db5518b885 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query35.q.out @@ -113,10 +113,11 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 10 <- Reducer 13 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Map 20 <- Reducer 16 (BROADCAST_EDGE) -Map 21 <- Reducer 19 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Map 20 <- Reducer 11 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE) +Map 21 <- Reducer 11 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE) +Map 9 <- Reducer 13 (BROADCAST_EDGE) +Reducer 10 <- Map 12 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 14 <- Map 12 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) Reducer 15 <- Reducer 14 (SIMPLE_EDGE) @@ -124,106 +125,68 @@ Reducer 16 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 17 <- Map 12 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) Reducer 18 <- Reducer 17 (SIMPLE_EDGE) Reducer 19 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 15 (ONE_TO_ONE_EDGE), Reducer 18 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 15 (ONE_TO_ONE_EDGE), Reducer 18 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_226] - Limit [LIM_225] (rows=100 width=88) + File Output Operator [FS_227] + Limit [LIM_226] (rows=1 width=352) Number of rows:100 - Select Operator [SEL_224] (rows=1045432122 width=88) + Select Operator [SEL_225] (rows=1 width=352) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_223] - Select Operator [SEL_222] (rows=1045432122 width=88) + SHUFFLE [RS_224] + Select Operator [SEL_223] (rows=1 width=352) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] - Group By Operator [GBY_221] (rows=1045432122 width=88) + Group By Operator [GBY_222] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","count(VALUE._col2)","max(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","max(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","max(VALUE._col9)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_62] (rows=2090864244 width=88) + Group By Operator [GBY_62] (rows=1 width=336) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count()","sum(_col8)","count(_col8)","max(_col8)","sum(_col9)","count(_col9)","max(_col9)","sum(_col10)","count(_col10)","max(_col10)"],keys:_col4, _col6, _col7, _col8, _col9, _col10 - Top N Key Operator [TNK_104] (rows=2090864244 width=88) + Top N Key Operator [TNK_104] (rows=161199 width=276) keys:_col4, _col6, _col7, _col8, _col9, _col10,sort order:++++++,top n:100 - Select Operator [SEL_61] (rows=2090864244 width=88) + Select Operator [SEL_61] (rows=161199 width=276) Output:["_col4","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_60] (rows=2090864244 width=88) + Filter Operator [FIL_60] (rows=161199 width=276) predicate:(_col12 is not null or _col14 is not null) - Merge Join Operator [MERGEJOIN_174] (rows=2090864244 width=88) - Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_212._col0(Left Outer),RS_55._col0=RS_220._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] - <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_55] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_170] (rows=96800003 width=860) - Conds:RS_50._col1=RS_183._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_183] - PartitionCols:_col0 - Select Operator [SEL_182] (rows=1861800 width=385) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_181] (rows=1861800 width=385) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_50] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_169] (rows=88000001 width=860) - Conds:RS_177._col2=RS_180._col0(Inner),Output:["_col0","_col1","_col4"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_177] - PartitionCols:_col2 - Select Operator [SEL_176] (rows=80000000 width=860) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_175] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_180] - PartitionCols:_col0 - Select Operator [SEL_179] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_178] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 11 [SIMPLE_EDGE] + Merge Join Operator [MERGEJOIN_174] (rows=161199 width=276) + Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_213._col0(Left Outer),RS_55._col0=RS_221._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0 - Group By Operator [GBY_54] (rows=633595212 width=88) + Group By Operator [GBY_54] (rows=168231 width=2) Output:["_col0"],keys:_col0 - Select Operator [SEL_18] (rows=633595212 width=88) + Select Operator [SEL_18] (rows=62428523 width=2) Output:["_col0"] - Merge Join Operator [MERGEJOIN_171] (rows=633595212 width=88) - Conds:RS_204._col0=RS_186._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_171] (rows=62428523 width=2) + Conds:RS_202._col0=RS_186._col0(Inner),Output:["_col1"] <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_186] PartitionCols:_col0 - Select Operator [SEL_185] (rows=12174 width=1119) + Select Operator [SEL_185] (rows=217 width=12) Output:["_col0"] - Filter Operator [FIL_184] (rows=12174 width=1119) + Filter Operator [FIL_184] (rows=217 width=12) predicate:((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_12] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_204] + TableScan [TS_12] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_202] PartitionCols:_col0 - Select Operator [SEL_203] (rows=575995635 width=88) + Select Operator [SEL_201] (rows=525327388 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_202] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_9] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] + Filter Operator [FIL_200] (rows=525327388 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_9] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_199] Group By Operator [GBY_198] (rows=1 width=12) @@ -232,94 +195,134 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_195] Group By Operator [GBY_192] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_187] (rows=12174 width=1119) + Select Operator [SEL_187] (rows=217 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_185] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_201] - Group By Operator [GBY_200] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=96800000)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_137] - Group By Operator [GBY_136] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"] - Select Operator [SEL_135] (rows=96800003 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_170] <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_212] + FORWARD [RS_213] PartitionCols:_col0 - Select Operator [SEL_211] (rows=79201469 width=135) + Select Operator [SEL_212] (rows=168231 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_210] (rows=79201469 width=135) + Group By Operator [GBY_211] (rows=168231 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Group By Operator [GBY_29] (rows=158402938 width=135) + Group By Operator [GBY_29] (rows=168231 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_172] (rows=158402938 width=135) - Conds:RS_209._col0=RS_188._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_172] (rows=17104380 width=3) + Conds:RS_210._col0=RS_188._col0(Inner),Output:["_col1"] <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_188] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_185] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_209] + SHUFFLE [RS_210] PartitionCols:_col0 - Select Operator [SEL_208] (rows=144002668 width=135) + Select Operator [SEL_209] (rows=143930993 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_207] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_19] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] - <-Reducer 16 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_208] (rows=143930993 width=7) + predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_56_store_sales_ss_customer_sk_min) AND DynamicValue(RS_56_store_sales_ss_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_56_store_sales_ss_customer_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_19] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_206] Group By Operator [GBY_205] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 10 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_117] + Group By Operator [GBY_116] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_115] (rows=168231 width=2) + Output:["_col0"] + Please refer to the previous Group By Operator [GBY_54] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_204] + Group By Operator [GBY_203] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_196] Group By Operator [GBY_193] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_189] (rows=12174 width=1119) + Select Operator [SEL_189] (rows=217 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_185] <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_220] + FORWARD [RS_221] PartitionCols:_col0 - Select Operator [SEL_219] (rows=158394413 width=135) + Select Operator [SEL_220] (rows=167041 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_218] (rows=158394413 width=135) + Group By Operator [GBY_219] (rows=167041 width=3) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 - Group By Operator [GBY_43] (rows=316788826 width=135) + Group By Operator [GBY_43] (rows=167041 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_173] (rows=316788826 width=135) - Conds:RS_217._col0=RS_190._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_173] (rows=33642830 width=3) + Conds:RS_218._col0=RS_190._col0(Inner),Output:["_col1"] <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_190] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_185] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_217] + SHUFFLE [RS_218] PartitionCols:_col0 - Select Operator [SEL_216] (rows=287989836 width=135) + Select Operator [SEL_217] (rows=285115246 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_215] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_33] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] + Filter Operator [FIL_216] (rows=285115246 width=7) + predicate:((cs_ship_customer_sk BETWEEN DynamicValue(RS_56_store_sales_ss_customer_sk_min) AND DynamicValue(RS_56_store_sales_ss_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_56_store_sales_ss_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_33] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_207] + Please refer to the previous Group By Operator [GBY_205] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_214] - Group By Operator [GBY_213] (rows=1 width=12) + BROADCAST [RS_215] + Group By Operator [GBY_214] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_197] Group By Operator [GBY_194] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_191] (rows=12174 width=1119) + Select Operator [SEL_191] (rows=217 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_185] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_55] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_170] (rows=78293105 width=272) + Conds:RS_50._col1=RS_183._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_183] + PartitionCols:_col0 + Select Operator [SEL_182] (rows=1861800 width=186) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_181] (rows=1861800 width=186) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=186) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_169] (rows=77201384 width=93) + Conds:RS_177._col2=RS_180._col0(Inner),Output:["_col0","_col1","_col4"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_177] + PartitionCols:_col2 + Select Operator [SEL_176] (rows=77201384 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_175] (rows=77201384 width=11) + predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=11) + default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_180] + PartitionCols:_col0 + Select Operator [SEL_179] (rows=40000000 width=90) + Output:["_col0","_col1"] + Filter Operator [FIL_178] (rows=40000000 width=90) + predicate:ca_address_sk is not null + TableScan [TS_3] (rows=40000000 width=90) + default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query36.q.out b/ql/src/test/results/clientpositive/perf/tez/query36.q.out index bc9a40ea5a..b65d9c4065 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query36.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query36.q.out @@ -59,9 +59,8 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) @@ -75,81 +74,81 @@ Stage-0 limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_119] - Limit [LIM_118] (rows=100 width=88) + File Output Operator [FS_114] + Limit [LIM_113] (rows=100 width=490) Number of rows:100 - Select Operator [SEL_117] (rows=1149975358 width=88) + Select Operator [SEL_112] (rows=3060 width=490) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_116] - Select Operator [SEL_115] (rows=1149975358 width=88) + SHUFFLE [RS_111] + Select Operator [SEL_110] (rows=3060 width=490) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - PTF Operator [PTF_114] (rows=1149975358 width=88) + PTF Operator [PTF_109] (rows=3060 width=414) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(_col2 / _col3) ASC NULLS FIRST","partition by:":"(grouping(_col4, 1) + grouping(_col4, 0)), CASE WHEN ((grouping(_col4, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END"}] - Select Operator [SEL_113] (rows=1149975358 width=88) + Select Operator [SEL_108] (rows=3060 width=414) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] + SHUFFLE [RS_107] PartitionCols:(grouping(_col4, 1) + grouping(_col4, 0)), CASE WHEN ((grouping(_col4, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END - Select Operator [SEL_111] (rows=1149975358 width=88) + Select Operator [SEL_106] (rows=3060 width=414) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_110] (rows=1149975358 width=88) + Group By Operator [GBY_105] (rows=3060 width=414) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_23] (rows=2299950717 width=88) + Group By Operator [GBY_23] (rows=85680 width=414) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col0, _col1, 0L - Select Operator [SEL_21] (rows=766650239 width=88) + Select Operator [SEL_21] (rows=30601888 width=232) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_82] (rows=766650239 width=88) - Conds:RS_18._col1=RS_101._col0(Inner),Output:["_col3","_col4","_col10","_col11"] + Merge Join Operator [MERGEJOIN_82] (rows=30601888 width=232) + Conds:RS_18._col1=RS_104._col0(Inner),Output:["_col3","_col4","_col10","_col11"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_101] + SHUFFLE [RS_104] PartitionCols:_col0 - Select Operator [SEL_100] (rows=462000 width=1436) + Select Operator [SEL_103] (rows=462000 width=186) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_99] (rows=462000 width=1436) + Filter Operator [FIL_102] (rows=462000 width=186) predicate:i_item_sk is not null - TableScan [TS_9] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_class","i_category"] + TableScan [TS_9] (rows=462000 width=186) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_class","i_category"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_81] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_81] (rows=30601888 width=54) Conds:RS_15._col2=RS_93._col0(Inner),Output:["_col1","_col3","_col4"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_93] PartitionCols:_col0 - Select Operator [SEL_92] (rows=1704 width=1910) + Select Operator [SEL_92] (rows=278 width=90) Output:["_col0"] - Filter Operator [FIL_91] (rows=1704 width=1910) + Filter Operator [FIL_91] (rows=278 width=90) predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') and s_store_sk is not null) - TableScan [TS_6] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] + TableScan [TS_6] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_80] (rows=633595212 width=88) - Conds:RS_109._col0=RS_85._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_80] (rows=187574154 width=203) + Conds:RS_101._col0=RS_85._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_85] PartitionCols:_col0 - Select Operator [SEL_84] (rows=36524 width=1119) + Select Operator [SEL_84] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_83] (rows=36524 width=1119) + Filter Operator [FIL_83] (rows=652 width=8) predicate:((d_year = 1999) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_109] + SHUFFLE [RS_101] PartitionCols:_col0 - Select Operator [SEL_108] (rows=575995635 width=88) + Select Operator [SEL_100] (rows=525329897 width=225) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_107] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_13_d1_d_date_sk_min) AND DynamicValue(RS_13_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_16_store_s_store_sk_min) AND DynamicValue(RS_16_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_16_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_ext_sales_price","ss_net_profit"] + Filter Operator [FIL_99] (rows=525329897 width=225) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_13_d1_d_date_sk_min) AND DynamicValue(RS_13_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_16_store_s_store_sk_min) AND DynamicValue(RS_16_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_16_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=225) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_ext_sales_price","ss_net_profit"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_98] Group By Operator [GBY_97] (rows=1 width=12) @@ -158,20 +157,9 @@ Stage-0 SHUFFLE [RS_96] Group By Operator [GBY_95] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_94] (rows=1704 width=1910) + Select Operator [SEL_94] (rows=278 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_92] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_104] - Group By Operator [GBY_103] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_102] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_100] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_90] Group By Operator [GBY_89] (rows=1 width=12) @@ -180,7 +168,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_88] Group By Operator [GBY_87] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_86] (rows=36524 width=1119) + Select Operator [SEL_86] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_84] diff --git a/ql/src/test/results/clientpositive/perf/tez/query37.q.out b/ql/src/test/results/clientpositive/perf/tez/query37.q.out index 6b5ce3e319..b716d3104a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query37.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query37.q.out @@ -47,64 +47,64 @@ Stage-0 Stage-1 Reducer 4 vectorized File Output Operator [FS_97] - Limit [LIM_96] (rows=100 width=135) + Limit [LIM_96] (rows=100 width=396) Number of rows:100 - Select Operator [SEL_95] (rows=316788826 width=135) + Select Operator [SEL_95] (rows=26286282 width=396) Output:["_col0","_col1","_col2"] <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_94] - Group By Operator [GBY_93] (rows=316788826 width=135) + Group By Operator [GBY_93] (rows=26286282 width=396) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_21] (rows=633577652 width=135) + Group By Operator [GBY_21] (rows=118943936 width=395) Output:["_col0","_col1","_col2"],keys:_col2, _col3, _col4 - Top N Key Operator [TNK_43] (rows=633577652 width=135) + Top N Key Operator [TNK_43] (rows=118943936 width=396) keys:_col2, _col3, _col4,sort order:+++,top n:100 - Merge Join Operator [MERGEJOIN_73] (rows=633577652 width=135) + Merge Join Operator [MERGEJOIN_73] (rows=118943936 width=396) Conds:RS_92._col0=RS_76._col0(Inner),RS_76._col0=RS_18._col1(Inner),Output:["_col2","_col3","_col4"] <-Map 5 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_76] PartitionCols:_col0 - Select Operator [SEL_75] (rows=51333 width=1436) + Select Operator [SEL_75] (rows=297 width=404) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_74] (rows=51333 width=1436) + Filter Operator [FIL_74] (rows=297 width=404) predicate:((i_manufact_id) IN (678, 964, 918, 849) and i_current_price BETWEEN 22 AND 52 and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_manufact_id"] + TableScan [TS_3] (rows=462000 width=403) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_manufact_id"] <-Reducer 8 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_72] (rows=4593600 width=15) + Merge Join Operator [MERGEJOIN_72] (rows=463969 width=4) Conds:RS_84._col0=RS_87._col0(Inner),Output:["_col1"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=8116 width=1119) + Select Operator [SEL_86] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_85] (rows=8116 width=1119) + Filter Operator [FIL_85] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-06-02 00:00:00' AND TIMESTAMP'2001-08-01 00:00:00' and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_9] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_84] PartitionCols:_col0 - Select Operator [SEL_83] (rows=4176000 width=15) + Select Operator [SEL_83] (rows=4176000 width=11) Output:["_col0","_col1"] - Filter Operator [FIL_82] (rows=4176000 width=15) + Filter Operator [FIL_82] (rows=4176000 width=11) predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) - TableScan [TS_6] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] + TableScan [TS_6] (rows=37584000 width=11) + default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_92] PartitionCols:_col0 - Select Operator [SEL_91] (rows=287989836 width=135) + Select Operator [SEL_91] (rows=287989836 width=4) Output:["_col0"] - Filter Operator [FIL_90] (rows=287989836 width=135) + Filter Operator [FIL_90] (rows=287989836 width=4) predicate:((cs_item_sk BETWEEN DynamicValue(RS_17_item_i_item_sk_min) AND DynamicValue(RS_17_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_17_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_18_inventory_inv_item_sk_min) AND DynamicValue(RS_18_inventory_inv_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_18_inventory_inv_item_sk_bloom_filter))) and cs_item_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_item_sk"] + TableScan [TS_0] (rows=287989836 width=4) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_item_sk"] <-Reducer 6 [BROADCAST_EDGE] vectorized BROADCAST [RS_81] Group By Operator [GBY_80] (rows=1 width=12) @@ -113,18 +113,18 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_79] Group By Operator [GBY_78] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_77] (rows=51333 width=1436) + Select Operator [SEL_77] (rows=297 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_75] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_89] Group By Operator [GBY_88] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4593600)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_51] Group By Operator [GBY_50] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4593600)"] - Select Operator [SEL_49] (rows=4593600 width=15) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_49] (rows=463969 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_72] diff --git a/ql/src/test/results/clientpositive/perf/tez/query38.q.out b/ql/src/test/results/clientpositive/perf/tez/query38.q.out index 78cb5e15cb..ddc81ed791 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query38.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query38.q.out @@ -45,20 +45,18 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 19 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Map 21 <- Reducer 13 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) -Map 22 <- Reducer 17 (BROADCAST_EDGE) -Reducer 10 <- Map 21 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) +Map 19 <- Reducer 13 (BROADCAST_EDGE) +Map 20 <- Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 11 <- Map 18 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 13 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 22 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 14 <- Map 20 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 15 <- Map 18 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) Reducer 16 <- Reducer 15 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 17 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 20 <- Map 18 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 18 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE) @@ -70,197 +68,175 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_244] - Limit [LIM_243] (rows=1 width=16) + File Output Operator [FS_236] + Limit [LIM_235] (rows=1 width=8) Number of rows:100 - Group By Operator [GBY_242] (rows=1 width=16) + Group By Operator [GBY_234] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_241] - Group By Operator [GBY_240] (rows=1 width=16) + PARTITION_ONLY_SHUFFLE [RS_233] + Group By Operator [GBY_232] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_239] (rows=1 width=108) - Filter Operator [FIL_238] (rows=1 width=108) + Select Operator [SEL_231] (rows=1 width=8) + Filter Operator [FIL_230] (rows=1 width=8) predicate:(_col3 = 3L) - Select Operator [SEL_237] (rows=152458212 width=108) + Select Operator [SEL_229] (rows=106034544 width=8) Output:["_col3"] - Group By Operator [GBY_236] (rows=152458212 width=108) + Group By Operator [GBY_228] (rows=106034544 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 5 [SIMPLE_EDGE] <-Reducer 12 [CONTAINS] vectorized - Reduce Output Operator [RS_256] + Reduce Output Operator [RS_246] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_255] (rows=304916424 width=108) + Group By Operator [GBY_245] (rows=106034544 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_254] (rows=87116929 width=135) + Group By Operator [GBY_244] (rows=31677591 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_253] (rows=174233858 width=135) + Select Operator [SEL_243] (rows=31677591 width=274) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_252] (rows=174233858 width=135) + Group By Operator [GBY_242] (rows=31677591 width=274) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_41] (rows=348467716 width=135) + Group By Operator [GBY_41] (rows=31677591 width=274) Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_178] (rows=348467716 width=135) - Conds:RS_37._col1=RS_219._col0(Inner),Output:["_col3","_col6","_col7"] + Merge Join Operator [MERGEJOIN_178] (rows=31677591 width=274) + Conds:RS_37._col1=RS_221._col0(Inner),Output:["_col3","_col6","_col7"] <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_219] + SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_216] (rows=80000000 width=860) + Select Operator [SEL_219] (rows=80000000 width=184) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_215] (rows=80000000 width=860) + Filter Operator [FIL_218] (rows=80000000 width=184) predicate:c_customer_sk is not null - TableScan [TS_6] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name"] + TableScan [TS_6] (rows=80000000 width=184) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_177] (rows=316788826 width=135) - Conds:RS_251._col0=RS_203._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_177] (rows=31677591 width=97) + Conds:RS_241._col0=RS_203._col0(Inner),Output:["_col1","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_203] PartitionCols:_col0 - Select Operator [SEL_200] (rows=8116 width=1119) + Select Operator [SEL_200] (rows=8116 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_199] (rows=8116 width=1119) + Filter Operator [FIL_199] (rows=8116 width=102) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_month_seq"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_251] + TableScan [TS_3] (rows=73049 width=102) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_month_seq"] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_241] PartitionCols:_col0 - Select Operator [SEL_250] (rows=287989836 width=135) + Select Operator [SEL_240] (rows=285117831 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_249] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_38_customer_c_customer_sk_min) AND DynamicValue(RS_38_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_38_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_25] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] + Filter Operator [FIL_239] (rows=285117831 width=7) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_25] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_246] - Group By Operator [GBY_245] (rows=1 width=12) + BROADCAST [RS_238] + Group By Operator [GBY_237] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_211] Group By Operator [GBY_208] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_204] (rows=8116 width=1119) + Select Operator [SEL_204] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_200] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_248] - Group By Operator [GBY_247] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_225] - Group By Operator [GBY_223] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_220] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_216] <-Reducer 16 [CONTAINS] vectorized - Reduce Output Operator [RS_266] + Reduce Output Operator [RS_256] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_265] (rows=304916424 width=108) + Group By Operator [GBY_255] (rows=106034544 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_264] (rows=43560808 width=135) + Group By Operator [GBY_254] (rows=15991238 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_263] (rows=87121617 width=135) + Select Operator [SEL_253] (rows=15991238 width=274) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_262] (rows=87121617 width=135) + Group By Operator [GBY_252] (rows=15991238 width=274) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_68] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_67] (rows=174243235 width=135) + Group By Operator [GBY_67] (rows=15991238 width=274) Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_180] (rows=174243235 width=135) - Conds:RS_63._col1=RS_221._col0(Inner),Output:["_col3","_col6","_col7"] + Merge Join Operator [MERGEJOIN_180] (rows=15991238 width=274) + Conds:RS_63._col1=RS_222._col0(Inner),Output:["_col3","_col6","_col7"] <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_221] + SHUFFLE [RS_222] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_216] + Please refer to the previous Select Operator [SEL_219] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_179] (rows=158402938 width=135) - Conds:RS_261._col0=RS_205._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_179] (rows=15991238 width=97) + Conds:RS_251._col0=RS_205._col0(Inner),Output:["_col1","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_205] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_200] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_261] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_251] PartitionCols:_col0 - Select Operator [SEL_260] (rows=144002668 width=135) + Select Operator [SEL_250] (rows=143930993 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_259] (rows=144002668 width=135) + Filter Operator [FIL_249] (rows=143930993 width=7) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_61_date_dim_d_date_sk_min) AND DynamicValue(RS_61_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_61_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_51] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + TableScan [TS_51] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_258] - Group By Operator [GBY_257] (rows=1 width=12) + BROADCAST [RS_248] + Group By Operator [GBY_247] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_212] Group By Operator [GBY_209] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_206] (rows=8116 width=1119) + Select Operator [SEL_206] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_200] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_235] + Reduce Output Operator [RS_227] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_234] (rows=304916424 width=108) + Group By Operator [GBY_226] (rows=106034544 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_233] (rows=174238687 width=88) + Group By Operator [GBY_225] (rows=58365715 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_232] (rows=348477374 width=88) + Select Operator [SEL_224] (rows=58365715 width=274) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_231] (rows=348477374 width=88) + Group By Operator [GBY_223] (rows=58365715 width=274) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=58365715 width=274) Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_176] (rows=696954748 width=88) - Conds:RS_12._col1=RS_217._col0(Inner),Output:["_col3","_col6","_col7"] + Merge Join Operator [MERGEJOIN_176] (rows=58365715 width=274) + Conds:RS_12._col1=RS_220._col0(Inner),Output:["_col3","_col6","_col7"] <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_217] + SHUFFLE [RS_220] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_216] + Please refer to the previous Select Operator [SEL_219] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_175] (rows=633595212 width=88) - Conds:RS_230._col0=RS_201._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_175] (rows=58365715 width=96) + Conds:RS_217._col0=RS_201._col0(Inner),Output:["_col1","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_201] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_200] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_230] + SHUFFLE [RS_217] PartitionCols:_col0 - Select Operator [SEL_229] (rows=575995635 width=88) + Select Operator [SEL_216] (rows=525327388 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_228] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_13_customer_c_customer_sk_min) AND DynamicValue(RS_13_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_13_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_227] - Group By Operator [GBY_226] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_224] - Group By Operator [GBY_222] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_218] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_216] + Filter Operator [FIL_215] (rows=525327388 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_0] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_214] Group By Operator [GBY_213] (rows=1 width=12) @@ -269,7 +245,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_210] Group By Operator [GBY_207] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_202] (rows=8116 width=1119) + Select Operator [SEL_202] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_200] diff --git a/ql/src/test/results/clientpositive/perf/tez/query39.q.out b/ql/src/test/results/clientpositive/perf/tez/query39.q.out index 3677fbae3c..a26f0330f4 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query39.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query39.q.out @@ -70,59 +70,59 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_232] - Select Operator [SEL_231] (rows=13756683 width=15) + Select Operator [SEL_231] (rows=189509 width=56) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_60] - Merge Join Operator [MERGEJOIN_202] (rows=13756683 width=15) + Merge Join Operator [MERGEJOIN_202] (rows=189509 width=48) Conds:RS_225._col0, _col1=RS_230._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_230] PartitionCols:_col0, _col1 - Select Operator [SEL_229] (rows=12506076 width=15) + Select Operator [SEL_229] (rows=18049 width=24) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_228] (rows=12506076 width=15) + Filter Operator [FIL_228] (rows=18049 width=40) predicate:CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (false) ELSE (((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4)) > 1.0D)) END - Select Operator [SEL_227] (rows=25012152 width=15) + Select Operator [SEL_227] (rows=36099 width=40) Output:["_col0","_col1","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_226] (rows=25012152 width=15) + Group By Operator [GBY_226] (rows=36099 width=140) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_51] (rows=50024305 width=15) + Group By Operator [GBY_51] (rows=36099 width=140) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)","count(_col3)","sum(_col5)","sum(_col4)"],keys:_col1, _col2, _col0 - Select Operator [SEL_49] (rows=50024305 width=15) + Select Operator [SEL_49] (rows=1032514 width=108) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_201] (rows=50024305 width=15) + Merge Join Operator [MERGEJOIN_201] (rows=1032514 width=108) Conds:RS_46._col2=RS_220._col0(Inner),Output:["_col3","_col7","_col8","_col9"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_220] PartitionCols:_col0 - Select Operator [SEL_218] (rows=27 width=1029) + Select Operator [SEL_218] (rows=27 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_217] (rows=27 width=1029) + Filter Operator [FIL_217] (rows=27 width=104) predicate:w_warehouse_sk is not null - TableScan [TS_9] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"] + TableScan [TS_9] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_46] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_200] (rows=45476640 width=15) + Merge Join Operator [MERGEJOIN_200] (rows=1032514 width=8) Conds:RS_43._col1=RS_216._col0(Inner),Output:["_col2","_col3","_col7"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_216] PartitionCols:_col0 - Select Operator [SEL_214] (rows=462000 width=1436) + Select Operator [SEL_214] (rows=462000 width=4) Output:["_col0"] - Filter Operator [FIL_213] (rows=462000 width=1436) + Filter Operator [FIL_213] (rows=462000 width=4) predicate:i_item_sk is not null - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk"] + TableScan [TS_6] (rows=462000 width=4) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_199] (rows=41342400 width=15) + Merge Join Operator [MERGEJOIN_199] (rows=1032514 width=8) Conds:RS_206._col0=RS_212._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_206] @@ -132,35 +132,35 @@ Stage-0 Filter Operator [FIL_203] (rows=37584000 width=15) predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) TableScan [TS_0] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] + default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_212] PartitionCols:_col0 - Select Operator [SEL_210] (rows=18262 width=1119) + Select Operator [SEL_210] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_208] (rows=18262 width=1119) + Filter Operator [FIL_208] (rows=50 width=12) predicate:((d_moy = 5) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_225] PartitionCols:_col0, _col1 - Select Operator [SEL_224] (rows=12506076 width=15) + Select Operator [SEL_224] (rows=18049 width=24) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_223] (rows=12506076 width=15) + Filter Operator [FIL_223] (rows=18049 width=40) predicate:CASE WHEN (((UDFToDouble(_col3) / _col4) = 0)) THEN (false) ELSE (((power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) / (UDFToDouble(_col3) / _col4)) > 1.0D)) END - Select Operator [SEL_222] (rows=25012152 width=15) + Select Operator [SEL_222] (rows=36099 width=40) Output:["_col0","_col1","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_221] (rows=25012152 width=15) + Group By Operator [GBY_221] (rows=36099 width=140) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_23] (rows=50024305 width=15) + Group By Operator [GBY_23] (rows=36099 width=140) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)","count(_col3)","sum(_col5)","sum(_col4)"],keys:_col1, _col2, _col0 - Select Operator [SEL_21] (rows=50024305 width=15) + Select Operator [SEL_21] (rows=1032514 width=108) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_198] (rows=50024305 width=15) + Merge Join Operator [MERGEJOIN_198] (rows=1032514 width=108) Conds:RS_18._col2=RS_219._col0(Inner),Output:["_col3","_col7","_col8","_col9"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_219] @@ -169,7 +169,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_197] (rows=45476640 width=15) + Merge Join Operator [MERGEJOIN_197] (rows=1032514 width=8) Conds:RS_15._col1=RS_215._col0(Inner),Output:["_col2","_col3","_col7"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_215] @@ -178,7 +178,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_196] (rows=41342400 width=15) + Merge Join Operator [MERGEJOIN_196] (rows=1032514 width=8) Conds:RS_205._col0=RS_211._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_205] @@ -187,9 +187,9 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_211] PartitionCols:_col0 - Select Operator [SEL_209] (rows=18262 width=1119) + Select Operator [SEL_209] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_207] (rows=18262 width=1119) + Filter Operator [FIL_207] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] diff --git a/ql/src/test/results/clientpositive/perf/tez/query4.q.out b/ql/src/test/results/clientpositive/perf/tez/query4.q.out index 3f663cdfeb..2c98d49fdb 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query4.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query4.q.out @@ -218,11 +218,11 @@ Plan optimized by CBO. Vertex dependency in root stage Map 1 <- Reducer 30 (BROADCAST_EDGE) -Map 11 <- Reducer 32 (BROADCAST_EDGE), Reducer 38 (BROADCAST_EDGE) +Map 11 <- Reducer 32 (BROADCAST_EDGE) Map 15 <- Reducer 33 (BROADCAST_EDGE) -Map 19 <- Reducer 29 (BROADCAST_EDGE), Reducer 36 (BROADCAST_EDGE) -Map 23 <- Reducer 28 (BROADCAST_EDGE), Reducer 35 (BROADCAST_EDGE) -Map 7 <- Reducer 31 (BROADCAST_EDGE), Reducer 37 (BROADCAST_EDGE) +Map 19 <- Reducer 29 (BROADCAST_EDGE) +Map 23 <- Reducer 28 (BROADCAST_EDGE) +Map 7 <- Reducer 31 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE) Reducer 13 <- Map 34 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) @@ -244,10 +244,6 @@ Reducer 30 <- Map 27 (CUSTOM_SIMPLE_EDGE) Reducer 31 <- Map 27 (CUSTOM_SIMPLE_EDGE) Reducer 32 <- Map 27 (CUSTOM_SIMPLE_EDGE) Reducer 33 <- Map 27 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Map 34 (CUSTOM_SIMPLE_EDGE) -Reducer 36 <- Map 34 (CUSTOM_SIMPLE_EDGE) -Reducer 37 <- Map 34 (CUSTOM_SIMPLE_EDGE) -Reducer 38 <- Map 34 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 10 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) @@ -259,297 +255,264 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_587] - Limit [LIM_586] (rows=100 width=88) + File Output Operator [FS_567] + Limit [LIM_566] (rows=100 width=85) Number of rows:100 - Select Operator [SEL_585] (rows=479156399 width=88) + Select Operator [SEL_565] (rows=46893314 width=85) Output:["_col0"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_139] - Select Operator [SEL_138] (rows=479156399 width=88) + Select Operator [SEL_138] (rows=46893314 width=85) Output:["_col0"] - Filter Operator [FIL_136] (rows=479156399 width=88) + Filter Operator [FIL_136] (rows=46893314 width=757) predicate:(CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > (_col12 / _col3))) ELSE ((null > (_col12 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > null)) ELSE (null) END) END and CASE WHEN (_col7 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > (_col1 / _col7))) ELSE ((null > (_col1 / _col7))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col9 / _col5) > null)) ELSE (null) END) END) - Merge Join Operator [MERGEJOIN_470] (rows=1916625598 width=88) - Conds:RS_530._col0=RS_542._col0(Inner),RS_542._col0=RS_554._col0(Inner),RS_542._col0=RS_564._col0(Inner),RS_542._col0=RS_574._col0(Inner),RS_542._col0=RS_584._col0(Inner),Output:["_col1","_col3","_col5","_col7","_col9","_col11","_col12"] + Merge Join Operator [MERGEJOIN_470] (rows=187573258 width=757) + Conds:RS_518._col0=RS_528._col0(Inner),RS_528._col0=RS_538._col0(Inner),RS_528._col0=RS_548._col0(Inner),RS_528._col0=RS_556._col0(Inner),RS_528._col0=RS_564._col0(Inner),Output:["_col1","_col3","_col5","_col7","_col9","_col11","_col12"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_542] + SHUFFLE [RS_528] PartitionCols:_col0 - Select Operator [SEL_541] (rows=116159124 width=88) + Select Operator [SEL_527] (rows=62524419 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_540] (rows=116159124 width=88) + Filter Operator [FIL_526] (rows=62524419 width=212) predicate:(_col7 > 0) - Select Operator [SEL_539] (rows=348477374 width=88) + Select Operator [SEL_525] (rows=187573258 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_538] (rows=348477374 width=88) + Group By Operator [GBY_524] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_38] (rows=696954748 width=88) + Group By Operator [GBY_38] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_36] (rows=696954748 width=88) + Select Operator [SEL_36] (rows=187573258 width=1043) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_461] (rows=696954748 width=88) - Conds:RS_33._col1=RS_515._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_461] (rows=187573258 width=1043) + Conds:RS_33._col1=RS_513._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_515] + SHUFFLE [RS_513] PartitionCols:_col0 - Select Operator [SEL_509] (rows=80000000 width=860) + Select Operator [SEL_509] (rows=80000000 width=656) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_508] (rows=80000000 width=860) + Filter Operator [FIL_508] (rows=80000000 width=656) predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_114] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] + TableScan [TS_114] (rows=80000000 width=656) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_460] (rows=633595212 width=88) - Conds:RS_537._col0=RS_485._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_460] (rows=187573258 width=395) + Conds:RS_523._col0=RS_485._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_485] PartitionCols:_col0 - Select Operator [SEL_476] (rows=36524 width=1119) + Select Operator [SEL_476] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_472] (rows=36524 width=1119) + Filter Operator [FIL_472] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) - TableScan [TS_111] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_111] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_537] + SHUFFLE [RS_523] PartitionCols:_col0 - Select Operator [SEL_536] (rows=575995635 width=88) + Select Operator [SEL_522] (rows=525327388 width=435) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_535] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_34_customer_c_customer_sk_min) AND DynamicValue(RS_34_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_34_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_21] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] + Filter Operator [FIL_521] (rows=525327388 width=435) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_21] (rows=575995635 width=435) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_532] - Group By Operator [GBY_531] (rows=1 width=12) + BROADCAST [RS_520] + Group By Operator [GBY_519] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_500] Group By Operator [GBY_494] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_486] (rows=36524 width=1119) + Select Operator [SEL_486] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_476] - <-Reducer 37 [BROADCAST_EDGE] vectorized - BROADCAST [RS_534] - Group By Operator [GBY_533] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_526] - Group By Operator [GBY_522] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_516] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_509] <-Reducer 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_554] + SHUFFLE [RS_538] PartitionCols:_col0 - Select Operator [SEL_553] (rows=58077952 width=135) + Select Operator [SEL_537] (rows=33694814 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_552] (rows=58077952 width=135) + Filter Operator [FIL_536] (rows=33694814 width=212) predicate:(_col7 > 0) - Select Operator [SEL_551] (rows=174233858 width=135) + Select Operator [SEL_535] (rows=101084444 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_550] (rows=174233858 width=135) + Group By Operator [GBY_534] (rows=101084444 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_61] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_60] (rows=348467716 width=135) + Group By Operator [GBY_60] (rows=101084444 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_58] (rows=348467716 width=135) + Select Operator [SEL_58] (rows=101084444 width=1093) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_463] (rows=348467716 width=135) - Conds:RS_55._col1=RS_517._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_463] (rows=101084444 width=1093) + Conds:RS_55._col1=RS_514._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_517] + SHUFFLE [RS_514] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_509] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_462] (rows=316788826 width=135) - Conds:RS_549._col0=RS_487._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_462] (rows=101084444 width=445) + Conds:RS_533._col0=RS_487._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_487] PartitionCols:_col0 - Select Operator [SEL_477] (rows=36524 width=1119) + Select Operator [SEL_477] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_473] (rows=36524 width=1119) + Filter Operator [FIL_473] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) Please refer to the previous TableScan [TS_111] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_549] + SHUFFLE [RS_533] PartitionCols:_col0 - Select Operator [SEL_548] (rows=287989836 width=135) + Select Operator [SEL_532] (rows=285117831 width=453) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_547] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_56_customer_c_customer_sk_min) AND DynamicValue(RS_56_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_56_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_53_date_dim_d_date_sk_min) AND DynamicValue(RS_53_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_53_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_43] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] + Filter Operator [FIL_531] (rows=285117831 width=453) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_53_date_dim_d_date_sk_min) AND DynamicValue(RS_53_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_53_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_43] (rows=287989836 width=453) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] <-Reducer 32 [BROADCAST_EDGE] vectorized - BROADCAST [RS_544] - Group By Operator [GBY_543] (rows=1 width=12) + BROADCAST [RS_530] + Group By Operator [GBY_529] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_501] Group By Operator [GBY_495] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_488] (rows=36524 width=1119) + Select Operator [SEL_488] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_477] - <-Reducer 38 [BROADCAST_EDGE] vectorized - BROADCAST [RS_546] - Group By Operator [GBY_545] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_527] - Group By Operator [GBY_523] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_518] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_509] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_564] + SHUFFLE [RS_548] PartitionCols:_col0 - Select Operator [SEL_563] (rows=29040539 width=135) + Select Operator [SEL_547] (rows=17130654 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_562] (rows=29040539 width=135) + Filter Operator [FIL_546] (rows=17130654 width=212) predicate:(_col7 > 0) - Select Operator [SEL_561] (rows=87121617 width=135) + Select Operator [SEL_545] (rows=51391963 width=212) Output:["_col0","_col7"] - Group By Operator [GBY_560] (rows=87121617 width=135) + Group By Operator [GBY_544] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_83] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_82] (rows=174243235 width=135) + Group By Operator [GBY_82] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_80] (rows=174243235 width=135) + Select Operator [SEL_80] (rows=51391963 width=1099) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_465] (rows=174243235 width=135) - Conds:RS_77._col1=RS_519._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_465] (rows=51391963 width=1099) + Conds:RS_77._col1=RS_515._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_519] + SHUFFLE [RS_515] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_509] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_464] (rows=158402938 width=135) - Conds:RS_559._col0=RS_489._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_464] (rows=51391963 width=451) + Conds:RS_543._col0=RS_489._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_489] PartitionCols:_col0 - Select Operator [SEL_478] (rows=36524 width=1119) + Select Operator [SEL_478] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_474] (rows=36524 width=1119) + Filter Operator [FIL_474] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) Please refer to the previous TableScan [TS_111] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_559] + SHUFFLE [RS_543] PartitionCols:_col0 - Select Operator [SEL_558] (rows=144002668 width=135) + Select Operator [SEL_542] (rows=143930993 width=455) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_557] (rows=144002668 width=135) + Filter Operator [FIL_541] (rows=143930993 width=455) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_75_date_dim_d_date_sk_min) AND DynamicValue(RS_75_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_75_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_65] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] + TableScan [TS_65] (rows=144002668 width=455) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_556] - Group By Operator [GBY_555] (rows=1 width=12) + BROADCAST [RS_540] + Group By Operator [GBY_539] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_502] Group By Operator [GBY_496] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_490] (rows=36524 width=1119) + Select Operator [SEL_490] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_478] <-Reducer 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_574] + SHUFFLE [RS_556] PartitionCols:_col0 - Select Operator [SEL_573] (rows=174233858 width=135) + Select Operator [SEL_555] (rows=101084444 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_572] (rows=174233858 width=135) + Group By Operator [GBY_554] (rows=101084444 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_105] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_104] (rows=348467716 width=135) + Group By Operator [GBY_104] (rows=101084444 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_102] (rows=348467716 width=135) + Select Operator [SEL_102] (rows=101084444 width=1093) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_467] (rows=348467716 width=135) - Conds:RS_99._col1=RS_512._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_467] (rows=101084444 width=1093) + Conds:RS_99._col1=RS_511._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_512] + SHUFFLE [RS_511] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_509] <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_99] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_466] (rows=316788826 width=135) - Conds:RS_571._col0=RS_481._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_466] (rows=101084444 width=445) + Conds:RS_553._col0=RS_481._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_481] PartitionCols:_col0 - Select Operator [SEL_475] (rows=36524 width=1119) + Select Operator [SEL_475] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_471] (rows=36524 width=1119) + Filter Operator [FIL_471] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_111] <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_571] + SHUFFLE [RS_553] PartitionCols:_col0 - Select Operator [SEL_570] (rows=287989836 width=135) + Select Operator [SEL_552] (rows=285117831 width=453) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_569] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_100_customer_c_customer_sk_min) AND DynamicValue(RS_100_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_100_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_97_date_dim_d_date_sk_min) AND DynamicValue(RS_97_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_97_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_87] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] + Filter Operator [FIL_551] (rows=285117831 width=453) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_97_date_dim_d_date_sk_min) AND DynamicValue(RS_97_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_97_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_87] (rows=287989836 width=453) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_ext_discount_amt","cs_ext_sales_price","cs_ext_wholesale_cost","cs_ext_list_price"] <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_566] - Group By Operator [GBY_565] (rows=1 width=12) + BROADCAST [RS_550] + Group By Operator [GBY_549] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_498] Group By Operator [GBY_492] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_482] (rows=36524 width=1119) + Select Operator [SEL_482] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_475] - <-Reducer 36 [BROADCAST_EDGE] vectorized - BROADCAST [RS_568] - Group By Operator [GBY_567] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_525] - Group By Operator [GBY_521] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_513] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_509] <-Reducer 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_584] + SHUFFLE [RS_564] PartitionCols:_col0 - Select Operator [SEL_583] (rows=348477374 width=88) + Select Operator [SEL_563] (rows=187573258 width=297) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_582] (rows=348477374 width=88) + Group By Operator [GBY_562] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_126] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_125] (rows=696954748 width=88) + Group By Operator [GBY_125] (rows=187573258 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_123] (rows=696954748 width=88) + Select Operator [SEL_123] (rows=187573258 width=1043) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_469] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_469] (rows=187573258 width=1043) Conds:RS_120._col1=RS_510._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 34 [SIMPLE_EDGE] vectorized SHUFFLE [RS_510] @@ -558,67 +521,56 @@ Stage-0 <-Reducer 24 [SIMPLE_EDGE] SHUFFLE [RS_120] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_468] (rows=633595212 width=88) - Conds:RS_581._col0=RS_479._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_468] (rows=187573258 width=395) + Conds:RS_561._col0=RS_479._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_479] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_475] <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_581] + SHUFFLE [RS_561] PartitionCols:_col0 - Select Operator [SEL_580] (rows=575995635 width=88) + Select Operator [SEL_560] (rows=525327388 width=435) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_579] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_121_customer_c_customer_sk_min) AND DynamicValue(RS_121_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_121_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_118_date_dim_d_date_sk_min) AND DynamicValue(RS_118_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_118_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_108] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] + Filter Operator [FIL_559] (rows=525327388 width=435) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_118_date_dim_d_date_sk_min) AND DynamicValue(RS_118_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_118_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_108] (rows=575995635 width=435) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_sales_price","ss_ext_wholesale_cost","ss_ext_list_price"] <-Reducer 28 [BROADCAST_EDGE] vectorized - BROADCAST [RS_576] - Group By Operator [GBY_575] (rows=1 width=12) + BROADCAST [RS_558] + Group By Operator [GBY_557] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_497] Group By Operator [GBY_491] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_480] (rows=36524 width=1119) + Select Operator [SEL_480] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_475] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_578] - Group By Operator [GBY_577] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_524] - Group By Operator [GBY_520] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_511] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_509] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_530] + SHUFFLE [RS_518] PartitionCols:_col0 - Select Operator [SEL_529] (rows=87121617 width=135) + Select Operator [SEL_517] (rows=51391963 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_528] (rows=87121617 width=135) + Group By Operator [GBY_516] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Group By Operator [GBY_17] (rows=174243235 width=135) + Group By Operator [GBY_17] (rows=51391963 width=764) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Operator [SEL_15] (rows=174243235 width=135) + Select Operator [SEL_15] (rows=51391963 width=1099) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_459] (rows=174243235 width=135) - Conds:RS_12._col1=RS_514._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Merge Join Operator [MERGEJOIN_459] (rows=51391963 width=1099) + Conds:RS_12._col1=RS_512._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_514] + SHUFFLE [RS_512] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_509] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_458] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_458] (rows=51391963 width=451) Conds:RS_507._col0=RS_483._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_483] @@ -627,12 +579,12 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_507] PartitionCols:_col0 - Select Operator [SEL_506] (rows=144002668 width=135) + Select Operator [SEL_506] (rows=143930993 width=455) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_505] (rows=144002668 width=135) + Filter Operator [FIL_505] (rows=143930993 width=455) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] + TableScan [TS_0] (rows=144002668 width=455) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_sales_price","ws_ext_wholesale_cost","ws_ext_list_price"] <-Reducer 30 [BROADCAST_EDGE] vectorized BROADCAST [RS_504] Group By Operator [GBY_503] (rows=1 width=12) @@ -641,7 +593,7 @@ Stage-0 SHUFFLE [RS_499] Group By Operator [GBY_493] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_484] (rows=36524 width=1119) + Select Operator [SEL_484] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_475] diff --git a/ql/src/test/results/clientpositive/perf/tez/query40.q.out b/ql/src/test/results/clientpositive/perf/tez/query40.q.out index a3b6c03801..4c8e4bd77b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query40.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query40.q.out @@ -55,10 +55,9 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) @@ -71,77 +70,77 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_136] - Limit [LIM_135] (rows=100 width=135) + File Output Operator [FS_131] + Limit [LIM_130] (rows=100 width=410) Number of rows:100 - Select Operator [SEL_134] (rows=210822976 width=135) + Select Operator [SEL_129] (rows=769995 width=410) Output:["_col0","_col1","_col2","_col3"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_133] - Group By Operator [GBY_132] (rows=210822976 width=135) + SHUFFLE [RS_128] + Group By Operator [GBY_127] (rows=769995 width=410) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col1 - Group By Operator [GBY_29] (rows=421645953 width=135) + Group By Operator [GBY_29] (rows=3519685 width=410) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col0, _col1 - Top N Key Operator [TNK_55] (rows=421645953 width=135) + Top N Key Operator [TNK_55] (rows=3519685 width=346) keys:_col0, _col1,sort order:++,top n:100 - Select Operator [SEL_27] (rows=421645953 width=135) + Select Operator [SEL_27] (rows=3519685 width=346) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_101] (rows=421645953 width=135) - Conds:RS_24._col1=RS_120._col0(Inner),Output:["_col4","_col7","_col9","_col11","_col14"] + Merge Join Operator [MERGEJOIN_101] (rows=3519685 width=346) + Conds:RS_24._col1=RS_126._col0(Inner),Output:["_col4","_col7","_col9","_col11","_col14"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] + SHUFFLE [RS_126] PartitionCols:_col0 - Select Operator [SEL_119] (rows=27 width=1029) + Select Operator [SEL_125] (rows=27 width=90) Output:["_col0","_col1"] - Filter Operator [FIL_118] (rows=27 width=1029) + Filter Operator [FIL_124] (rows=27 width=90) predicate:w_warehouse_sk is not null - TableScan [TS_12] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_state"] + TableScan [TS_12] (rows=27 width=90) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_state"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_100] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_100] (rows=3519685 width=263) Conds:RS_21._col2=RS_112._col0(Inner),Output:["_col1","_col4","_col7","_col9","_col11"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_112] PartitionCols:_col0 - Select Operator [SEL_111] (rows=51333 width=1436) + Select Operator [SEL_111] (rows=51333 width=215) Output:["_col0","_col1"] - Filter Operator [FIL_110] (rows=51333 width=1436) + Filter Operator [FIL_110] (rows=51333 width=215) predicate:(i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) - TableScan [TS_9] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_current_price"] + TableScan [TS_9] (rows=462000 width=215) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_current_price"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_99] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_99] (rows=31677367 width=208) Conds:RS_18._col0=RS_104._col0(Inner),Output:["_col1","_col2","_col4","_col7","_col9"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_104] PartitionCols:_col0 - Select Operator [SEL_103] (rows=8116 width=1119) + Select Operator [SEL_103] (rows=8116 width=98) Output:["_col0","_col1"] - Filter Operator [FIL_102] (rows=8116 width=1119) + Filter Operator [FIL_102] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_6] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_98] (rows=316788826 width=135) - Conds:RS_128._col2, _col3=RS_131._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col7"] + Merge Join Operator [MERGEJOIN_98] (rows=285115816 width=194) + Conds:RS_120._col2, _col3=RS_123._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_128] + SHUFFLE [RS_120] PartitionCols:_col2, _col3 - Select Operator [SEL_127] (rows=287989836 width=135) + Select Operator [SEL_119] (rows=285115816 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_126] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_22_item_i_item_sk_min) AND DynamicValue(RS_22_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_22_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (cs_warehouse_sk BETWEEN DynamicValue(RS_25_warehouse_w_warehouse_sk_min) AND DynamicValue(RS_25_warehouse_w_warehouse_sk_max) and in_bloom_filter(cs_warehouse_sk, DynamicValue(RS_25_warehouse_w_warehouse_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_warehouse_sk","cs_item_sk","cs_order_number","cs_sales_price"] + Filter Operator [FIL_118] (rows=285115816 width=127) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_22_item_i_item_sk_min) AND DynamicValue(RS_22_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_22_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is not null) + TableScan [TS_0] (rows=287989836 width=127) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_warehouse_sk","cs_item_sk","cs_order_number","cs_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_109] Group By Operator [GBY_108] (rows=1 width=12) @@ -150,7 +149,7 @@ Stage-0 SHUFFLE [RS_107] Group By Operator [GBY_106] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_105] (rows=8116 width=1119) + Select Operator [SEL_105] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_103] <-Reducer 12 [BROADCAST_EDGE] vectorized @@ -161,27 +160,16 @@ Stage-0 SHUFFLE [RS_115] Group By Operator [GBY_114] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_113] (rows=51333 width=1436) + Select Operator [SEL_113] (rows=51333 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_111] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_125] - Group By Operator [GBY_124] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_121] (rows=27 width=1029) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_119] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_131] + SHUFFLE [RS_123] PartitionCols:_col0, _col1 - Select Operator [SEL_130] (rows=28798881 width=106) + Select Operator [SEL_122] (rows=28798881 width=117) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_129] (rows=28798881 width=106) + Filter Operator [FIL_121] (rows=28798881 width=117) predicate:cr_item_sk is not null - TableScan [TS_3] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash"] + TableScan [TS_3] (rows=28798881 width=117) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query42.q.out b/ql/src/test/results/clientpositive/perf/tez/query42.q.out index a653fa8f65..85101e23ee 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query42.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query42.q.out @@ -57,55 +57,55 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_79] - Limit [LIM_78] (rows=100 width=88) + Limit [LIM_78] (rows=100 width=210) Number of rows:100 - Select Operator [SEL_77] (rows=348477374 width=88) + Select Operator [SEL_77] (rows=110 width=210) Output:["_col0","_col1","_col2","_col3"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_76] - Select Operator [SEL_75] (rows=348477374 width=88) + Select Operator [SEL_75] (rows=110 width=318) Output:["_col0","_col1","_col3"] - Group By Operator [GBY_74] (rows=348477374 width=88) + Group By Operator [GBY_74] (rows=110 width=206) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=120 width=206) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 - Merge Join Operator [MERGEJOIN_54] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_54] (rows=2301098 width=94) Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col7","_col8"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_65] PartitionCols:_col0 - Select Operator [SEL_64] (rows=231000 width=1436) + Select Operator [SEL_64] (rows=7333 width=101) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_63] (rows=231000 width=1436) + Filter Operator [FIL_63] (rows=7333 width=101) predicate:((i_manager_id = 1) and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_category_id","i_category","i_manager_id"] + TableScan [TS_6] (rows=462000 width=101) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category_id","i_category","i_manager_id"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_53] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_53] (rows=15062131 width=4) Conds:RS_73._col0=RS_57._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=18262 width=1119) + Select Operator [SEL_56] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_55] (rows=18262 width=1119) + Filter Operator [FIL_55] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,dt,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,dt,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_73] PartitionCols:_col0 - Select Operator [SEL_72] (rows=575995635 width=88) + Select Operator [SEL_72] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_71] (rows=575995635 width=88) + Filter Operator [FIL_71] (rows=550076554 width=114) predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_dt_d_date_sk_min) AND DynamicValue(RS_10_dt_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_dt_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_62] Group By Operator [GBY_61] (rows=1 width=12) @@ -114,7 +114,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_60] Group By Operator [GBY_59] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_58] (rows=18262 width=1119) + Select Operator [SEL_58] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_56] <-Reducer 9 [BROADCAST_EDGE] vectorized @@ -125,7 +125,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_68] Group By Operator [GBY_67] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_66] (rows=231000 width=1436) + Select Operator [SEL_66] (rows=7333 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_64] diff --git a/ql/src/test/results/clientpositive/perf/tez/query43.q.out b/ql/src/test/results/clientpositive/perf/tez/query43.q.out index afa3363caa..d0739a9907 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query43.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query43.q.out @@ -51,57 +51,57 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_79] - Limit [LIM_78] (rows=100 width=88) + Limit [LIM_78] (rows=100 width=972) Number of rows:100 - Select Operator [SEL_77] (rows=348477374 width=88) + Select Operator [SEL_77] (rows=3751 width=972) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_76] - Group By Operator [GBY_75] (rows=348477374 width=88) + Group By Operator [GBY_75] (rows=3751 width=972) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1 - Group By Operator [GBY_17] (rows=696954748 width=88) + Group By Operator [GBY_17] (rows=176297 width=972) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 - Top N Key Operator [TNK_33] (rows=696954748 width=88) + Top N Key Operator [TNK_33] (rows=37536846 width=320) keys:_col0, _col1,sort order:++,top n:100 - Select Operator [SEL_15] (rows=696954748 width=88) + Select Operator [SEL_15] (rows=37536846 width=320) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_55] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_55] (rows=37536846 width=320) Conds:RS_12._col1=RS_66._col0(Inner),Output:["_col2","_col5","_col7","_col8"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_66] PartitionCols:_col0 - Select Operator [SEL_65] (rows=852 width=1910) + Select Operator [SEL_65] (rows=341 width=304) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_64] (rows=852 width=1910) + Filter Operator [FIL_64] (rows=341 width=303) predicate:((s_gmt_offset = -6) and s_store_sk is not null) - TableScan [TS_6] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name","s_gmt_offset"] + TableScan [TS_6] (rows=1704 width=303) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name","s_gmt_offset"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_54] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_54] (rows=187574154 width=192) Conds:RS_74._col0=RS_58._col0(Inner),Output:["_col1","_col2","_col5"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_58] PartitionCols:_col0 - Select Operator [SEL_57] (rows=36524 width=1119) + Select Operator [SEL_57] (rows=652 width=99) Output:["_col0","_col2"] - Filter Operator [FIL_56] (rows=36524 width=1119) + Filter Operator [FIL_56] (rows=652 width=99) predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_day_name"] + TableScan [TS_3] (rows=73049 width=99) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_day_name"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_74] PartitionCols:_col0 - Select Operator [SEL_73] (rows=575995635 width=88) + Select Operator [SEL_73] (rows=525329897 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_72] (rows=575995635 width=88) + Filter Operator [FIL_72] (rows=525329897 width=114) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_13_store_s_store_sk_min) AND DynamicValue(RS_13_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_13_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_63] Group By Operator [GBY_62] (rows=1 width=12) @@ -110,7 +110,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_61] Group By Operator [GBY_60] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_59] (rows=36524 width=1119) + Select Operator [SEL_59] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_57] <-Reducer 9 [BROADCAST_EDGE] vectorized @@ -121,7 +121,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_69] Group By Operator [GBY_68] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_67] (rows=852 width=1910) + Select Operator [SEL_67] (rows=341 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_65] diff --git a/ql/src/test/results/clientpositive/perf/tez/query44.q.out b/ql/src/test/results/clientpositive/perf/tez/query44.q.out index 8105de9ce5..359d26404d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query44.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query44.q.out @@ -86,86 +86,86 @@ Stage-0 Stage-1 Reducer 4 vectorized File Output Operator [FS_138] - Limit [LIM_137] (rows=100 width=177) + Limit [LIM_137] (rows=100 width=218) Number of rows:100 - Select Operator [SEL_136] (rows=1393898919384048 width=177) + Select Operator [SEL_136] (rows=6951 width=218) Output:["_col0","_col1","_col2"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_69] - Select Operator [SEL_68] (rows=1393898919384048 width=177) + Select Operator [SEL_68] (rows=6951 width=218) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_107] (rows=1393898919384048 width=177) + Merge Join Operator [MERGEJOIN_107] (rows=6951 width=218) Conds:RS_65._col3=RS_66._col3(Inner),Output:["_col1","_col3","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_65] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_104] (rows=1267180808338276 width=177) + Merge Join Operator [MERGEJOIN_104] (rows=6951 width=111) Conds:RS_110._col0=RS_130._col0(Inner),Output:["_col1","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=462000 width=1436) + Select Operator [SEL_109] (rows=462000 width=111) Output:["_col0","_col1"] - Filter Operator [FIL_108] (rows=462000 width=1436) + Filter Operator [FIL_108] (rows=462000 width=111) predicate:i_item_sk is not null - TableScan [TS_0] (rows=462000 width=1436) - default@item,i1,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_product_name"] + TableScan [TS_0] (rows=462000 width=111) + default@item,i1,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_product_name"] <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_130] PartitionCols:_col0 - Select Operator [SEL_129] (rows=1151982528066248 width=177) + Select Operator [SEL_129] (rows=6951 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_128] (rows=1151982528066248 width=177) + Filter Operator [FIL_128] (rows=6951 width=116) predicate:((rank_window_0 < 11) and _col0 is not null) - PTF Operator [PTF_127] (rows=3455947584198744 width=177) + PTF Operator [PTF_127] (rows=20854 width=116) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_126] (rows=3455947584198744 width=177) + Select Operator [SEL_126] (rows=20854 width=116) Output:["_col0","_col1"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:0 - Filter Operator [FIL_21] (rows=3455947584198744 width=177) + Filter Operator [FIL_21] (rows=20854 width=228) predicate:(_col1 > (0.9 * _col2)) - Merge Join Operator [MERGEJOIN_103] (rows=10367842752596232 width=177) + Merge Join Operator [MERGEJOIN_103] (rows=62562 width=228) Conds:(Inner),Output:["_col0","_col1","_col2"] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_125] - Select Operator [SEL_124] (rows=71999454 width=88) + Select Operator [SEL_124] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_123] (rows=71999454 width=88) + Group By Operator [GBY_123] (rows=1 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_122] PartitionCols:_col0 - Group By Operator [GBY_121] (rows=143998908 width=88) + Group By Operator [GBY_121] (rows=258 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col1)"],keys:410 - Select Operator [SEL_120] (rows=143998908 width=88) + Select Operator [SEL_120] (rows=287946 width=114) Output:["_col1"] - Filter Operator [FIL_119] (rows=143998908 width=88) + Filter Operator [FIL_119] (rows=287946 width=114) predicate:((ss_store_sk = 410) and ss_hdemo_sk is null) - TableScan [TS_10] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_hdemo_sk","ss_store_sk","ss_net_profit"] + TableScan [TS_10] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_hdemo_sk","ss_store_sk","ss_net_profit"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_118] - Select Operator [SEL_117] (rows=143998908 width=88) + Select Operator [SEL_117] (rows=62562 width=116) Output:["_col0","_col1"] - Group By Operator [GBY_116] (rows=143998908 width=88) + Group By Operator [GBY_116] (rows=62562 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_115] PartitionCols:_col0 - Group By Operator [GBY_114] (rows=287997817 width=88) + Group By Operator [GBY_114] (rows=3199976 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_net_profit)","count(ss_net_profit)"],keys:ss_item_sk - Select Operator [SEL_113] (rows=287997817 width=88) + Select Operator [SEL_113] (rows=6399952 width=114) Output:["ss_item_sk","ss_net_profit"] - Filter Operator [FIL_112] (rows=287997817 width=88) + Filter Operator [FIL_112] (rows=6399952 width=114) predicate:(ss_store_sk = 410) - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,ss1,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_store_sk","ss_net_profit"] + TableScan [TS_3] (rows=575995635 width=114) + default@store_sales,ss1,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_store_sk","ss_net_profit"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_106] (rows=1267180808338276 width=177) + Merge Join Operator [MERGEJOIN_106] (rows=6951 width=111) Conds:RS_111._col0=RS_135._col0(Inner),Output:["_col1","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_111] @@ -174,13 +174,13 @@ Stage-0 <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_135] PartitionCols:_col0 - Select Operator [SEL_134] (rows=1151982528066248 width=177) + Select Operator [SEL_134] (rows=6951 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_133] (rows=1151982528066248 width=177) + Filter Operator [FIL_133] (rows=6951 width=116) predicate:((rank_window_0 < 11) and _col0 is not null) - PTF Operator [PTF_132] (rows=3455947584198744 width=177) + PTF Operator [PTF_132] (rows=20854 width=116) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_131] (rows=3455947584198744 width=177) + Select Operator [SEL_131] (rows=20854 width=116) Output:["_col0","_col1"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_51] diff --git a/ql/src/test/results/clientpositive/perf/tez/query45.q.out b/ql/src/test/results/clientpositive/perf/tez/query45.q.out index 6458811aa6..597210d328 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query45.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query45.q.out @@ -40,168 +40,156 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 14 <- Reducer 11 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Reducer 10 <- Reducer 15 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 8 (SIMPLE_EDGE) -Reducer 13 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Map 13 <- Reducer 16 (BROADCAST_EDGE) +Reducer 10 <- Reducer 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 8 (SIMPLE_EDGE) +Reducer 12 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) +Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 9 <- Map 8 (SIMPLE_EDGE), Reducer 12 (ONE_TO_ONE_EDGE) +Reducer 9 <- Map 8 (SIMPLE_EDGE), Reducer 11 (ONE_TO_ONE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_173] - Limit [LIM_172] (rows=100 width=152) + File Output Operator [FS_171] + Limit [LIM_170] (rows=100 width=299) Number of rows:100 - Select Operator [SEL_171] (rows=95833781 width=152) + Select Operator [SEL_169] (rows=285780 width=299) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_170] - Group By Operator [GBY_169] (rows=95833781 width=152) + SHUFFLE [RS_168] + Group By Operator [GBY_167] (rows=285780 width=299) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col0, _col1 - Group By Operator [GBY_52] (rows=191667562 width=152) + Group By Operator [GBY_52] (rows=4858260 width=299) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col7 - Top N Key Operator [TNK_82] (rows=191667562 width=152) + Top N Key Operator [TNK_82] (rows=10246864 width=418) keys:_col8, _col7,sort order:++,top n:100 - Select Operator [SEL_51] (rows=191667562 width=152) + Select Operator [SEL_51] (rows=10246864 width=418) Output:["_col3","_col7","_col8"] - Filter Operator [FIL_50] (rows=191667562 width=152) + Filter Operator [FIL_50] (rows=10246864 width=418) predicate:((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or CASE WHEN ((_col14 = 0L)) THEN (false) WHEN (_col17 is not null) THEN (true) WHEN (_col13 is null) THEN (null) WHEN ((_col15 < _col14)) THEN (null) ELSE (false) END) - Select Operator [SEL_49] (rows=191667562 width=152) + Select Operator [SEL_49] (rows=10246864 width=418) Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col17"] - Merge Join Operator [MERGEJOIN_133] (rows=191667562 width=152) + Merge Join Operator [MERGEJOIN_133] (rows=10246864 width=418) Conds:(Inner),Output:["_col3","_col4","_col6","_col8","_col12","_col16","_col17"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_168] - Group By Operator [GBY_167] (rows=1 width=16) + <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_166] + Group By Operator [GBY_165] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_150] Group By Operator [GBY_148] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["count()","count(i_item_id)"] - Select Operator [SEL_145] (rows=462000 width=1436) + Select Operator [SEL_145] (rows=11 width=104) Output:["i_item_id"] - Filter Operator [FIL_142] (rows=462000 width=1436) + Filter Operator [FIL_142] (rows=11 width=104) predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + TableScan [TS_6] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_46] - Merge Join Operator [MERGEJOIN_132] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_132] (rows=10246864 width=402) Conds:RS_43._col0=RS_44._col6(Inner),Output:["_col3","_col4","_col6","_col8","_col12"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_131] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_131] (rows=10246864 width=219) Conds:RS_29._col0=RS_30._col1(Inner),Output:["_col1","_col3","_col6","_col7"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_130] (rows=10246864 width=119) + Conds:RS_164._col0=RS_156._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 15 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_156] + PartitionCols:_col0 + Select Operator [SEL_155] (rows=130 width=12) + Output:["_col0"] + Filter Operator [FIL_154] (rows=130 width=12) + predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) + TableScan [TS_19] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_164] + PartitionCols:_col0 + Select Operator [SEL_163] (rows=143930993 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_162] (rows=143930993 width=123) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_23_date_dim_d_date_sk_min) AND DynamicValue(RS_23_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_23_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_16] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_161] + Group By Operator [GBY_160] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_159] + Group By Operator [GBY_158] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_157] (rows=130 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_155] <-Reducer 9 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_29] + SHUFFLE [RS_29] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_129] (rows=508200 width=1436) + Merge Join Operator [MERGEJOIN_129] (rows=462000 width=104) Conds:RS_146._col1=RS_153._col0(Left Outer),Output:["_col0","_col1","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_146] PartitionCols:_col1 - Select Operator [SEL_143] (rows=462000 width=1436) + Select Operator [SEL_143] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_140] (rows=462000 width=1436) + Filter Operator [FIL_140] (rows=462000 width=104) predicate:i_item_sk is not null Please refer to the previous TableScan [TS_6] - <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized + <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_153] PartitionCols:_col0 - Select Operator [SEL_152] (rows=231000 width=1436) + Select Operator [SEL_152] (rows=5 width=104) Output:["_col0","_col1"] - Group By Operator [GBY_151] (rows=231000 width=1436) + Group By Operator [GBY_151] (rows=5 width=100) Output:["_col0"],keys:KEY._col0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_149] PartitionCols:_col0 - Group By Operator [GBY_147] (rows=462000 width=1436) + Group By Operator [GBY_147] (rows=5 width=100) Output:["_col0"],keys:i_item_id - Select Operator [SEL_144] (rows=462000 width=1436) + Select Operator [SEL_144] (rows=11 width=104) Output:["i_item_id"] - Filter Operator [FIL_141] (rows=462000 width=1436) + Filter Operator [FIL_141] (rows=11 width=104) predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) Please refer to the previous TableScan [TS_6] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_130] (rows=158402938 width=135) - Conds:RS_166._col0=RS_156._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_156] - PartitionCols:_col0 - Select Operator [SEL_155] (rows=18262 width=1119) - Output:["_col0"] - Filter Operator [FIL_154] (rows=18262 width=1119) - predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_19] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_166] - PartitionCols:_col0 - Select Operator [SEL_165] (rows=144002668 width=135) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_164] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_23_date_dim_d_date_sk_min) AND DynamicValue(RS_23_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_23_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_16] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_163] - Group By Operator [GBY_162] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_115] - Group By Operator [GBY_114] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_113] (rows=508200 width=1436) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_129] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_161] - Group By Operator [GBY_160] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_159] - Group By Operator [GBY_158] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_157] (rows=18262 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_155] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_128] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_128] (rows=80000000 width=191) Conds:RS_136._col1=RS_139._col0(Inner),Output:["_col0","_col3","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_136] PartitionCols:_col1 - Select Operator [SEL_135] (rows=80000000 width=860) + Select Operator [SEL_135] (rows=80000000 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_134] (rows=80000000 width=860) + Filter Operator [FIL_134] (rows=80000000 width=8) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] + TableScan [TS_0] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_139] PartitionCols:_col0 - Select Operator [SEL_138] (rows=40000000 width=1014) + Select Operator [SEL_138] (rows=40000000 width=191) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_137] (rows=40000000 width=1014) + Filter Operator [FIL_137] (rows=40000000 width=191) predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_zip"] + TableScan [TS_3] (rows=40000000 width=191) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_zip"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query46.q.out b/ql/src/test/results/clientpositive/perf/tez/query46.q.out index 66f51c3173..6f354c5d39 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query46.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query46.q.out @@ -69,184 +69,160 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 10 <- Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 5 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) -Reducer 12 <- Map 16 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Map 8 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 16 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Map 6 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) -Reducer 8 <- Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Map 6 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_192] - Limit [LIM_191] (rows=100 width=88) + File Output Operator [FS_185] + Limit [LIM_184] (rows=100 width=594) Number of rows:100 - Select Operator [SEL_190] (rows=463823414 width=88) + Select Operator [SEL_183] (rows=20351707 width=594) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_46] - Select Operator [SEL_45] (rows=463823414 width=88) + Select Operator [SEL_45] (rows=20351707 width=594) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_44] (rows=463823414 width=88) + Filter Operator [FIL_44] (rows=20351707 width=594) predicate:(_col5 <> _col8) - Merge Join Operator [MERGEJOIN_145] (rows=463823414 width=88) - Conds:RS_41._col0=RS_189._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10"] + Merge Join Operator [MERGEJOIN_145] (rows=20351707 width=594) + Conds:RS_41._col0=RS_182._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10"] <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_41] + SHUFFLE [RS_41] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_140] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_140] (rows=80000000 width=277) Conds:RS_148._col1=RS_151._col0(Inner),Output:["_col0","_col2","_col3","_col5"] - <-Map 6 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_151] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] PartitionCols:_col0 - Select Operator [SEL_150] (rows=40000000 width=1014) + Select Operator [SEL_150] (rows=40000000 width=97) Output:["_col0","_col1"] - Filter Operator [FIL_149] (rows=40000000 width=1014) + Filter Operator [FIL_149] (rows=40000000 width=97) predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,current_addr,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_city"] + TableScan [TS_3] (rows=40000000 width=97) + default@customer_address,current_addr,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_148] PartitionCols:_col1 - Select Operator [SEL_147] (rows=80000000 width=860) + Select Operator [SEL_147] (rows=80000000 width=188) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_146] (rows=80000000 width=860) + Filter Operator [FIL_146] (rows=80000000 width=188) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] - <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_189] + TableScan [TS_0] (rows=80000000 width=188) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] + <-Reducer 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_182] PartitionCols:_col1 - Select Operator [SEL_188] (rows=421657640 width=88) + Select Operator [SEL_181] (rows=20351707 width=321) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_187] (rows=421657640 width=88) + Group By Operator [GBY_180] (rows=20351707 width=321) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 7 [SIMPLE_EDGE] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_34] (rows=843315281 width=88) + Group By Operator [GBY_34] (rows=20351707 width=321) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col17, _col3, _col5 - Merge Join Operator [MERGEJOIN_144] (rows=843315281 width=88) + Merge Join Operator [MERGEJOIN_144] (rows=20351707 width=97) Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col17"] - <-Map 6 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_152] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_152] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_150] - <-Reducer 13 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_143] (rows=766650239 width=88) - Conds:RS_27._col2=RS_174._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7"] - <-Map 18 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_174] + Merge Join Operator [MERGEJOIN_143] (rows=20351707 width=4) + Conds:RS_27._col2=RS_171._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_173] (rows=7200 width=107) + Select Operator [SEL_170] (rows=1855 width=12) Output:["_col0"] - Filter Operator [FIL_172] (rows=7200 width=107) + Filter Operator [FIL_169] (rows=1855 width=12) predicate:(((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) - TableScan [TS_15] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] - <-Reducer 12 [SIMPLE_EDGE] + TableScan [TS_15] (rows=7200 width=12) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_142] (rows=696954748 width=88) - Conds:RS_24._col4=RS_166._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_166] + Merge Join Operator [MERGEJOIN_142] (rows=78993142 width=178) + Conds:RS_24._col4=RS_163._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] + <-Map 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_165] (rows=1704 width=1910) + Select Operator [SEL_162] (rows=85 width=97) Output:["_col0"] - Filter Operator [FIL_164] (rows=1704 width=1910) + Filter Operator [FIL_161] (rows=85 width=97) predicate:((s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') and s_store_sk is not null) - TableScan [TS_12] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_city"] - <-Reducer 11 [SIMPLE_EDGE] + TableScan [TS_12] (rows=1704 width=97) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_city"] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_141] (rows=633595212 width=88) - Conds:RS_186._col0=RS_158._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_158] + Merge Join Operator [MERGEJOIN_141] (rows=196204013 width=218) + Conds:RS_179._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_157] (rows=73049 width=1119) + Select Operator [SEL_154] (rows=783 width=12) Output:["_col0"] - Filter Operator [FIL_156] (rows=73049 width=1119) + Filter Operator [FIL_153] (rows=783 width=12) predicate:((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dow"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_186] + TableScan [TS_9] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dow"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_179] PartitionCols:_col0 - Select Operator [SEL_185] (rows=575995635 width=88) + Select Operator [SEL_178] (rows=457565061 width=237) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_184] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_31_customer_address_ca_address_sk_min) AND DynamicValue(RS_31_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_31_customer_address_ca_address_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_41_customer_c_customer_sk_min) AND DynamicValue(RS_41_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_41_customer_c_customer_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_28_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_28_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_28_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_25_store_s_store_sk_min) AND DynamicValue(RS_25_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_25_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] + Filter Operator [FIL_177] (rows=457565061 width=237) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_28_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_28_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_28_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_25_store_s_store_sk_min) AND DynamicValue(RS_25_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_25_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (rows=575995635 width=237) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_160] + Group By Operator [GBY_159] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_158] + Group By Operator [GBY_157] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_156] (rows=783 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_154] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_163] - Group By Operator [GBY_162] (rows=1 width=12) + BROADCAST [RS_168] + Group By Operator [GBY_167] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_161] - Group By Operator [GBY_160] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_166] + Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_159] (rows=73049 width=1119) + Select Operator [SEL_164] (rows=85 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_157] + Please refer to the previous Select Operator [SEL_162] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_171] - Group By Operator [GBY_170] (rows=1 width=12) + BROADCAST [RS_176] + Group By Operator [GBY_175] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_169] - Group By Operator [GBY_168] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_167] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_165] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_179] - Group By Operator [GBY_178] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_177] - Group By Operator [GBY_176] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_174] + Group By Operator [GBY_173] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_175] (rows=7200 width=107) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_173] - <-Reducer 5 [BROADCAST_EDGE] vectorized - BROADCAST [RS_183] - Group By Operator [GBY_182] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_117] - Group By Operator [GBY_116] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] - Select Operator [SEL_115] (rows=88000001 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_140] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_181] - Group By Operator [GBY_180] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_155] - Group By Operator [GBY_154] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_153] (rows=40000000 width=1014) + Select Operator [SEL_172] (rows=1855 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_150] + Please refer to the previous Select Operator [SEL_170] diff --git a/ql/src/test/results/clientpositive/perf/tez/query47.q.out b/ql/src/test/results/clientpositive/perf/tez/query47.q.out index d034ea9433..4ee00a7e0a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query47.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query47.q.out @@ -101,15 +101,13 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Map 1 <- Reducer 13 (BROADCAST_EDGE) Reducer 10 <- Reducer 5 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) Reducer 3 <- Map 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 11 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) @@ -121,99 +119,99 @@ Stage-0 limit:-1 Stage-1 Reducer 8 vectorized - File Output Operator [FS_320] - Limit [LIM_319] (rows=100 width=88) + File Output Operator [FS_310] + Limit [LIM_309] (rows=100 width=658) Number of rows:100 - Select Operator [SEL_318] (rows=843315280 width=88) + Select Operator [SEL_308] (rows=301730 width=658) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_108] - Select Operator [SEL_107] (rows=843315280 width=88) + Select Operator [SEL_107] (rows=301730 width=658) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_279] (rows=843315280 width=88) + Merge Join Operator [MERGEJOIN_279] (rows=301730 width=546) Conds:RS_103._col0, _col1, _col2, _col3, (_col5 + 1)=RS_104._col0, _col1, _col2, _col3, _col8(Inner),RS_104._col0, _col1, _col2, _col3, _col8=RS_105._col0, _col1, _col2, _col3, (_col5 - 1)(Inner),Output:["_col4","_col6","_col10","_col11","_col12","_col13","_col19"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0, _col1, _col2, _col3, _col8 - Select Operator [SEL_67] (rows=31943759 width=88) + Select Operator [SEL_67] (rows=301730 width=605) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_169] (rows=31943759 width=88) + Filter Operator [FIL_169] (rows=301730 width=605) predicate:CASE WHEN ((_col0 > 0)) THEN (((abs((_col7 - _col0)) / _col0) > 0.1)) ELSE (null) END - Select Operator [SEL_66] (rows=63887519 width=88) + Select Operator [SEL_66] (rows=603460 width=601) Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_170] (rows=63887519 width=88) + Filter Operator [FIL_170] (rows=603460 width=601) predicate:((_col0 > 0) and (_col1 = 2000) and rank_window_1 is not null) - PTF Operator [PTF_65] (rows=383325119 width=88) + PTF Operator [PTF_65] (rows=202762560 width=601) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST, _col2 ASC NULLS FIRST","partition by:":"_col4, _col3, _col5, _col6"}] - Select Operator [SEL_64] (rows=383325119 width=88) + Select Operator [SEL_64] (rows=202762560 width=601) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_316] + SHUFFLE [RS_306] PartitionCols:_col3, _col2, _col4, _col5 - Select Operator [SEL_315] (rows=383325119 width=88) + Select Operator [SEL_305] (rows=202762560 width=489) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_314] (rows=383325119 width=88) + PTF Operator [PTF_304] (rows=202762560 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST, _col0 ASC NULLS FIRST","partition by:":"_col3, _col2, _col4, _col5, _col0"}] - Select Operator [SEL_313] (rows=383325119 width=88) + Select Operator [SEL_303] (rows=202762560 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_310] + SHUFFLE [RS_300] PartitionCols:_col3, _col2, _col4, _col5, _col0 - Group By Operator [GBY_307] (rows=383325119 width=88) + Group By Operator [GBY_297] (rows=202762560 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_92] (rows=766650239 width=88) + Group By Operator [GBY_92] (rows=216343183 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col8, _col9, _col11, _col12 - Merge Join Operator [MERGEJOIN_278] (rows=766650239 width=88) - Conds:RS_88._col2=RS_298._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col11","_col12"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_298] + Merge Join Operator [MERGEJOIN_278] (rows=216343183 width=476) + Conds:RS_88._col2=RS_296._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col11","_col12"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_296] PartitionCols:_col0 - Select Operator [SEL_297] (rows=1704 width=1910) + Select Operator [SEL_295] (rows=1704 width=183) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_296] (rows=1704 width=1910) + Filter Operator [FIL_294] (rows=1704 width=183) predicate:(s_company_name is not null and s_store_name is not null and s_store_sk is not null) - TableScan [TS_79] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_company_name"] + TableScan [TS_79] (rows=1704 width=183) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_company_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_88] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_277] (rows=696954748 width=88) - Conds:RS_85._col1=RS_290._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9"] + Merge Join Operator [MERGEJOIN_277] (rows=216343183 width=301) + Conds:RS_85._col1=RS_293._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_290] + SHUFFLE [RS_293] PartitionCols:_col0 - Select Operator [SEL_289] (rows=462000 width=1436) + Select Operator [SEL_292] (rows=462000 width=194) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_288] (rows=462000 width=1436) + Filter Operator [FIL_291] (rows=462000 width=194) predicate:(i_brand is not null and i_category is not null and i_item_sk is not null) - TableScan [TS_76] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_category"] + TableScan [TS_76] (rows=462000 width=194) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_85] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_276] (rows=633595212 width=88) - Conds:RS_306._col0=RS_282._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] + Merge Join Operator [MERGEJOIN_276] (rows=216343183 width=115) + Conds:RS_290._col0=RS_282._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_282] PartitionCols:_col0 - Select Operator [SEL_281] (rows=73048 width=1119) + Select Operator [SEL_281] (rows=752 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_280] (rows=73048 width=1119) + Filter Operator [FIL_280] (rows=752 width=12) predicate:(((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) - TableScan [TS_73] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_73] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_306] + SHUFFLE [RS_290] PartitionCols:_col0 - Select Operator [SEL_305] (rows=575995635 width=88) + Select Operator [SEL_289] (rows=525329897 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_304] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_86_item_i_item_sk_min) AND DynamicValue(RS_86_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_86_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_83_date_dim_d_date_sk_min) AND DynamicValue(RS_83_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_83_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_89_store_s_store_sk_min) AND DynamicValue(RS_89_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_89_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_70] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + Filter Operator [FIL_288] (rows=525329897 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_83_date_dim_d_date_sk_min) AND DynamicValue(RS_83_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_83_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_70] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_287] Group By Operator [GBY_286] (rows=1 width=12) @@ -222,59 +220,37 @@ Stage-0 SHUFFLE [RS_285] Group By Operator [GBY_284] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_283] (rows=73048 width=1119) + Select Operator [SEL_283] (rows=752 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_281] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_295] - Group By Operator [GBY_294] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_293] - Group By Operator [GBY_292] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_291] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_289] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_303] - Group By Operator [GBY_302] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_301] - Group By Operator [GBY_300] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_299] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_297] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_105] PartitionCols:_col0, _col1, _col2, _col3, (_col5 - 1) - Select Operator [SEL_99] (rows=383325119 width=88) + Select Operator [SEL_99] (rows=202762560 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_175] (rows=383325119 width=88) + Filter Operator [FIL_175] (rows=202762560 width=489) predicate:rank_window_0 is not null - PTF Operator [PTF_98] (rows=383325119 width=88) + PTF Operator [PTF_98] (rows=202762560 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST","partition by:":"_col3, _col2, _col4, _col5"}] - Select Operator [SEL_97] (rows=383325119 width=88) + Select Operator [SEL_97] (rows=202762560 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_308] + SHUFFLE [RS_298] PartitionCols:_col3, _col2, _col4, _col5 - Please refer to the previous Group By Operator [GBY_307] + Please refer to the previous Group By Operator [GBY_297] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_103] PartitionCols:_col0, _col1, _col2, _col3, (_col5 + 1) - Select Operator [SEL_29] (rows=383325119 width=88) + Select Operator [SEL_29] (rows=202762560 width=485) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_164] (rows=383325119 width=88) + Filter Operator [FIL_164] (rows=202762560 width=489) predicate:rank_window_0 is not null - PTF Operator [PTF_28] (rows=383325119 width=88) + PTF Operator [PTF_28] (rows=202762560 width=489) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST","partition by:":"_col3, _col2, _col4, _col5"}] - Select Operator [SEL_27] (rows=383325119 width=88) + Select Operator [SEL_27] (rows=202762560 width=489) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_309] + SHUFFLE [RS_299] PartitionCols:_col3, _col2, _col4, _col5 - Please refer to the previous Group By Operator [GBY_307] + Please refer to the previous Group By Operator [GBY_297] diff --git a/ql/src/test/results/clientpositive/perf/tez/query48.q.out b/ql/src/test/results/clientpositive/perf/tez/query48.q.out index 7b0ce1c046..eafbac1359 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query48.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query48.q.out @@ -131,10 +131,9 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) @@ -147,77 +146,77 @@ Stage-0 limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_133] - Group By Operator [GBY_132] (rows=1 width=8) + File Output Operator [FS_128] + Group By Operator [GBY_127] (rows=1 width=8) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_30] Group By Operator [GBY_29] (rows=1 width=8) Output:["_col0"],aggregations:["sum(_col4)"] - Merge Join Operator [MERGEJOIN_96] (rows=93701696 width=88) - Conds:RS_25._col3=RS_123._col0(Inner),Output:["_col4"] + Merge Join Operator [MERGEJOIN_96] (rows=321351 width=0) + Conds:RS_25._col3=RS_126._col0(Inner),Output:["_col4"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] + SHUFFLE [RS_126] PartitionCols:_col0 - Select Operator [SEL_122] (rows=1704 width=1910) + Select Operator [SEL_125] (rows=1704 width=4) Output:["_col0"] - Filter Operator [FIL_121] (rows=1704 width=1910) + Filter Operator [FIL_124] (rows=1704 width=4) predicate:s_store_sk is not null - TableScan [TS_12] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"] + TableScan [TS_12] (rows=1704 width=4) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col3 - Filter Operator [FIL_24] (rows=85183359 width=88) + Filter Operator [FIL_24] (rows=321351 width=86) predicate:((((_col13 = 'KY') or (_col13 = 'GA') or (_col13 = 'NM')) and _col6 BETWEEN 0 AND 2000) or (((_col13 = 'MT') or (_col13 = 'OR') or (_col13 = 'IN')) and _col6 BETWEEN 150 AND 3000) or (((_col13 = 'WI') or (_col13 = 'MO') or (_col13 = 'WV')) and _col6 BETWEEN 50 AND 25000)) - Merge Join Operator [MERGEJOIN_95] (rows=255550079 width=88) + Merge Join Operator [MERGEJOIN_95] (rows=1285413 width=86) Conds:RS_21._col2=RS_115._col0(Inner),Output:["_col3","_col4","_col6","_col13"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_115] PartitionCols:_col0 - Select Operator [SEL_114] (rows=20000000 width=1014) + Select Operator [SEL_114] (rows=20000000 width=187) Output:["_col0","_col1"] - Filter Operator [FIL_113] (rows=20000000 width=1014) + Filter Operator [FIL_113] (rows=20000000 width=187) predicate:((ca_country = 'United States') and ca_address_sk is not null) - TableScan [TS_9] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"] + TableScan [TS_9] (rows=40000000 width=187) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_94] (rows=232318249 width=88) + Merge Join Operator [MERGEJOIN_94] (rows=2570826 width=0) Conds:RS_18._col1=RS_107._col0(Inner),Output:["_col2","_col3","_col4","_col6"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_107] PartitionCols:_col0 - Select Operator [SEL_106] (rows=465450 width=385) + Select Operator [SEL_106] (rows=29552 width=184) Output:["_col0"] - Filter Operator [FIL_105] (rows=465450 width=385) + Filter Operator [FIL_105] (rows=29552 width=183) predicate:((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M') and cd_demo_sk is not null) - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + TableScan [TS_6] (rows=1861800 width=183) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_93] (rows=211198404 width=88) - Conds:RS_131._col0=RS_99._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"] + Merge Join Operator [MERGEJOIN_93] (rows=57024544 width=111) + Conds:RS_123._col0=RS_99._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col6"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_99] PartitionCols:_col0 - Select Operator [SEL_98] (rows=36524 width=1119) + Select Operator [SEL_98] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_97] (rows=36524 width=1119) + Filter Operator [FIL_97] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_131] + SHUFFLE [RS_123] PartitionCols:_col0 - Select Operator [SEL_130] (rows=191998545 width=88) + Select Operator [SEL_122] (rows=159705893 width=233) Output:["_col0","_col1","_col2","_col3","_col4","_col6"] - Filter Operator [FIL_129] (rows=191998545 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_22_customer_address_ca_address_sk_min) AND DynamicValue(RS_22_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_22_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_19_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_19_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_19_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_26_store_s_store_sk_min) AND DynamicValue(RS_26_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_26_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"] + Filter Operator [FIL_121] (rows=159705893 width=233) + predicate:((ss_addr_sk BETWEEN DynamicValue(RS_22_customer_address_ca_address_sk_min) AND DynamicValue(RS_22_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_22_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_19_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_19_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_19_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=233) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_net_profit"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_112] Group By Operator [GBY_111] (rows=1 width=12) @@ -226,7 +225,7 @@ Stage-0 SHUFFLE [RS_110] Group By Operator [GBY_109] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_108] (rows=465450 width=385) + Select Operator [SEL_108] (rows=29552 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_106] <-Reducer 12 [BROADCAST_EDGE] vectorized @@ -237,20 +236,9 @@ Stage-0 SHUFFLE [RS_118] Group By Operator [GBY_117] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_116] (rows=20000000 width=1014) + Select Operator [SEL_116] (rows=20000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_114] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_128] - Group By Operator [GBY_127] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] - Group By Operator [GBY_125] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_124] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_122] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_104] Group By Operator [GBY_103] (rows=1 width=12) @@ -259,7 +247,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_102] Group By Operator [GBY_101] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_100] (rows=36524 width=1119) + Select Operator [SEL_100] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_98] diff --git a/ql/src/test/results/clientpositive/perf/tez/query49.q.out b/ql/src/test/results/clientpositive/perf/tez/query49.q.out index 6f642ef1b2..bfbbaebcb1 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query49.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query49.q.out @@ -284,87 +284,87 @@ Stage-0 Stage-1 Reducer 11 vectorized File Output Operator [FS_310] - Limit [LIM_309] (rows=100 width=101) + Limit [LIM_309] (rows=100 width=215) Number of rows:100 - Select Operator [SEL_308] (rows=5915494 width=101) + Select Operator [SEL_308] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_307] - Select Operator [SEL_306] (rows=5915494 width=101) + Select Operator [SEL_306] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_305] (rows=5915494 width=101) + Group By Operator [GBY_305] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 9 [SIMPLE_EDGE] <-Reducer 24 [CONTAINS] vectorized Reduce Output Operator [RS_351] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_350] (rows=11830988 width=101) + Group By Operator [GBY_350] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Top N Key Operator [TNK_349] (rows=11830988 width=101) + Top N Key Operator [TNK_349] (rows=3418 width=214) keys:_col0, _col3, _col4, _col1, _col2,sort order:+++++,top n:100 - Select Operator [SEL_348] (rows=8604378 width=88) + Select Operator [SEL_348] (rows=1142 width=213) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_347] (rows=8604378 width=88) + Filter Operator [FIL_347] (rows=1142 width=248) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) - PTF Operator [PTF_346] (rows=12906568 width=88) + PTF Operator [PTF_346] (rows=1714 width=248) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_345] (rows=12906568 width=88) + Select Operator [SEL_345] (rows=1714 width=248) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_344] PartitionCols:0 - Select Operator [SEL_343] (rows=12906568 width=88) + Select Operator [SEL_343] (rows=1714 width=244) Output:["rank_window_0","_col0","_col1","_col2","_col3","_col4"] - PTF Operator [PTF_342] (rows=12906568 width=88) + PTF Operator [PTF_342] (rows=1714 width=244) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_341] (rows=12906568 width=88) + Select Operator [SEL_341] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_340] PartitionCols:0 - Group By Operator [GBY_339] (rows=12906568 width=88) + Group By Operator [GBY_339] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_89] PartitionCols:_col0 - Group By Operator [GBY_88] (rows=25813137 width=88) + Group By Operator [GBY_88] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0 - Select Operator [SEL_86] (rows=25813137 width=88) + Select Operator [SEL_86] (rows=1673571 width=73) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_237] (rows=25813137 width=88) + Merge Join Operator [MERGEJOIN_237] (rows=1673571 width=73) Conds:RS_83._col1, _col2=RS_338._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col11","_col12"] <-Map 30 [SIMPLE_EDGE] vectorized SHUFFLE [RS_338] PartitionCols:_col0, _col1 - Select Operator [SEL_337] (rows=19197050 width=77) + Select Operator [SEL_337] (rows=19197050 width=119) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_336] (rows=19197050 width=77) + Filter Operator [FIL_336] (rows=19197050 width=119) predicate:((sr_return_amt > 10000) and sr_item_sk is not null and sr_ticket_number is not null) - TableScan [TS_77] (rows=57591150 width=77) - default@store_returns,sr,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] + TableScan [TS_77] (rows=57591150 width=119) + default@store_returns,sr,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_83] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_236] (rows=23466488 width=88) + Merge Join Operator [MERGEJOIN_236] (rows=1673571 width=8) Conds:RS_335._col0=RS_272._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_272] PartitionCols:_col0 - Select Operator [SEL_267] (rows=18262 width=1119) + Select Operator [SEL_267] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_266] (rows=18262 width=1119) + Filter Operator [FIL_266] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 29 [SIMPLE_EDGE] vectorized SHUFFLE [RS_335] PartitionCols:_col0 - Select Operator [SEL_334] (rows=21333171 width=88) + Select Operator [SEL_334] (rows=61119617 width=229) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_333] (rows=21333171 width=88) + Filter Operator [FIL_333] (rows=61119617 width=229) predicate:((ss_net_paid > 0) and (ss_net_profit > 1) and (ss_quantity > 0) and (ss_sold_date_sk BETWEEN DynamicValue(RS_81_date_dim_d_date_sk_min) AND DynamicValue(RS_81_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_81_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_ticket_number is not null) - TableScan [TS_71] (rows=575995635 width=88) - default@store_sales,sts,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_net_paid","ss_net_profit"] + TableScan [TS_71] (rows=575995635 width=229) + default@store_sales,sts,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_net_paid","ss_net_profit"] <-Reducer 25 [BROADCAST_EDGE] vectorized BROADCAST [RS_332] Group By Operator [GBY_331] (rows=1 width=12) @@ -373,70 +373,70 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_279] Group By Operator [GBY_276] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_273] (rows=18262 width=1119) + Select Operator [SEL_273] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_267] <-Reducer 8 [CONTAINS] vectorized Reduce Output Operator [RS_304] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_303] (rows=11830988 width=101) + Group By Operator [GBY_303] (rows=3418 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Top N Key Operator [TNK_302] (rows=11830988 width=101) + Top N Key Operator [TNK_302] (rows=3418 width=214) keys:_col0, _col3, _col4, _col1, _col2,sort order:+++++,top n:100 - Select Operator [SEL_301] (rows=3226610 width=135) + Select Operator [SEL_301] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_300] (rows=3226610 width=135) + Group By Operator [GBY_300] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 7 [SIMPLE_EDGE] <-Reducer 18 [CONTAINS] vectorized Reduce Output Operator [RS_330] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_329] (rows=6453220 width=135) + Group By Operator [GBY_329] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_328] (rows=4302070 width=135) + Select Operator [SEL_328] (rows=1134 width=215) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_327] (rows=4302070 width=135) + Filter Operator [FIL_327] (rows=1134 width=248) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) - PTF Operator [PTF_326] (rows=6453105 width=135) + PTF Operator [PTF_326] (rows=1701 width=248) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_325] (rows=6453105 width=135) + Select Operator [SEL_325] (rows=1701 width=248) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_324] PartitionCols:0 - Select Operator [SEL_323] (rows=6453105 width=135) + Select Operator [SEL_323] (rows=1701 width=244) Output:["rank_window_0","_col0","_col1","_col2","_col3","_col4"] - PTF Operator [PTF_322] (rows=6453105 width=135) + PTF Operator [PTF_322] (rows=1701 width=244) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_321] (rows=6453105 width=135) + Select Operator [SEL_321] (rows=1701 width=244) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_320] PartitionCols:0 - Group By Operator [GBY_319] (rows=6453105 width=135) + Group By Operator [GBY_319] (rows=1701 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_50] PartitionCols:_col0 - Group By Operator [GBY_49] (rows=12906211 width=135) + Group By Operator [GBY_49] (rows=1701 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0 - Select Operator [SEL_47] (rows=12906211 width=135) + Select Operator [SEL_47] (rows=865646 width=188) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_235] (rows=12906211 width=135) + Merge Join Operator [MERGEJOIN_235] (rows=865646 width=188) Conds:RS_44._col1, _col2=RS_318._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col11","_col12"] <-Map 28 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] PartitionCols:_col0, _col1 - Select Operator [SEL_317] (rows=9599627 width=106) + Select Operator [SEL_317] (rows=9599627 width=121) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_316] (rows=9599627 width=106) + Filter Operator [FIL_316] (rows=9599627 width=121) predicate:((cr_return_amount > 10000) and cr_item_sk is not null and cr_order_number is not null) - TableScan [TS_38] (rows=28798881 width=106) - default@catalog_returns,cr,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] + TableScan [TS_38] (rows=28798881 width=121) + default@catalog_returns,cr,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_234] (rows=11732919 width=135) + Merge Join Operator [MERGEJOIN_234] (rows=865646 width=102) Conds:RS_315._col0=RS_270._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_270] @@ -445,12 +445,12 @@ Stage-0 <-Map 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_315] PartitionCols:_col0 - Select Operator [SEL_314] (rows=10666290 width=135) + Select Operator [SEL_314] (rows=31838858 width=239) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_313] (rows=10666290 width=135) + Filter Operator [FIL_313] (rows=31838858 width=239) predicate:((cs_net_paid > 0) and (cs_net_profit > 1) and (cs_quantity > 0) and (cs_sold_date_sk BETWEEN DynamicValue(RS_42_date_dim_d_date_sk_min) AND DynamicValue(RS_42_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null and cs_sold_date_sk is not null) - TableScan [TS_32] (rows=287989836 width=135) - default@catalog_sales,cs,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_net_paid","cs_net_profit"] + TableScan [TS_32] (rows=287989836 width=239) + default@catalog_sales,cs,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_net_paid","cs_net_profit"] <-Reducer 19 [BROADCAST_EDGE] vectorized BROADCAST [RS_312] Group By Operator [GBY_311] (rows=1 width=12) @@ -459,58 +459,58 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_278] Group By Operator [GBY_275] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_271] (rows=18262 width=1119) + Select Operator [SEL_271] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_267] <-Reducer 6 [CONTAINS] vectorized Reduce Output Operator [RS_299] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_298] (rows=6453220 width=135) + Group By Operator [GBY_298] (rows=2276 width=215) Output:["_col0","_col1","_col2","_col3","_col4"],keys:_col0, _col3, _col4, _col1, _col2 - Select Operator [SEL_297] (rows=2151150 width=135) + Select Operator [SEL_297] (rows=1142 width=211) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_296] (rows=2151150 width=135) + Filter Operator [FIL_296] (rows=1142 width=248) predicate:((_col0 <= 10) or (rank_window_1 <= 10)) - PTF Operator [PTF_295] (rows=3226726 width=135) + PTF Operator [PTF_295] (rows=1714 width=248) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col4 AS decimal(15,4)) / CAST( _col5 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_294] (rows=3226726 width=135) + Select Operator [SEL_294] (rows=1714 width=248) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_293] PartitionCols:0 - Select Operator [SEL_292] (rows=3226726 width=135) + Select Operator [SEL_292] (rows=1714 width=244) Output:["rank_window_0","_col0","_col1","_col2","_col3","_col4"] - PTF Operator [PTF_291] (rows=3226726 width=135) + PTF Operator [PTF_291] (rows=1714 width=244) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"(CAST( _col1 AS decimal(15,4)) / CAST( _col2 AS decimal(15,4))) ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_290] (rows=3226726 width=135) + Select Operator [SEL_290] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_289] PartitionCols:0 - Group By Operator [GBY_288] (rows=3226726 width=135) + Group By Operator [GBY_288] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Group By Operator [GBY_17] (rows=6453452 width=135) + Group By Operator [GBY_17] (rows=1714 width=244) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0 - Select Operator [SEL_15] (rows=6453452 width=135) + Select Operator [SEL_15] (rows=438010 width=177) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_233] (rows=6453452 width=135) + Merge Join Operator [MERGEJOIN_233] (rows=438010 width=177) Conds:RS_12._col1, _col2=RS_287._col0, _col1(Inner),Output:["_col1","_col3","_col4","_col11","_col12"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_287] PartitionCols:_col0, _col1 - Select Operator [SEL_286] (rows=4799489 width=92) + Select Operator [SEL_286] (rows=4799489 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_285] (rows=4799489 width=92) + Filter Operator [FIL_285] (rows=4799489 width=118) predicate:((wr_return_amt > 10000) and wr_item_sk is not null and wr_order_number is not null) - TableScan [TS_6] (rows=14398467 width=92) - default@web_returns,wr,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] + TableScan [TS_6] (rows=14398467 width=118) + default@web_returns,wr,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_232] (rows=5866775 width=135) + Merge Join Operator [MERGEJOIN_232] (rows=438010 width=122) Conds:RS_284._col0=RS_268._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_268] @@ -519,12 +519,12 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_284] PartitionCols:_col0 - Select Operator [SEL_283] (rows=5333432 width=135) + Select Operator [SEL_283] (rows=15996318 width=239) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_282] (rows=5333432 width=135) + Filter Operator [FIL_282] (rows=15996318 width=239) predicate:((ws_net_paid > 0) and (ws_net_profit > 1) and (ws_quantity > 0) and (ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,ws,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_net_paid","ws_net_profit"] + TableScan [TS_0] (rows=144002668 width=239) + default@web_sales,ws,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_net_paid","ws_net_profit"] <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_281] Group By Operator [GBY_280] (rows=1 width=12) @@ -533,7 +533,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_277] Group By Operator [GBY_274] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_269] (rows=18262 width=1119) + Select Operator [SEL_269] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_267] diff --git a/ql/src/test/results/clientpositive/perf/tez/query5.q.out b/ql/src/test/results/clientpositive/perf/tez/query5.q.out index e554dd4400..38d5d68abd 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query5.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query5.q.out @@ -255,28 +255,22 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Union 2 (CONTAINS) -Map 22 <- Reducer 15 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE), Union 23 (CONTAINS) -Map 24 <- Union 23 (CONTAINS) -Map 27 <- Reducer 19 (BROADCAST_EDGE), Reducer 35 (BROADCAST_EDGE), Union 28 (CONTAINS) -Map 29 <- Reducer 32 (BROADCAST_EDGE), Reducer 33 (BROADCAST_EDGE), Reducer 35 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Union 2 (CONTAINS) +Map 21 <- Reducer 15 (BROADCAST_EDGE), Union 22 (CONTAINS) +Map 23 <- Union 22 (CONTAINS) +Map 25 <- Reducer 19 (BROADCAST_EDGE), Union 26 (CONTAINS) Map 9 <- Union 2 (CONTAINS) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 10 (SIMPLE_EDGE), Union 23 (SIMPLE_EDGE) -Reducer 13 <- Map 25 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 12 <- Map 10 (SIMPLE_EDGE), Union 22 (SIMPLE_EDGE) +Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Union 6 (CONTAINS) Reducer 15 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 10 (SIMPLE_EDGE), Union 28 (SIMPLE_EDGE) -Reducer 17 <- Map 34 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) +Reducer 16 <- Map 10 (SIMPLE_EDGE), Union 26 (SIMPLE_EDGE) +Reducer 17 <- Map 30 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) Reducer 18 <- Reducer 17 (SIMPLE_EDGE), Union 6 (CONTAINS) Reducer 19 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 26 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 28 <- Map 27 (SIMPLE_EDGE), Map 29 (SIMPLE_EDGE), Union 26 (CONTAINS) Reducer 3 <- Map 10 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) -Reducer 30 <- Map 29 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 32 <- Map 31 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 31 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Map 34 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Map 20 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) Reducer 7 <- Union 6 (SIMPLE_EDGE) @@ -287,249 +281,202 @@ Stage-0 limit:100 Stage-1 Reducer 8 vectorized - File Output Operator [FS_309] - Limit [LIM_308] (rows=100 width=110) + File Output Operator [FS_304] + Limit [LIM_303] (rows=100 width=619) Number of rows:100 - Select Operator [SEL_307] (rows=1136898901 width=110) + Select Operator [SEL_302] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_306] - Select Operator [SEL_305] (rows=1136898901 width=110) + SHUFFLE [RS_301] + Select Operator [SEL_300] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_304] (rows=1136898901 width=110) + Group By Operator [GBY_299] (rows=38846 width=627) Output:["_col0","_col1","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 6 [SIMPLE_EDGE] <-Reducer 14 [CONTAINS] vectorized - Reduce Output Operator [RS_323] + Reduce Output Operator [RS_315] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_322] (rows=2273797803 width=110) + Group By Operator [GBY_314] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_321] (rows=757932601 width=110) + Top N Key Operator [TNK_313] (rows=39721 width=618) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_320] (rows=191657181 width=132) + Select Operator [SEL_312] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_319] (rows=191657181 width=132) + Group By Operator [GBY_311] (rows=38846 width=548) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col0 - Group By Operator [GBY_46] (rows=383314363 width=132) + Group By Operator [GBY_46] (rows=2835758 width=548) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col9 - Merge Join Operator [MERGEJOIN_222] (rows=383314363 width=132) - Conds:RS_42._col0=RS_315._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] - <-Map 25 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_315] + Merge Join Operator [MERGEJOIN_222] (rows=34813117 width=535) + Conds:RS_42._col0=RS_310._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_310] PartitionCols:_col0 - Select Operator [SEL_314] (rows=46000 width=460) + Select Operator [SEL_309] (rows=46000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_313] (rows=46000 width=460) + Filter Operator [FIL_308] (rows=46000 width=104) predicate:cp_catalog_page_sk is not null - TableScan [TS_36] (rows=46000 width=460) - default@catalog_page,catalog_page,Tbl:COMPLETE,Col:NONE,Output:["cp_catalog_page_sk","cp_catalog_page_id"] + TableScan [TS_36] (rows=46000 width=104) + default@catalog_page,catalog_page,Tbl:COMPLETE,Col:COMPLETE,Output:["cp_catalog_page_sk","cp_catalog_page_id"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_221] (rows=348467596 width=132) - Conds:Union 23._col1=RS_276._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_221] (rows=34813117 width=438) + Conds:Union 22._col1=RS_276._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_276] PartitionCols:_col0 - Select Operator [SEL_273] (rows=8116 width=1119) + Select Operator [SEL_273] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_272] (rows=8116 width=1119) + Filter Operator [FIL_272] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-08-18 00:00:00' and d_date_sk is not null) - TableScan [TS_8] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Union 23 [SIMPLE_EDGE] - <-Map 22 [CONTAINS] vectorized - Reduce Output Operator [RS_341] + TableScan [TS_8] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Union 22 [SIMPLE_EDGE] + <-Map 21 [CONTAINS] vectorized + Reduce Output Operator [RS_328] PartitionCols:_col1 - Select Operator [SEL_340] (rows=287989836 width=135) + Select Operator [SEL_327] (rows=285117694 width=455) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_339] (rows=287989836 width=135) - predicate:((cs_catalog_page_sk BETWEEN DynamicValue(RS_43_catalog_page_cp_catalog_page_sk_min) AND DynamicValue(RS_43_catalog_page_cp_catalog_page_sk_max) and in_bloom_filter(cs_catalog_page_sk, DynamicValue(RS_43_catalog_page_cp_catalog_page_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_catalog_page_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_253] (rows=287989836 width=135) + Filter Operator [FIL_326] (rows=285117694 width=231) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_catalog_page_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_253] (rows=287989836 width=231) Output:["cs_sold_date_sk","cs_catalog_page_sk","cs_ext_sales_price","cs_net_profit"] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_336] - Group By Operator [GBY_335] (rows=1 width=12) + BROADCAST [RS_325] + Group By Operator [GBY_324] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_284] Group By Operator [GBY_281] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_277] (rows=8116 width=1119) + Select Operator [SEL_277] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_273] - <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_338] - Group By Operator [GBY_337] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_318] - Group By Operator [GBY_317] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_316] (rows=46000 width=460) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_314] - <-Map 24 [CONTAINS] vectorized - Reduce Output Operator [RS_344] + <-Map 23 [CONTAINS] vectorized + Reduce Output Operator [RS_331] PartitionCols:_col1 - Select Operator [SEL_343] (rows=28798881 width=106) + Select Operator [SEL_330] (rows=28221805 width=451) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_342] (rows=28798881 width=106) + Filter Operator [FIL_329] (rows=28221805 width=227) predicate:(cr_catalog_page_sk is not null and cr_returned_date_sk is not null) - TableScan [TS_258] (rows=28798881 width=106) + TableScan [TS_258] (rows=28798881 width=227) Output:["cr_returned_date_sk","cr_catalog_page_sk","cr_return_amount","cr_net_loss"] <-Reducer 18 [CONTAINS] vectorized - Reduce Output Operator [RS_334] + Reduce Output Operator [RS_323] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_333] (rows=2273797803 width=110) + Group By Operator [GBY_322] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_332] (rows=757932601 width=110) + Top N Key Operator [TNK_321] (rows=39721 width=618) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_331] (rows=182955399 width=135) + Select Operator [SEL_320] (rows=53 width=615) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_330] (rows=182955399 width=135) + Group By Operator [GBY_319] (rows=53 width=548) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_80] PartitionCols:_col0 - Group By Operator [GBY_79] (rows=365910798 width=135) + Group By Operator [GBY_79] (rows=3498 width=548) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col9 - Merge Join Operator [MERGEJOIN_224] (rows=365910798 width=135) - Conds:RS_75._col0=RS_326._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] - <-Map 34 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_326] + Merge Join Operator [MERGEJOIN_224] (rows=30966059 width=543) + Conds:RS_75._col0=RS_318._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_318] PartitionCols:_col0 - Select Operator [SEL_325] (rows=84 width=1850) + Select Operator [SEL_317] (rows=84 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_324] (rows=84 width=1850) + Filter Operator [FIL_316] (rows=84 width=104) predicate:web_site_sk is not null - TableScan [TS_69] (rows=84 width=1850) - default@web_site,web_site,Tbl:COMPLETE,Col:NONE,Output:["web_site_sk","web_site_id"] + TableScan [TS_69] (rows=84 width=104) + default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_site_id"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_75] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_223] (rows=332646173 width=135) - Conds:Union 28._col1=RS_278._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_223] (rows=30966059 width=447) + Conds:Union 26._col1=RS_278._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_278] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_273] - <-Union 28 [SIMPLE_EDGE] - <-Map 27 [CONTAINS] vectorized - Reduce Output Operator [RS_352] + <-Union 26 [SIMPLE_EDGE] + <-Map 25 [CONTAINS] vectorized + Reduce Output Operator [RS_336] PartitionCols:_col1 - Select Operator [SEL_351] (rows=144002668 width=135) + Select Operator [SEL_335] (rows=143930874 width=455) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_350] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_73_date_dim_d_date_sk_min) AND DynamicValue(RS_73_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_73_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_76_web_site_web_site_sk_min) AND DynamicValue(RS_76_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_76_web_site_web_site_sk_bloom_filter))) and ws_sold_date_sk is not null and ws_web_site_sk is not null) - TableScan [TS_263] (rows=144002668 width=135) + Filter Operator [FIL_334] (rows=143930874 width=231) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_73_date_dim_d_date_sk_min) AND DynamicValue(RS_73_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_73_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null and ws_web_site_sk is not null) + TableScan [TS_263] (rows=144002668 width=231) Output:["ws_sold_date_sk","ws_web_site_sk","ws_ext_sales_price","ws_net_profit"] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_348] - Group By Operator [GBY_347] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_329] - Group By Operator [GBY_328] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_327] (rows=84 width=1850) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_325] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_346] - Group By Operator [GBY_345] (rows=1 width=12) + BROADCAST [RS_333] + Group By Operator [GBY_332] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_285] Group By Operator [GBY_282] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_279] (rows=8116 width=1119) + Select Operator [SEL_279] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_273] - <-Reducer 30 [CONTAINS] + <-Reducer 28 [CONTAINS] Reduce Output Operator [RS_271] PartitionCols:_col1 - Select Operator [SEL_269] (rows=158402938 width=135) + Select Operator [SEL_269] (rows=134782734 width=454) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_268] (rows=158402938 width=135) - Conds:RS_368._col0, _col2=RS_355._col1, _col2(Inner),Output:["_col1","_col3","_col6","_col7"] - <-Map 31 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_355] + Merge Join Operator [MERGEJOIN_268] (rows=134782734 width=230) + Conds:RS_339._col0, _col2=RS_342._col1, _col2(Inner),Output:["_col1","_col3","_col6","_col7"] + <-Map 27 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_339] + PartitionCols:_col0, _col2 + Select Operator [SEL_338] (rows=143966669 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_337] (rows=143966669 width=11) + predicate:(ws_item_sk is not null and ws_order_number is not null and ws_web_site_sk is not null) + TableScan [TS_54] (rows=144002668 width=11) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_item_sk","ws_web_site_sk","ws_order_number"] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_342] PartitionCols:_col1, _col2 - Select Operator [SEL_354] (rows=14398467 width=92) + Select Operator [SEL_341] (rows=13749816 width=225) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_353] (rows=14398467 width=92) + Filter Operator [FIL_340] (rows=13749816 width=225) predicate:(wr_item_sk is not null and wr_order_number is not null and wr_returned_date_sk is not null) - TableScan [TS_57] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_item_sk","wr_order_number","wr_return_amt","wr_net_loss"] - <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_368] - PartitionCols:_col0, _col2 - Select Operator [SEL_367] (rows=144002668 width=135) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_366] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_61_web_returns_wr_item_sk_min) AND DynamicValue(RS_61_web_returns_wr_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_61_web_returns_wr_item_sk_bloom_filter))) and (ws_order_number BETWEEN DynamicValue(RS_61_web_returns_wr_order_number_min) AND DynamicValue(RS_61_web_returns_wr_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_61_web_returns_wr_order_number_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_76_web_site_web_site_sk_min) AND DynamicValue(RS_76_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_76_web_site_web_site_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_web_site_sk is not null) - TableScan [TS_54] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_item_sk","ws_web_site_sk","ws_order_number"] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_349] - Please refer to the previous Group By Operator [GBY_347] - <-Reducer 32 [BROADCAST_EDGE] vectorized - BROADCAST [RS_363] - Group By Operator [GBY_362] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=14398467)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_360] - Group By Operator [GBY_358] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=14398467)"] - Select Operator [SEL_356] (rows=14398467 width=92) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_354] - <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_365] - Group By Operator [GBY_364] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=14398467)"] - <-Map 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_361] - Group By Operator [GBY_359] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=14398467)"] - Select Operator [SEL_357] (rows=14398467 width=92) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_354] + TableScan [TS_57] (rows=14398467 width=225) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_returned_date_sk","wr_item_sk","wr_order_number","wr_return_amt","wr_net_loss"] <-Reducer 5 [CONTAINS] vectorized - Reduce Output Operator [RS_303] + Reduce Output Operator [RS_298] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_302] (rows=2273797803 width=110) + Group By Operator [GBY_297] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_301] (rows=757932601 width=110) + Top N Key Operator [TNK_296] (rows=39721 width=618) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_300] (rows=383320021 width=87) + Select Operator [SEL_295] (rows=822 width=617) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_299] (rows=383320021 width=87) + Group By Operator [GBY_294] (rows=822 width=548) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0 - Group By Operator [GBY_21] (rows=766640042 width=87) + Group By Operator [GBY_21] (rows=78090 width=548) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col2)","sum(_col4)","sum(_col3)","sum(_col5)"],keys:_col9 - Merge Join Operator [MERGEJOIN_220] (rows=766640042 width=87) - Conds:RS_17._col0=RS_290._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] + Merge Join Operator [MERGEJOIN_220] (rows=64325014 width=376) + Conds:RS_17._col0=RS_293._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col9"] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_290] + SHUFFLE [RS_293] PartitionCols:_col0 - Select Operator [SEL_289] (rows=1704 width=1910) + Select Operator [SEL_292] (rows=1704 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_288] (rows=1704 width=1910) + Filter Operator [FIL_291] (rows=1704 width=104) predicate:s_store_sk is not null - TableScan [TS_11] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id"] + TableScan [TS_11] (rows=1704 width=104) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_219] (rows=696945478 width=87) + Merge Join Operator [MERGEJOIN_219] (rows=64325014 width=277) Conds:Union 2._col1=RS_274._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_274] @@ -537,13 +484,13 @@ Stage-0 Please refer to the previous Select Operator [SEL_273] <-Union 2 [SIMPLE_EDGE] <-Map 1 [CONTAINS] vectorized - Reduce Output Operator [RS_298] + Reduce Output Operator [RS_290] PartitionCols:_col1 - Select Operator [SEL_297] (rows=575995635 width=88) + Select Operator [SEL_289] (rows=525329897 width=445) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_296] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_15_date_dim_d_date_sk_min) AND DynamicValue(RS_15_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_15_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_18_store_s_store_sk_min) AND DynamicValue(RS_18_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_18_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_225] (rows=575995635 width=88) + Filter Operator [FIL_288] (rows=525329897 width=221) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_15_date_dim_d_date_sk_min) AND DynamicValue(RS_15_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_15_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_225] (rows=575995635 width=221) Output:["ss_sold_date_sk","ss_store_sk","ss_ext_sales_price","ss_net_profit"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_287] @@ -553,27 +500,16 @@ Stage-0 SHUFFLE [RS_283] Group By Operator [GBY_280] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_275] (rows=8116 width=1119) + Select Operator [SEL_275] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_273] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_295] - Group By Operator [GBY_294] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_293] - Group By Operator [GBY_292] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_291] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_289] <-Map 9 [CONTAINS] vectorized - Reduce Output Operator [RS_312] + Reduce Output Operator [RS_307] PartitionCols:_col1 - Select Operator [SEL_311] (rows=57591150 width=77) + Select Operator [SEL_306] (rows=53634860 width=447) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_310] (rows=57591150 width=77) + Filter Operator [FIL_305] (rows=53634860 width=223) predicate:(sr_returned_date_sk is not null and sr_store_sk is not null) - TableScan [TS_236] (rows=57591150 width=77) + TableScan [TS_236] (rows=57591150 width=223) Output:["sr_returned_date_sk","sr_store_sk","sr_return_amt","sr_net_loss"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query50.q.out b/ql/src/test/results/clientpositive/perf/tez/query50.q.out index efbae5cbf3..0e6b8c8bd8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query50.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query50.q.out @@ -117,14 +117,12 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 12 <- Reducer 10 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 12 <- Reducer 10 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 10 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 15 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) @@ -135,139 +133,117 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_156] - Limit [LIM_155] (rows=100 width=88) + File Output Operator [FS_146] + Limit [LIM_145] (rows=100 width=858) Number of rows:100 - Select Operator [SEL_154] (rows=383325119 width=88) + Select Operator [SEL_144] (rows=11945216 width=857) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_153] - Group By Operator [GBY_152] (rows=383325119 width=88) + SHUFFLE [RS_143] + Group By Operator [GBY_142] (rows=11945216 width=857) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Group By Operator [GBY_29] (rows=766650239 width=88) + Group By Operator [GBY_29] (rows=11945216 width=857) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Top N Key Operator [TNK_56] (rows=766650239 width=88) + Top N Key Operator [TNK_56] (rows=11945216 width=821) keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9,sort order:++++++++++,top n:100 - Select Operator [SEL_27] (rows=766650239 width=88) + Select Operator [SEL_27] (rows=11945216 width=821) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - Merge Join Operator [MERGEJOIN_120] (rows=766650239 width=88) - Conds:RS_24._col10=RS_143._col0(Inner),Output:["_col0","_col7","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_143] + Merge Join Operator [MERGEJOIN_120] (rows=11945216 width=821) + Conds:RS_24._col10=RS_141._col0(Inner),Output:["_col0","_col7","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_141] PartitionCols:_col0 - Select Operator [SEL_142] (rows=1704 width=1910) + Select Operator [SEL_140] (rows=1704 width=821) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_141] (rows=1704 width=1910) + Filter Operator [FIL_139] (rows=1704 width=821) predicate:s_store_sk is not null - TableScan [TS_12] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_company_id","s_street_number","s_street_name","s_street_type","s_suite_number","s_city","s_county","s_state","s_zip"] + TableScan [TS_12] (rows=1704 width=821) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_company_id","s_street_number","s_street_name","s_street_type","s_suite_number","s_city","s_county","s_state","s_zip"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col10 - Merge Join Operator [MERGEJOIN_119] (rows=696954748 width=88) - Conds:RS_21._col7=RS_135._col0(Inner),Output:["_col0","_col7","_col10"] + Merge Join Operator [MERGEJOIN_119] (rows=11945216 width=3) + Conds:RS_21._col7=RS_138._col0(Inner),Output:["_col0","_col7","_col10"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] + SHUFFLE [RS_138] PartitionCols:_col0 - Select Operator [SEL_134] (rows=73049 width=1119) + Select Operator [SEL_137] (rows=73049 width=4) Output:["_col0"] - Filter Operator [FIL_133] (rows=73049 width=1119) + Filter Operator [FIL_136] (rows=73049 width=4) predicate:d_date_sk is not null - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk"] + TableScan [TS_9] (rows=73049 width=4) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_118] (rows=633595212 width=88) - Conds:RS_18._col1, _col2, _col3=RS_151._col1, _col2, _col4(Inner),Output:["_col0","_col7","_col10"] + Merge Join Operator [MERGEJOIN_118] (rows=11945216 width=3) + Conds:RS_18._col1, _col2, _col3=RS_135._col1, _col2, _col4(Inner),Output:["_col0","_col7","_col10"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_18] PartitionCols:_col1, _col2, _col3 - Merge Join Operator [MERGEJOIN_117] (rows=63350266 width=77) + Merge Join Operator [MERGEJOIN_117] (rows=1339446 width=8) Conds:RS_123._col0=RS_126._col0(Inner),Output:["_col0","_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_123] PartitionCols:_col0 - Select Operator [SEL_122] (rows=57591150 width=77) + Select Operator [SEL_122] (rows=53632139 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_121] (rows=57591150 width=77) + Filter Operator [FIL_121] (rows=53632139 width=15) predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) - TableScan [TS_0] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number"] + TableScan [TS_0] (rows=57591150 width=15) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_126] PartitionCols:_col0 - Select Operator [SEL_125] (rows=18262 width=1119) + Select Operator [SEL_125] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_124] (rows=18262 width=1119) + Filter Operator [FIL_124] (rows=50 width=12) predicate:((d_moy = 9) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_151] + SHUFFLE [RS_135] PartitionCols:_col1, _col2, _col4 - Select Operator [SEL_150] (rows=575995635 width=88) + Select Operator [SEL_134] (rows=501694138 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_149] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_18_store_returns_sr_customer_sk_min) AND DynamicValue(RS_18_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_18_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_18_store_returns_sr_item_sk_min) AND DynamicValue(RS_18_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_18_store_returns_sr_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_d1_d_date_sk_min) AND DynamicValue(RS_22_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_25_store_s_store_sk_min) AND DynamicValue(RS_25_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_25_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_18_store_returns_sr_ticket_number_min) AND DynamicValue(RS_18_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_18_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number"] + Filter Operator [FIL_133] (rows=501694138 width=19) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_18_store_returns_sr_customer_sk_min) AND DynamicValue(RS_18_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_18_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_18_store_returns_sr_item_sk_min) AND DynamicValue(RS_18_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_18_store_returns_sr_item_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_18_store_returns_sr_ticket_number_min) AND DynamicValue(RS_18_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_18_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_6] (rows=575995635 width=19) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_132] Group By Operator [GBY_131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_94] Group By Operator [GBY_93] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_92] (rows=63350266 width=77) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_117] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_140] - Group By Operator [GBY_139] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_138] - Group By Operator [GBY_137] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_136] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_134] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_148] - Group By Operator [GBY_147] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_146] - Group By Operator [GBY_145] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_144] (rows=1704 width=1910) + Select Operator [SEL_92] (rows=1339446 width=8) Output:["_col0"] - Please refer to the previous Select Operator [SEL_142] + Please refer to the previous Merge Join Operator [MERGEJOIN_117] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_128] Group By Operator [GBY_127] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_84] Group By Operator [GBY_83] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_82] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_82] (rows=1339446 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_117] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_130] Group By Operator [GBY_129] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_89] Group By Operator [GBY_88] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_87] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_87] (rows=1339446 width=0) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_117] diff --git a/ql/src/test/results/clientpositive/perf/tez/query51.q.out b/ql/src/test/results/clientpositive/perf/tez/query51.q.out index be123ae8c8..d9e901096c 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query51.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query51.q.out @@ -107,59 +107,59 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_113] - Limit [LIM_112] (rows=100 width=88) + Limit [LIM_112] (rows=100 width=636) Number of rows:100 - Select Operator [SEL_111] (rows=116159124 width=88) + Select Operator [SEL_111] (rows=37060934008 width=636) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_50] - Select Operator [SEL_46] (rows=116159124 width=88) + Select Operator [SEL_46] (rows=37060934008 width=636) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_58] (rows=116159124 width=88) + Filter Operator [FIL_58] (rows=37060934008 width=420) predicate:(max_window_0 > max_window_1) - PTF Operator [PTF_45] (rows=348477374 width=88) + PTF Operator [PTF_45] (rows=111182802024 width=420) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"CASE WHEN (_col4 is not null) THEN (_col4) ELSE (_col1) END ASC NULLS FIRST","partition by:":"CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END"}] - Select Operator [SEL_44] (rows=348477374 width=88) + Select Operator [SEL_44] (rows=111182802024 width=420) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:CASE WHEN (_col3 is not null) THEN (_col3) ELSE (_col0) END - Merge Join Operator [MERGEJOIN_87] (rows=348477374 width=88) + Merge Join Operator [MERGEJOIN_87] (rows=111182802024 width=420) Conds:RS_40._col0, _col1=RS_41._col0, _col1(Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0, _col1 - Select Operator [SEL_37] (rows=79201469 width=135) + Select Operator [SEL_37] (rows=15995224 width=210) Output:["_col0","_col1","_col2"] - PTF Operator [PTF_36] (rows=79201469 width=135) + PTF Operator [PTF_36] (rows=15995224 width=210) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"_col0"}] - Group By Operator [GBY_32] (rows=79201469 width=135) + Group By Operator [GBY_32] (rows=15995224 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col0 - Group By Operator [GBY_30] (rows=158402938 width=135) + Group By Operator [GBY_30] (rows=15995224 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_86] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_86] (rows=15995224 width=209) Conds:RS_108._col0=RS_92._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_92] PartitionCols:_col0 - Select Operator [SEL_89] (rows=8116 width=1119) + Select Operator [SEL_89] (rows=8116 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_88] (rows=8116 width=1119) + Filter Operator [FIL_88] (rows=8116 width=102) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_month_seq"] + TableScan [TS_3] (rows=73049 width=102) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_month_seq"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_108] PartitionCols:_col0 - Select Operator [SEL_107] (rows=144002668 width=135) + Select Operator [SEL_107] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_106] (rows=144002668 width=135) + Filter Operator [FIL_106] (rows=143966864 width=119) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_27_date_dim_d_date_sk_min) AND DynamicValue(RS_27_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_27_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_20] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_sales_price"] + TableScan [TS_20] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_sales_price"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_105] Group By Operator [GBY_104] (rows=1 width=12) @@ -168,24 +168,24 @@ Stage-0 SHUFFLE [RS_97] Group By Operator [GBY_95] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_93] (rows=8116 width=1119) + Select Operator [SEL_93] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_89] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col0, _col1 - Select Operator [SEL_17] (rows=316797606 width=88) + Select Operator [SEL_17] (rows=56414316 width=210) Output:["_col0","_col1","_col2"] - PTF Operator [PTF_16] (rows=316797606 width=88) + PTF Operator [PTF_16] (rows=56414316 width=210) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"_col0"}] - Group By Operator [GBY_12] (rows=316797606 width=88) + Group By Operator [GBY_12] (rows=56414316 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_10] (rows=633595212 width=88) + Group By Operator [GBY_10] (rows=61115434 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_85] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_85] (rows=61115434 width=164) Conds:RS_102._col0=RS_90._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_90] @@ -194,12 +194,12 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_102] PartitionCols:_col0 - Select Operator [SEL_101] (rows=575995635 width=88) + Select Operator [SEL_101] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_100] (rows=575995635 width=88) + Filter Operator [FIL_100] (rows=550076554 width=114) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_sales_price"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_sales_price"] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_99] Group By Operator [GBY_98] (rows=1 width=12) @@ -208,7 +208,7 @@ Stage-0 SHUFFLE [RS_96] Group By Operator [GBY_94] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_91] (rows=8116 width=1119) + Select Operator [SEL_91] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_89] diff --git a/ql/src/test/results/clientpositive/perf/tez/query52.q.out b/ql/src/test/results/clientpositive/perf/tez/query52.q.out index eec20fba25..10dbe45060 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query52.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query52.q.out @@ -57,55 +57,55 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_79] - Select Operator [SEL_78] (rows=100 width=88) + Select Operator [SEL_78] (rows=100 width=220) Output:["_col0","_col1","_col2","_col3"] - Limit [LIM_77] (rows=100 width=88) + Limit [LIM_77] (rows=100 width=216) Number of rows:100 - Select Operator [SEL_76] (rows=348477374 width=88) + Select Operator [SEL_76] (rows=401322 width=215) Output:["_col0","_col1","_col2"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_75] - Group By Operator [GBY_74] (rows=348477374 width=88) + Group By Operator [GBY_74] (rows=401322 width=215) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=401322 width=215) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 - Merge Join Operator [MERGEJOIN_54] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_54] (rows=2301098 width=104) Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col7","_col8"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_65] PartitionCols:_col0 - Select Operator [SEL_64] (rows=231000 width=1436) + Select Operator [SEL_64] (rows=7333 width=111) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_63] (rows=231000 width=1436) + Filter Operator [FIL_63] (rows=7333 width=111) predicate:((i_manager_id = 1) and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manager_id"] + TableScan [TS_6] (rows=462000 width=111) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manager_id"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_53] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_53] (rows=15062131 width=4) Conds:RS_73._col0=RS_57._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=18262 width=1119) + Select Operator [SEL_56] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_55] (rows=18262 width=1119) + Filter Operator [FIL_55] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 1998) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,dt,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,dt,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_73] PartitionCols:_col0 - Select Operator [SEL_72] (rows=575995635 width=88) + Select Operator [SEL_72] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_71] (rows=575995635 width=88) + Filter Operator [FIL_71] (rows=550076554 width=114) predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_dt_d_date_sk_min) AND DynamicValue(RS_10_dt_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_dt_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_62] Group By Operator [GBY_61] (rows=1 width=12) @@ -114,7 +114,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_60] Group By Operator [GBY_59] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_58] (rows=18262 width=1119) + Select Operator [SEL_58] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_56] <-Reducer 9 [BROADCAST_EDGE] vectorized @@ -125,7 +125,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_68] Group By Operator [GBY_67] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_66] (rows=231000 width=1436) + Select Operator [SEL_66] (rows=7333 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_64] diff --git a/ql/src/test/results/clientpositive/perf/tez/query53.q.out b/ql/src/test/results/clientpositive/perf/tez/query53.q.out index 267e28c9e3..e849f8acc8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query53.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query53.q.out @@ -55,9 +55,8 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) @@ -70,78 +69,78 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_116] - Limit [LIM_115] (rows=100 width=88) + File Output Operator [FS_111] + Limit [LIM_110] (rows=100 width=228) Number of rows:100 - Select Operator [SEL_114] (rows=191662559 width=88) + Select Operator [SEL_109] (rows=300 width=228) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_33] - Select Operator [SEL_30] (rows=191662559 width=88) + Select Operator [SEL_30] (rows=300 width=228) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_46] (rows=191662559 width=88) + Filter Operator [FIL_46] (rows=300 width=228) predicate:CASE WHEN ((avg_window_0 > 0)) THEN (((abs((_col2 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END - Select Operator [SEL_29] (rows=383325119 width=88) + Select Operator [SEL_29] (rows=600 width=116) Output:["avg_window_0","_col0","_col2"] - PTF Operator [PTF_28] (rows=383325119 width=88) + PTF Operator [PTF_28] (rows=600 width=116) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS FIRST","partition by:":"_col0"}] - Select Operator [SEL_25] (rows=383325119 width=88) + Select Operator [SEL_25] (rows=600 width=116) Output:["_col0","_col2"] - Group By Operator [GBY_24] (rows=383325119 width=88) + Group By Operator [GBY_24] (rows=600 width=120) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0 - Group By Operator [GBY_22] (rows=766650239 width=88) + Group By Operator [GBY_22] (rows=605 width=120) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col11 - Merge Join Operator [MERGEJOIN_84] (rows=766650239 width=88) - Conds:RS_18._col2=RS_103._col0(Inner),Output:["_col3","_col8","_col11"] + Merge Join Operator [MERGEJOIN_84] (rows=1318594 width=8) + Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col8","_col11"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] + SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_102] (rows=1704 width=1910) + Select Operator [SEL_105] (rows=1704 width=4) Output:["_col0"] - Filter Operator [FIL_101] (rows=1704 width=1910) + Filter Operator [FIL_104] (rows=1704 width=4) predicate:s_store_sk is not null - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"] + TableScan [TS_9] (rows=1704 width=4) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_83] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_83] (rows=1318594 width=8) Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col8","_col11"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=73049 width=1119) + Select Operator [SEL_94] (rows=317 width=12) Output:["_col0","_col2"] - Filter Operator [FIL_93] (rows=73049 width=1119) + Filter Operator [FIL_93] (rows=317 width=12) predicate:((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq","d_qoy"] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq","d_qoy"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_82] (rows=633595212 width=88) - Conds:RS_111._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col8"] + Merge Join Operator [MERGEJOIN_82] (rows=7595537 width=4) + Conds:RS_103._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col8"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=462000 width=1436) + Select Operator [SEL_86] (rows=694 width=289) Output:["_col0","_col4"] - Filter Operator [FIL_85] (rows=462000 width=1436) + Filter Operator [FIL_85] (rows=694 width=289) predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'reference', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_manufact_id"] + TableScan [TS_3] (rows=462000 width=289) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category","i_manufact_id"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] + SHUFFLE [RS_103] PartitionCols:_col1 - Select Operator [SEL_110] (rows=575995635 width=88) + Select Operator [SEL_102] (rows=525329897 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_109] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + Filter Operator [FIL_101] (rows=525329897 width=118) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_100] Group By Operator [GBY_99] (rows=1 width=12) @@ -150,20 +149,9 @@ Stage-0 SHUFFLE [RS_98] Group By Operator [GBY_97] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_96] (rows=73049 width=1119) + Select Operator [SEL_96] (rows=317 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_94] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_108] - Group By Operator [GBY_107] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_104] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_92] Group By Operator [GBY_91] (rows=1 width=12) @@ -172,7 +160,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_90] Group By Operator [GBY_89] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_88] (rows=462000 width=1436) + Select Operator [SEL_88] (rows=694 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_86] diff --git a/ql/src/test/results/clientpositive/perf/tez/query54.q.out b/ql/src/test/results/clientpositive/perf/tez/query54.q.out index c889ce153f..cb9b4de3fe 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query54.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query54.q.out @@ -115,13 +115,13 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 12 (BROADCAST_EDGE) -Map 17 <- Reducer 25 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE), Union 18 (CONTAINS) +Map 1 <- Reducer 15 (BROADCAST_EDGE) +Map 17 <- Reducer 25 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Union 18 (CONTAINS) Map 23 <- Reducer 25 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Union 18 (CONTAINS) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE) Reducer 19 <- Map 24 (SIMPLE_EDGE), Union 18 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Reducer 20 <- Map 26 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) @@ -129,17 +129,16 @@ Reducer 21 <- Map 28 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) Reducer 22 <- Reducer 21 (SIMPLE_EDGE) Reducer 25 <- Map 24 (CUSTOM_SIMPLE_EDGE) Reducer 27 <- Map 26 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 31 <- Map 30 (SIMPLE_EDGE) -Reducer 32 <- Reducer 31 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 30 (SIMPLE_EDGE) -Reducer 34 <- Reducer 33 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Map 30 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 32 (CUSTOM_SIMPLE_EDGE) -Reducer 5 <- Reducer 31 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Reducer 34 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 35 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 30 <- Map 29 (SIMPLE_EDGE) +Reducer 31 <- Reducer 30 (CUSTOM_SIMPLE_EDGE) +Reducer 32 <- Map 29 (SIMPLE_EDGE) +Reducer 33 <- Reducer 32 (CUSTOM_SIMPLE_EDGE) +Reducer 34 <- Map 29 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE), Reducer 31 (CUSTOM_SIMPLE_EDGE) +Reducer 5 <- Reducer 30 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Reducer 33 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Reducer 34 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) @@ -148,288 +147,277 @@ Stage-0 limit:100 Stage-1 Reducer 10 vectorized - File Output Operator [FS_360] - Limit [LIM_359] (rows=100 width=158) + File Output Operator [FS_354] + Limit [LIM_353] (rows=1 width=16) Number of rows:100 - Select Operator [SEL_358] (rows=1614130953450400 width=158) + Select Operator [SEL_352] (rows=1 width=16) Output:["_col0","_col1","_col2"] <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_357] - Select Operator [SEL_356] (rows=1614130953450400 width=158) + SHUFFLE [RS_351] + Select Operator [SEL_350] (rows=1 width=16) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_355] (rows=1614130953450400 width=158) + Group By Operator [GBY_349] (rows=1 width=12) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_354] + SHUFFLE [RS_348] PartitionCols:_col0 - Group By Operator [GBY_353] (rows=3228261906900801 width=158) + Group By Operator [GBY_347] (rows=1 width=12) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Select Operator [SEL_352] (rows=3228261906900801 width=158) + Select Operator [SEL_346] (rows=1 width=116) Output:["_col0"] - Group By Operator [GBY_351] (rows=3228261906900801 width=158) + Group By Operator [GBY_345] (rows=1 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_119] PartitionCols:_col0 - Group By Operator [GBY_118] (rows=6456523813801603 width=158) + Group By Operator [GBY_118] (rows=312 width=116) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_117] (rows=6456523813801603 width=158) + Select Operator [SEL_117] (rows=624257222 width=127) Output:["_col0","_col1"] - Filter Operator [FIL_116] (rows=6456523813801603 width=158) + Filter Operator [FIL_116] (rows=624257222 width=127) predicate:_col2 BETWEEN _col3 AND _col4 - Merge Join Operator [MERGEJOIN_273] (rows=58108714324214428 width=158) + Merge Join Operator [MERGEJOIN_273] (rows=5618315000 width=127) Conds:(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_350] - Group By Operator [GBY_349] (rows=9131 width=1119) + <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_344] + Group By Operator [GBY_343] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_331] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_325] PartitionCols:_col0 - Group By Operator [GBY_328] (rows=18262 width=1119) + Group By Operator [GBY_322] (rows=25 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_325] (rows=18262 width=1119) + Select Operator [SEL_319] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_322] (rows=18262 width=1119) + Filter Operator [FIL_316] (rows=50 width=12) predicate:((d_moy = 3) and (d_year = 1999)) - TableScan [TS_50] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] + TableScan [TS_50] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_year","d_moy"] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_113] - Select Operator [SEL_104] (rows=6363893803988 width=1226) + Select Operator [SEL_104] (rows=224732600 width=119) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_272] (rows=6363893803988 width=1226) + Merge Join Operator [MERGEJOIN_272] (rows=224732600 width=119) Conds:(Inner),Output:["_col0","_col4","_col11","_col13"] - <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_348] - Select Operator [SEL_347] (rows=1 width=8) - Filter Operator [FIL_346] (rows=1 width=8) + <-Reducer 33 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_342] + Select Operator [SEL_341] (rows=1 width=8) + Filter Operator [FIL_340] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_345] (rows=1 width=8) + Group By Operator [GBY_339] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 33 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_344] - Group By Operator [GBY_343] (rows=1 width=8) + <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_338] + Group By Operator [GBY_337] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_342] (rows=9131 width=1119) - Group By Operator [GBY_341] (rows=9131 width=1119) + Select Operator [SEL_336] (rows=25 width=4) + Group By Operator [GBY_335] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_330] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_324] PartitionCols:_col0 - Group By Operator [GBY_327] (rows=18262 width=1119) + Group By Operator [GBY_321] (rows=25 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_324] (rows=18262 width=1119) + Select Operator [SEL_318] (rows=50 width=12) Output:["_col0"] - Please refer to the previous Filter Operator [FIL_322] + Please refer to the previous Filter Operator [FIL_316] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_101] - Select Operator [SEL_85] (rows=6363893803988 width=1217) + Select Operator [SEL_85] (rows=224732600 width=119) Output:["_col0","_col4","_col11","_col13"] - Merge Join Operator [MERGEJOIN_271] (rows=6363893803988 width=1217) + Merge Join Operator [MERGEJOIN_271] (rows=224732600 width=119) Conds:(Left Outer),Output:["_col2","_col4","_col10","_col13"] - <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_334] - Group By Operator [GBY_332] (rows=9131 width=1119) + <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_328] + Group By Operator [GBY_326] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_329] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_326] (rows=18262 width=1119) + Group By Operator [GBY_320] (rows=25 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_323] (rows=18262 width=1119) + Select Operator [SEL_317] (rows=50 width=12) Output:["_col0"] - Please refer to the previous Filter Operator [FIL_322] + Please refer to the previous Filter Operator [FIL_316] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_82] - Merge Join Operator [MERGEJOIN_270] (rows=696954748 width=97) + Merge Join Operator [MERGEJOIN_270] (rows=8989304 width=8) Conds:(Inner),Output:["_col2","_col4","_col10"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_79] - Merge Join Operator [MERGEJOIN_269] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_269] (rows=8989304 width=8) Conds:RS_76._col1=RS_77._col5(Inner),Output:["_col2","_col4","_col10"] - <-Reducer 15 [SIMPLE_EDGE] + <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_268] (rows=316240138 width=135) - Conds:RS_46._col0=RS_321._col1(Inner),Output:["_col5"] - <-Reducer 14 [SIMPLE_EDGE] + Merge Join Operator [MERGEJOIN_268] (rows=55046 width=4) + Conds:RS_46._col0=RS_307._col1(Inner),Output:["_col5"] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_46] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_264] (rows=44000000 width=1014) - Conds:RS_297._col1, _col2=RS_300._col0, _col1(Inner),Output:["_col0"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_297] + Merge Join Operator [MERGEJOIN_264] (rows=39720279 width=4) + Conds:RS_286._col1, _col2=RS_289._col0, _col1(Inner),Output:["_col0"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_286] PartitionCols:_col1, _col2 - Select Operator [SEL_296] (rows=40000000 width=1014) + Select Operator [SEL_285] (rows=40000000 width=188) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_295] (rows=40000000 width=1014) + Filter Operator [FIL_284] (rows=40000000 width=188) predicate:(ca_address_sk is not null and ca_county is not null and ca_state is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_state"] + TableScan [TS_6] (rows=40000000 width=188) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state"] <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_300] + SHUFFLE [RS_289] PartitionCols:_col0, _col1 - Select Operator [SEL_299] (rows=1704 width=1910) + Select Operator [SEL_288] (rows=1704 width=184) Output:["_col0","_col1"] - Filter Operator [FIL_298] (rows=1704 width=1910) + Filter Operator [FIL_287] (rows=1704 width=184) predicate:(s_county is not null and s_state is not null) - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_county","s_state"] + TableScan [TS_9] (rows=1704 width=184) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_county","s_state"] <-Reducer 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] + SHUFFLE [RS_307] PartitionCols:_col1 - Select Operator [SEL_320] (rows=287491029 width=135) + Select Operator [SEL_306] (rows=55046 width=8) Output:["_col0","_col1"] - Group By Operator [GBY_319] (rows=287491029 width=135) + Group By Operator [GBY_305] (rows=55046 width=8) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col0, _col1 - Group By Operator [GBY_39] (rows=574982058 width=135) + Group By Operator [GBY_39] (rows=55046 width=8) Output:["_col0","_col1"],keys:_col10, _col9 - Merge Join Operator [MERGEJOIN_267] (rows=574982058 width=135) - Conds:RS_35._col1=RS_315._col0(Inner),Output:["_col9","_col10"] + Merge Join Operator [MERGEJOIN_267] (rows=110092 width=8) + Conds:RS_35._col1=RS_304._col0(Inner),Output:["_col9","_col10"] <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_315] + SHUFFLE [RS_304] PartitionCols:_col0 - Select Operator [SEL_314] (rows=80000000 width=860) + Select Operator [SEL_303] (rows=80000000 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_313] (rows=80000000 width=860) + Filter Operator [FIL_302] (rows=80000000 width=8) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_26] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] + TableScan [TS_26] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_266] (rows=522710951 width=135) - Conds:RS_32._col2=RS_309._col0(Inner),Output:["_col1"] + Merge Join Operator [MERGEJOIN_266] (rows=110092 width=0) + Conds:RS_32._col2=RS_298._col0(Inner),Output:["_col1"] <-Map 26 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_309] + PARTITION_ONLY_SHUFFLE [RS_298] PartitionCols:_col0 - Select Operator [SEL_308] (rows=115500 width=1436) + Select Operator [SEL_297] (rows=453 width=190) Output:["_col0"] - Filter Operator [FIL_307] (rows=115500 width=1436) + Filter Operator [FIL_296] (rows=453 width=186) predicate:((i_category = 'Jewelry') and (i_class = 'consignment') and i_item_sk is not null) - TableScan [TS_23] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_class","i_category"] + TableScan [TS_23] (rows=462000 width=186) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_class","i_category"] <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_265] (rows=475191764 width=135) - Conds:Union 18._col0=RS_303._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_265] (rows=11665117 width=7) + Conds:Union 18._col0=RS_292._col0(Inner),Output:["_col1","_col2"] <-Map 24 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_303] + PARTITION_ONLY_SHUFFLE [RS_292] PartitionCols:_col0 - Select Operator [SEL_302] (rows=18262 width=1119) + Select Operator [SEL_291] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_301] (rows=18262 width=1119) + Filter Operator [FIL_290] (rows=50 width=12) predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_20] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_20] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Union 18 [SIMPLE_EDGE] <-Map 17 [CONTAINS] vectorized - Reduce Output Operator [RS_371] + Reduce Output Operator [RS_363] PartitionCols:_col0 - Select Operator [SEL_370] (rows=287989836 width=135) + Select Operator [SEL_362] (rows=285117831 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_369] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_36_customer_c_customer_sk_min) AND DynamicValue(RS_36_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_36_customer_c_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_33_item_i_item_sk_min) AND DynamicValue(RS_33_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_33_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_274] (rows=287989836 width=135) + Filter Operator [FIL_361] (rows=285117831 width=11) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_33_item_i_item_sk_min) AND DynamicValue(RS_33_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_33_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_274] (rows=287989836 width=11) Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk"] <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_362] - Group By Operator [GBY_361] (rows=1 width=12) + BROADCAST [RS_356] + Group By Operator [GBY_355] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_306] - Group By Operator [GBY_305] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_295] + Group By Operator [GBY_294] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_304] (rows=18262 width=1119) + Select Operator [SEL_293] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_302] + Please refer to the previous Select Operator [SEL_291] <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_365] - Group By Operator [GBY_364] (rows=1 width=12) + BROADCAST [RS_359] + Group By Operator [GBY_358] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_312] - Group By Operator [GBY_311] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_301] + Group By Operator [GBY_300] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_310] (rows=115500 width=1436) + Select Operator [SEL_299] (rows=453 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_308] - <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_368] - Group By Operator [GBY_367] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_318] - Group By Operator [GBY_317] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_316] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_314] + Please refer to the previous Select Operator [SEL_297] <-Map 23 [CONTAINS] vectorized - Reduce Output Operator [RS_374] + Reduce Output Operator [RS_366] PartitionCols:_col0 - Select Operator [SEL_373] (rows=144002668 width=135) + Select Operator [SEL_365] (rows=143930993 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_372] (rows=144002668 width=135) + Filter Operator [FIL_364] (rows=143930993 width=11) predicate:((ws_item_sk BETWEEN DynamicValue(RS_33_item_i_item_sk_min) AND DynamicValue(RS_33_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_33_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_279] (rows=144002668 width=135) + TableScan [TS_279] (rows=144002668 width=11) Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk"] <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_363] - Please refer to the previous Group By Operator [GBY_361] + BROADCAST [RS_357] + Please refer to the previous Group By Operator [GBY_355] <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_366] - Please refer to the previous Group By Operator [GBY_364] + BROADCAST [RS_360] + Please refer to the previous Group By Operator [GBY_358] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_76] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_263] (rows=633595212 width=88) - Conds:RS_294._col0=RS_286._col0(Inner),Output:["_col1","_col2","_col4"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_286] - PartitionCols:_col0 - Select Operator [SEL_285] (rows=73049 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_284] (rows=73049 width=1119) - predicate:d_date_sk is not null - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] + Merge Join Operator [MERGEJOIN_263] (rows=525327388 width=114) + Conds:RS_312._col0=RS_315._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_294] + SHUFFLE [RS_312] PartitionCols:_col0 - Select Operator [SEL_293] (rows=575995635 width=88) + Select Operator [SEL_311] (rows=525327388 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_292] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_74_date_dim_d_date_sk_min) AND DynamicValue(RS_74_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_74_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_sales_price"] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_291] - Group By Operator [GBY_290] (rows=1 width=12) + Filter Operator [FIL_310] (rows=525327388 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_77_customer_c_customer_sk_min) AND DynamicValue(RS_77_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_77_customer_c_customer_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_sales_price"] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_309] + Group By Operator [GBY_308] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_289] - Group By Operator [GBY_288] (rows=1 width=12) + <-Reducer 14 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_183] + Group By Operator [GBY_182] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_287] (rows=73049 width=1119) + Select Operator [SEL_181] (rows=55046 width=8) Output:["_col0"] - Please refer to the previous Select Operator [SEL_285] - <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_340] - Select Operator [SEL_339] (rows=1 width=8) - Filter Operator [FIL_338] (rows=1 width=8) + Please refer to the previous Merge Join Operator [MERGEJOIN_268] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_315] + PartitionCols:_col0 + Select Operator [SEL_314] (rows=73049 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_313] (rows=73049 width=8) + predicate:d_date_sk is not null + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_334] + Select Operator [SEL_333] (rows=1 width=8) + Filter Operator [FIL_332] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_337] (rows=1 width=8) + Group By Operator [GBY_331] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_336] - Group By Operator [GBY_335] (rows=1 width=8) + <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_330] + Group By Operator [GBY_329] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_333] (rows=9131 width=1119) - Please refer to the previous Group By Operator [GBY_332] + Select Operator [SEL_327] (rows=25 width=4) + Please refer to the previous Group By Operator [GBY_326] diff --git a/ql/src/test/results/clientpositive/perf/tez/query55.q.out b/ql/src/test/results/clientpositive/perf/tez/query55.q.out index 8693539c0e..2e8bcfb53d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query55.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query55.q.out @@ -41,55 +41,55 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_79] - Limit [LIM_78] (rows=100 width=88) + Limit [LIM_78] (rows=100 width=220) Number of rows:100 - Select Operator [SEL_77] (rows=348477374 width=88) + Select Operator [SEL_77] (rows=401322 width=219) Output:["_col0","_col1","_col2"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_76] - Select Operator [SEL_75] (rows=348477374 width=88) + Select Operator [SEL_75] (rows=401322 width=219) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_74] (rows=348477374 width=88) + Group By Operator [GBY_74] (rows=401322 width=215) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=401322 width=215) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)"],keys:_col7, _col8 - Merge Join Operator [MERGEJOIN_54] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_54] (rows=2301098 width=104) Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col7","_col8"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_65] PartitionCols:_col0 - Select Operator [SEL_64] (rows=231000 width=1436) + Select Operator [SEL_64] (rows=7333 width=111) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_63] (rows=231000 width=1436) + Filter Operator [FIL_63] (rows=7333 width=111) predicate:((i_manager_id = 36) and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manager_id"] + TableScan [TS_6] (rows=462000 width=111) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manager_id"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_53] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_53] (rows=15062131 width=4) Conds:RS_73._col0=RS_57._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_57] PartitionCols:_col0 - Select Operator [SEL_56] (rows=18262 width=1119) + Select Operator [SEL_56] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_55] (rows=18262 width=1119) + Filter Operator [FIL_55] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_73] PartitionCols:_col0 - Select Operator [SEL_72] (rows=575995635 width=88) + Select Operator [SEL_72] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_71] (rows=575995635 width=88) + Filter Operator [FIL_71] (rows=550076554 width=114) predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_62] Group By Operator [GBY_61] (rows=1 width=12) @@ -98,7 +98,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_60] Group By Operator [GBY_59] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_58] (rows=18262 width=1119) + Select Operator [SEL_58] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_56] <-Reducer 9 [BROADCAST_EDGE] vectorized @@ -109,7 +109,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_68] Group By Operator [GBY_67] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_66] (rows=231000 width=1436) + Select Operator [SEL_66] (rows=7333 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_64] diff --git a/ql/src/test/results/clientpositive/perf/tez/query56.q.out b/ql/src/test/results/clientpositive/perf/tez/query56.q.out index 40f39b556e..d0958c0127 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query56.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query56.q.out @@ -170,98 +170,98 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_370] - Limit [LIM_369] (rows=100 width=108) + Limit [LIM_369] (rows=100 width=212) Number of rows:100 - Select Operator [SEL_368] (rows=335408073 width=108) + Select Operator [SEL_368] (rows=430 width=212) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_367] - Group By Operator [GBY_366] (rows=335408073 width=108) + Group By Operator [GBY_366] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] <-Reducer 10 [CONTAINS] vectorized Reduce Output Operator [RS_382] PartitionCols:_col0 - Group By Operator [GBY_381] (rows=670816147 width=108) + Group By Operator [GBY_381] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_380] (rows=191657247 width=135) + Group By Operator [GBY_380] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_71] PartitionCols:_col0 - Group By Operator [GBY_70] (rows=383314495 width=135) + Group By Operator [GBY_70] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_303] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_303] (rows=373066 width=100) Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_293] (rows=508200 width=1436) + Merge Join Operator [MERGEJOIN_293] (rows=17170 width=104) Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_319] PartitionCols:_col1 - Select Operator [SEL_318] (rows=462000 width=1436) + Select Operator [SEL_318] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_317] (rows=462000 width=1436) + Filter Operator [FIL_317] (rows=462000 width=104) predicate:(i_item_id is not null and i_item_sk is not null) - TableScan [TS_0] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + TableScan [TS_0] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_325] PartitionCols:_col0 - Group By Operator [GBY_324] (rows=231000 width=1436) + Group By Operator [GBY_324] (rows=11550 width=100) Output:["_col0"],keys:KEY._col0 <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_322] (rows=462000 width=1436) + Group By Operator [GBY_322] (rows=11550 width=100) Output:["_col0"],keys:i_item_id - Select Operator [SEL_321] (rows=462000 width=1436) + Select Operator [SEL_321] (rows=23100 width=189) Output:["i_item_id"] - Filter Operator [FIL_320] (rows=462000 width=1436) + Filter Operator [FIL_320] (rows=23100 width=189) predicate:((i_color) IN ('orchid', 'chiffon', 'lace') and i_item_id is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_id","i_color"] + TableScan [TS_3] (rows=462000 width=189) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_color"] <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col4 - Select Operator [SEL_62] (rows=348467716 width=135) + Select Operator [SEL_62] (rows=1550375 width=13) Output:["_col4","_col5"] - Merge Join Operator [MERGEJOIN_298] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_298] (rows=1550375 width=13) Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_346] PartitionCols:_col0 - Select Operator [SEL_343] (rows=20000000 width=1014) + Select Operator [SEL_343] (rows=8000000 width=116) Output:["_col0"] - Filter Operator [FIL_342] (rows=20000000 width=1014) + Filter Operator [FIL_342] (rows=8000000 width=112) predicate:((ca_gmt_offset = -8) and ca_address_sk is not null) - TableScan [TS_16] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"] + TableScan [TS_16] (rows=40000000 width=112) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_297] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_297] (rows=7751872 width=98) Conds:RS_379._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_330] PartitionCols:_col0 - Select Operator [SEL_327] (rows=18262 width=1119) + Select Operator [SEL_327] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_326] (rows=18262 width=1119) + Filter Operator [FIL_326] (rows=50 width=12) predicate:((d_moy = 1) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_13] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_13] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 32 [SIMPLE_EDGE] vectorized SHUFFLE [RS_379] PartitionCols:_col0 - Select Operator [SEL_378] (rows=287989836 width=135) + Select Operator [SEL_378] (rows=285117733 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_377] (rows=287989836 width=135) + Filter Operator [FIL_377] (rows=285117733 width=123) predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_66_item_i_item_sk_min) AND DynamicValue(RS_66_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_66_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_47] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] + TableScan [TS_47] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_376] Group By Operator [GBY_375] (rows=1 width=12) @@ -270,7 +270,7 @@ Stage-0 SHUFFLE [RS_240] Group By Operator [GBY_239] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_238] (rows=508200 width=1436) + Select Operator [SEL_238] (rows=17170 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 24 [BROADCAST_EDGE] vectorized @@ -281,33 +281,33 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_338] Group By Operator [GBY_335] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_331] (rows=18262 width=1119) + Select Operator [SEL_331] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_327] <-Reducer 30 [BROADCAST_EDGE] vectorized BROADCAST [RS_374] Group By Operator [GBY_373] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_354] Group By Operator [GBY_351] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_347] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_347] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_343] <-Reducer 13 [CONTAINS] vectorized Reduce Output Operator [RS_394] PartitionCols:_col0 - Group By Operator [GBY_393] (rows=670816147 width=108) + Group By Operator [GBY_393] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_392] (rows=95833781 width=135) + Group By Operator [GBY_392] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col0 - Group By Operator [GBY_108] (rows=191667562 width=135) + Group By Operator [GBY_108] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_304] (rows=189670 width=190) Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] @@ -316,9 +316,9 @@ Stage-0 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_105] PartitionCols:_col3 - Select Operator [SEL_100] (rows=174243235 width=135) + Select Operator [SEL_100] (rows=788222 width=110) Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_301] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_301] (rows=788222 width=110) Conds:RS_97._col2=RS_348._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_348] @@ -327,7 +327,7 @@ Stage-0 <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_300] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_300] (rows=3941109 width=118) Conds:RS_391._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_332] @@ -336,12 +336,12 @@ Stage-0 <-Map 33 [SIMPLE_EDGE] vectorized SHUFFLE [RS_391] PartitionCols:_col0 - Select Operator [SEL_390] (rows=144002668 width=135) + Select Operator [SEL_390] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_389] (rows=144002668 width=135) + Filter Operator [FIL_389] (rows=143931246 width=123) predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_85] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] + TableScan [TS_85] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_388] Group By Operator [GBY_387] (rows=1 width=12) @@ -350,7 +350,7 @@ Stage-0 SHUFFLE [RS_280] Group By Operator [GBY_279] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_278] (rows=508200 width=1436) + Select Operator [SEL_278] (rows=17170 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 27 [BROADCAST_EDGE] vectorized @@ -361,33 +361,33 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_339] Group By Operator [GBY_336] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_333] (rows=18262 width=1119) + Select Operator [SEL_333] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_327] <-Reducer 31 [BROADCAST_EDGE] vectorized BROADCAST [RS_386] Group By Operator [GBY_385] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_355] Group By Operator [GBY_352] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_349] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_349] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_343] <-Reducer 4 [CONTAINS] vectorized Reduce Output Operator [RS_365] PartitionCols:_col0 - Group By Operator [GBY_364] (rows=670816147 width=108) + Group By Operator [GBY_364] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_363] (rows=383325119 width=88) + Group By Operator [GBY_363] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Group By Operator [GBY_33] (rows=766650239 width=88) + Group By Operator [GBY_33] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_302] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_302] (rows=692265 width=100) Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] @@ -396,9 +396,9 @@ Stage-0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col3 - Select Operator [SEL_25] (rows=696954748 width=88) + Select Operator [SEL_25] (rows=2876890 width=4) Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_295] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_295] (rows=2876890 width=4) Conds:RS_22._col2=RS_344._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_344] @@ -407,7 +407,7 @@ Stage-0 <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_294] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_294] (rows=14384447 width=4) Conds:RS_362._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_328] @@ -416,12 +416,12 @@ Stage-0 <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_362] PartitionCols:_col0 - Select Operator [SEL_361] (rows=575995635 width=88) + Select Operator [SEL_361] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_360] (rows=575995635 width=88) + Filter Operator [FIL_360] (rows=525327191 width=118) predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_10] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] + TableScan [TS_10] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 21 [BROADCAST_EDGE] vectorized BROADCAST [RS_341] Group By Operator [GBY_340] (rows=1 width=12) @@ -430,18 +430,18 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_337] Group By Operator [GBY_334] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_329] (rows=18262 width=1119) + Select Operator [SEL_329] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_327] <-Reducer 29 [BROADCAST_EDGE] vectorized BROADCAST [RS_357] Group By Operator [GBY_356] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_353] Group By Operator [GBY_350] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_345] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_345] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_343] <-Reducer 8 [BROADCAST_EDGE] vectorized @@ -452,7 +452,7 @@ Stage-0 SHUFFLE [RS_200] Group By Operator [GBY_199] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_198] (rows=508200 width=1436) + Select Operator [SEL_198] (rows=17170 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_293] diff --git a/ql/src/test/results/clientpositive/perf/tez/query57.q.out b/ql/src/test/results/clientpositive/perf/tez/query57.q.out index 42cbbdc2a4..0e1c237e45 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query57.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query57.q.out @@ -95,15 +95,13 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Map 1 <- Reducer 13 (BROADCAST_EDGE) Reducer 10 <- Reducer 5 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) Reducer 3 <- Map 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 11 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) @@ -115,99 +113,99 @@ Stage-0 limit:-1 Stage-1 Reducer 8 vectorized - File Output Operator [FS_320] - Limit [LIM_319] (rows=100 width=135) + File Output Operator [FS_310] + Limit [LIM_309] (rows=100 width=758) Number of rows:100 - Select Operator [SEL_318] (rows=421645952 width=135) + Select Operator [SEL_308] (rows=173494 width=758) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_108] - Select Operator [SEL_107] (rows=421645952 width=135) + Select Operator [SEL_107] (rows=173494 width=758) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_279] (rows=421645952 width=135) + Merge Join Operator [MERGEJOIN_279] (rows=173494 width=646) Conds:RS_103._col0, _col1, _col2, (_col4 + 1)=RS_104._col0, _col1, _col2, _col7(Inner),RS_104._col0, _col1, _col2, _col7=RS_105._col0, _col1, _col2, (_col4 - 1)(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col10","_col11","_col16"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0, _col1, _col2, _col7 - Select Operator [SEL_67] (rows=15971437 width=135) + Select Operator [SEL_67] (rows=173494 width=524) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_169] (rows=15971437 width=135) + Filter Operator [FIL_169] (rows=173494 width=524) predicate:CASE WHEN ((_col0 > 0)) THEN (((abs((_col6 - _col0)) / _col0) > 0.1)) ELSE (null) END - Select Operator [SEL_66] (rows=31942874 width=135) + Select Operator [SEL_66] (rows=346989 width=520) Output:["rank_window_1","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_170] (rows=31942874 width=135) + Filter Operator [FIL_170] (rows=346989 width=520) predicate:((_col0 > 0) and (_col1 = 2000) and rank_window_1 is not null) - PTF Operator [PTF_65] (rows=191657247 width=135) + PTF Operator [PTF_65] (rows=116588247 width=520) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST, _col2 ASC NULLS FIRST","partition by:":"_col5, _col4, _col3"}] - Select Operator [SEL_64] (rows=191657247 width=135) + Select Operator [SEL_64] (rows=116588247 width=520) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_316] + SHUFFLE [RS_306] PartitionCols:_col4, _col3, _col2 - Select Operator [SEL_315] (rows=191657247 width=135) + Select Operator [SEL_305] (rows=116588247 width=408) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5"] - PTF Operator [PTF_314] (rows=191657247 width=135) + PTF Operator [PTF_304] (rows=116588247 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col4 ASC NULLS FIRST, _col3 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col0 ASC NULLS FIRST","partition by:":"_col4, _col3, _col2, _col0"}] - Select Operator [SEL_313] (rows=191657247 width=135) + Select Operator [SEL_303] (rows=116588247 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_310] + SHUFFLE [RS_300] PartitionCols:_col4, _col3, _col2, _col0 - Group By Operator [GBY_307] (rows=191657247 width=135) + Group By Operator [GBY_297] (rows=116588247 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_92] (rows=383314495 width=135) + Group By Operator [GBY_92] (rows=116588247 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col8, _col10, _col11 - Merge Join Operator [MERGEJOIN_278] (rows=383314495 width=135) - Conds:RS_88._col2=RS_298._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col10","_col11"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_298] + Merge Join Operator [MERGEJOIN_278] (rows=116588247 width=406) + Conds:RS_88._col2=RS_296._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col10","_col11"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_296] PartitionCols:_col0 - Select Operator [SEL_297] (rows=462000 width=1436) + Select Operator [SEL_295] (rows=462000 width=194) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_296] (rows=462000 width=1436) + Filter Operator [FIL_294] (rows=462000 width=194) predicate:(i_brand is not null and i_category is not null and i_item_sk is not null) - TableScan [TS_79] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_category"] + TableScan [TS_79] (rows=462000 width=194) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_category"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_88] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_277] (rows=348467716 width=135) - Conds:RS_85._col1=RS_290._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8"] + Merge Join Operator [MERGEJOIN_277] (rows=116588247 width=220) + Conds:RS_85._col1=RS_293._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_290] + SHUFFLE [RS_293] PartitionCols:_col0 - Select Operator [SEL_289] (rows=60 width=2045) + Select Operator [SEL_292] (rows=60 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_288] (rows=60 width=2045) + Filter Operator [FIL_291] (rows=60 width=102) predicate:(cc_call_center_sk is not null and cc_name is not null) - TableScan [TS_76] (rows=60 width=2045) - default@call_center,call_center,Tbl:COMPLETE,Col:NONE,Output:["cc_call_center_sk","cc_name"] + TableScan [TS_76] (rows=60 width=102) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_85] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_276] (rows=316788826 width=135) - Conds:RS_306._col0=RS_282._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] + Merge Join Operator [MERGEJOIN_276] (rows=116588247 width=126) + Conds:RS_290._col0=RS_282._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_282] PartitionCols:_col0 - Select Operator [SEL_281] (rows=73048 width=1119) + Select Operator [SEL_281] (rows=752 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_280] (rows=73048 width=1119) + Filter Operator [FIL_280] (rows=752 width=12) predicate:(((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) - TableScan [TS_73] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_73] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_306] + SHUFFLE [RS_290] PartitionCols:_col0 - Select Operator [SEL_305] (rows=287989836 width=135) + Select Operator [SEL_289] (rows=285117980 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_304] (rows=287989836 width=135) - predicate:((cs_call_center_sk BETWEEN DynamicValue(RS_86_call_center_cc_call_center_sk_min) AND DynamicValue(RS_86_call_center_cc_call_center_sk_max) and in_bloom_filter(cs_call_center_sk, DynamicValue(RS_86_call_center_cc_call_center_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_89_item_i_item_sk_min) AND DynamicValue(RS_89_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_89_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_83_date_dim_d_date_sk_min) AND DynamicValue(RS_83_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_83_date_dim_d_date_sk_bloom_filter))) and cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_70] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_call_center_sk","cs_item_sk","cs_sales_price"] + Filter Operator [FIL_288] (rows=285117980 width=123) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_83_date_dim_d_date_sk_min) AND DynamicValue(RS_83_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_83_date_dim_d_date_sk_bloom_filter))) and cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_70] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_call_center_sk","cs_item_sk","cs_sales_price"] <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_287] Group By Operator [GBY_286] (rows=1 width=12) @@ -216,59 +214,37 @@ Stage-0 SHUFFLE [RS_285] Group By Operator [GBY_284] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_283] (rows=73048 width=1119) + Select Operator [SEL_283] (rows=752 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_281] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_295] - Group By Operator [GBY_294] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_293] - Group By Operator [GBY_292] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_291] (rows=60 width=2045) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_289] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_303] - Group By Operator [GBY_302] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_301] - Group By Operator [GBY_300] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_299] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_297] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_105] PartitionCols:_col0, _col1, _col2, (_col4 - 1) - Select Operator [SEL_99] (rows=191657247 width=135) + Select Operator [SEL_99] (rows=116588247 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_175] (rows=191657247 width=135) + Filter Operator [FIL_175] (rows=116588247 width=408) predicate:rank_window_0 is not null - PTF Operator [PTF_98] (rows=191657247 width=135) + PTF Operator [PTF_98] (rows=116588247 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST","partition by:":"_col4, _col3, _col2"}] - Select Operator [SEL_97] (rows=191657247 width=135) + Select Operator [SEL_97] (rows=116588247 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_308] + SHUFFLE [RS_298] PartitionCols:_col4, _col3, _col2 - Please refer to the previous Group By Operator [GBY_307] + Please refer to the previous Group By Operator [GBY_297] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_103] PartitionCols:_col0, _col1, _col2, (_col4 + 1) - Select Operator [SEL_29] (rows=191657247 width=135) + Select Operator [SEL_29] (rows=116588247 width=404) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_164] (rows=191657247 width=135) + Filter Operator [FIL_164] (rows=116588247 width=408) predicate:rank_window_0 is not null - PTF Operator [PTF_28] (rows=191657247 width=135) + PTF Operator [PTF_28] (rows=116588247 width=408) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST","partition by:":"_col4, _col3, _col2"}] - Select Operator [SEL_27] (rows=191657247 width=135) + Select Operator [SEL_27] (rows=116588247 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_309] + SHUFFLE [RS_299] PartitionCols:_col4, _col3, _col2 - Please refer to the previous Group By Operator [GBY_307] + Please refer to the previous Group By Operator [GBY_297] diff --git a/ql/src/test/results/clientpositive/perf/tez/query58.q.out b/ql/src/test/results/clientpositive/perf/tez/query58.q.out index b3f9bbb645..43793ea981 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query58.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query58.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[403][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 24' is a cross product +Warning: Shuffle Join MERGEJOIN[403][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 21' is a cross product PREHOOK: query: explain with ss_items as (select i_item_id item_id @@ -130,280 +130,244 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 19 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 28 <- Reducer 12 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) -Map 29 <- Reducer 16 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE) -Reducer 10 <- Reducer 18 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 29 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (SIMPLE_EDGE) -Reducer 16 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Reducer 26 (ONE_TO_ONE_EDGE) -Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 16 (BROADCAST_EDGE) +Map 25 <- Reducer 17 (BROADCAST_EDGE) +Map 26 <- Reducer 18 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 26 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 13 <- Reducer 12 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (SIMPLE_EDGE), Reducer 23 (ONE_TO_ONE_EDGE) +Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 20 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) -Reducer 21 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) -Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) -Reducer 24 <- Map 27 (CUSTOM_SIMPLE_EDGE), Reducer 23 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 27 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) -Reducer 26 <- Reducer 25 (SIMPLE_EDGE) -Reducer 3 <- Reducer 18 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) +Reducer 21 <- Map 24 (CUSTOM_SIMPLE_EDGE), Reducer 20 (CUSTOM_SIMPLE_EDGE) +Reducer 22 <- Map 24 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) +Reducer 23 <- Reducer 22 (SIMPLE_EDGE) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 11 (ONE_TO_ONE_EDGE), Reducer 15 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) +Reducer 5 <- Reducer 10 (ONE_TO_ONE_EDGE), Reducer 13 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 28 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 8 <- Map 25 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 15 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_480] - Limit [LIM_479] (rows=100 width=88) + File Output Operator [FS_465] + Limit [LIM_464] (rows=1 width=884) Number of rows:100 - Select Operator [SEL_478] (rows=1442 width=88) + Select Operator [SEL_463] (rows=1 width=884) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_161] - Select Operator [SEL_160] (rows=1442 width=88) + Select Operator [SEL_160] (rows=1 width=884) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_154] (rows=1442 width=88) + Filter Operator [FIL_154] (rows=1 width=436) predicate:(_col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) - Merge Join Operator [MERGEJOIN_417] (rows=766650239 width=88) - Conds:RS_459._col0=RS_468._col0(Inner),RS_459._col0=RS_477._col0(Inner),Output:["_col0","_col1","_col3","_col5"] - <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_468] + Merge Join Operator [MERGEJOIN_417] (rows=68 width=436) + Conds:RS_448._col0=RS_455._col0(Inner),RS_448._col0=RS_462._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_455] PartitionCols:_col0 - Group By Operator [GBY_467] (rows=348477374 width=88) + Group By Operator [GBY_454] (rows=69 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col0 - Group By Operator [GBY_96] (rows=696954748 width=88) + Group By Operator [GBY_96] (rows=69 width=212) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_415] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_415] (rows=120498 width=100) Conds:RS_92._col0=RS_93._col0(Inner),Output:["_col2","_col4"] - <-Reducer 18 [SIMPLE_EDGE] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_405] (rows=80353 width=1119) - Conds:RS_436._col1=RS_452._col0(Inner),Output:["_col0"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_436] + Merge Join Operator [MERGEJOIN_405] (rows=2 width=4) + Conds:RS_420._col1=RS_436._col0(Inner),Output:["_col0"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_420] PartitionCols:_col1 - Select Operator [SEL_435] (rows=73049 width=1119) + Select Operator [SEL_419] (rows=73049 width=98) Output:["_col0","_col1"] - Filter Operator [FIL_434] (rows=73049 width=1119) + Filter Operator [FIL_418] (rows=73049 width=98) predicate:(d_date is not null and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Reducer 26 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_452] + TableScan [TS_6] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 23 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_436] PartitionCols:_col0 - Group By Operator [GBY_451] (rows=40176 width=1119) + Group By Operator [GBY_435] (rows=2 width=94) Output:["_col0"],keys:KEY._col0 - <-Reducer 25 [SIMPLE_EDGE] + <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col0 - Group By Operator [GBY_31] (rows=80353 width=1119) + Group By Operator [GBY_31] (rows=2 width=94) Output:["_col0"],keys:_col2 - Merge Join Operator [MERGEJOIN_404] (rows=80353 width=1119) - Conds:RS_27._col1=RS_449._col1(Inner),Output:["_col2"] - <-Map 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_449] + Merge Join Operator [MERGEJOIN_404] (rows=5 width=94) + Conds:RS_27._col1=RS_433._col1(Inner),Output:["_col2"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_433] PartitionCols:_col1 - Select Operator [SEL_447] (rows=73049 width=1119) + Select Operator [SEL_431] (rows=73049 width=98) Output:["_col0","_col1"] - Filter Operator [FIL_445] (rows=73049 width=1119) + Filter Operator [FIL_429] (rows=73049 width=98) predicate:(d_date is not null and d_week_seq is not null) - TableScan [TS_21] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] - <-Reducer 24 [SIMPLE_EDGE] + TableScan [TS_21] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] + <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_403] (rows=36524 width=1128) + Merge Join Operator [MERGEJOIN_403] (rows=1 width=4) Conds:(Inner),Output:["_col1"] - <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_450] - Select Operator [SEL_448] (rows=36524 width=1119) + <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_434] + Select Operator [SEL_432] (rows=1 width=4) Output:["_col0"] - Filter Operator [FIL_446] (rows=36524 width=1119) + Filter Operator [FIL_430] (rows=1 width=98) predicate:((d_date = '1998-02-19') and d_week_seq is not null) Please refer to the previous TableScan [TS_21] - <-Reducer 23 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_444] - Select Operator [SEL_443] (rows=1 width=8) - Filter Operator [FIL_442] (rows=1 width=8) + <-Reducer 20 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_428] + Select Operator [SEL_427] (rows=1 width=8) + Filter Operator [FIL_426] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_441] (rows=1 width=8) + Group By Operator [GBY_425] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_440] - Group By Operator [GBY_439] (rows=1 width=8) + <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_424] + Group By Operator [GBY_423] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_438] (rows=36524 width=1119) - Filter Operator [FIL_437] (rows=36524 width=1119) + Select Operator [SEL_422] (rows=1 width=94) + Filter Operator [FIL_421] (rows=1 width=94) predicate:(d_date = '1998-02-19') - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date"] - <-Reducer 9 [SIMPLE_EDGE] + TableScan [TS_9] (rows=73049 width=94) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date"] + <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_92] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_406] (rows=633595212 width=88) - Conds:RS_466._col1=RS_422._col0(Inner),Output:["_col0","_col2","_col4"] + Merge Join Operator [MERGEJOIN_406] (rows=550076554 width=210) + Conds:RS_453._col1=RS_445._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_422] + SHUFFLE [RS_445] PartitionCols:_col0 - Select Operator [SEL_419] (rows=462000 width=1436) + Select Operator [SEL_443] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_418] (rows=462000 width=1436) + Filter Operator [FIL_442] (rows=462000 width=104) predicate:(i_item_id is not null and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] - <-Map 28 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_466] + TableScan [TS_3] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_453] PartitionCols:_col1 - Select Operator [SEL_465] (rows=575995635 width=88) + Select Operator [SEL_452] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_464] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_90_item_i_item_sk_min) AND DynamicValue(RS_90_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_90_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_93_date_dim_d_date_sk_min) AND DynamicValue(RS_93_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_93_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_50] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_461] - Group By Operator [GBY_460] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_430] - Group By Operator [GBY_427] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_423] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_419] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_463] - Group By Operator [GBY_462] (rows=1 width=12) + Filter Operator [FIL_451] (rows=550076554 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_93_date_dim_d_date_sk_min) AND DynamicValue(RS_93_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_93_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_50] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_450] + Group By Operator [GBY_449] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 18 [CUSTOM_SIMPLE_EDGE] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] SHUFFLE [RS_321] Group By Operator [GBY_320] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_319] (rows=80353 width=1119) + Select Operator [SEL_319] (rows=2 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_405] - <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_477] + <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_462] PartitionCols:_col0 - Group By Operator [GBY_476] (rows=87121617 width=135) + Group By Operator [GBY_461] (rows=69 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 14 [SIMPLE_EDGE] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_147] PartitionCols:_col0 - Group By Operator [GBY_146] (rows=174243235 width=135) + Group By Operator [GBY_146] (rows=69 width=212) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_416] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_416] (rows=31537 width=100) Conds:RS_142._col0=RS_143._col0(Inner),Output:["_col2","_col4"] - <-Reducer 18 [SIMPLE_EDGE] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_143] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_405] - <-Reducer 13 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_142] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_410] (rows=158402938 width=135) - Conds:RS_475._col1=RS_424._col0(Inner),Output:["_col0","_col2","_col4"] + Merge Join Operator [MERGEJOIN_410] (rows=143966864 width=215) + Conds:RS_460._col1=RS_446._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_424] + SHUFFLE [RS_446] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_419] - <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_475] + Please refer to the previous Select Operator [SEL_443] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_460] PartitionCols:_col1 - Select Operator [SEL_474] (rows=144002668 width=135) + Select Operator [SEL_459] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_473] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_140_item_i_item_sk_min) AND DynamicValue(RS_140_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_140_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_143_date_dim_d_date_sk_min) AND DynamicValue(RS_143_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_143_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_100] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_470] - Group By Operator [GBY_469] (rows=1 width=12) + Filter Operator [FIL_458] (rows=143966864 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_143_date_dim_d_date_sk_min) AND DynamicValue(RS_143_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_143_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_100] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_457] + Group By Operator [GBY_456] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_431] - Group By Operator [GBY_428] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_425] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_419] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_472] - Group By Operator [GBY_471] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 18 [CUSTOM_SIMPLE_EDGE] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] SHUFFLE [RS_367] Group By Operator [GBY_366] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_365] (rows=80353 width=1119) + Select Operator [SEL_365] (rows=2 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_405] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_459] + FORWARD [RS_448] PartitionCols:_col0 - Group By Operator [GBY_458] (rows=174233858 width=135) + Group By Operator [GBY_447] (rows=68 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col0 - Group By Operator [GBY_46] (rows=348467716 width=135) + Group By Operator [GBY_46] (rows=68 width=212) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_414] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_414] (rows=62327 width=100) Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col2","_col4"] - <-Reducer 18 [SIMPLE_EDGE] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_405] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_402] (rows=316788826 width=135) - Conds:RS_457._col1=RS_420._col0(Inner),Output:["_col0","_col2","_col4"] + Merge Join Operator [MERGEJOIN_402] (rows=286549727 width=215) + Conds:RS_441._col1=RS_444._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_420] + SHUFFLE [RS_444] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_419] + Please refer to the previous Select Operator [SEL_443] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_457] + SHUFFLE [RS_441] PartitionCols:_col1 - Select Operator [SEL_456] (rows=287989836 width=135) + Select Operator [SEL_440] (rows=286549727 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_455] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_40_item_i_item_sk_min) AND DynamicValue(RS_40_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_40_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_454] - Group By Operator [GBY_453] (rows=1 width=12) + Filter Operator [FIL_439] (rows=286549727 width=119) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_438] + Group By Operator [GBY_437] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 18 [CUSTOM_SIMPLE_EDGE] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] SHUFFLE [RS_271] Group By Operator [GBY_270] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_269] (rows=80353 width=1119) + Select Operator [SEL_269] (rows=2 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_405] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_433] - Group By Operator [GBY_432] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_429] - Group By Operator [GBY_426] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_421] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_419] diff --git a/ql/src/test/results/clientpositive/perf/tez/query59.q.out b/ql/src/test/results/clientpositive/perf/tez/query59.q.out index a4be291b1b..4bf2171bca 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query59.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query59.q.out @@ -87,197 +87,132 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 17 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Map 18 <- Reducer 14 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) -Reducer 10 <- Map 18 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 15 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 19 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) +Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 13 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 10 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (SIMPLE_EDGE) +Reducer 9 <- Map 12 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_234] - Limit [LIM_233] (rows=100 width=88) + File Output Operator [FS_210] + Limit [LIM_209] (rows=100 width=976) Number of rows:100 - Select Operator [SEL_232] (rows=421657640 width=88) + Select Operator [SEL_208] (rows=108896978 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_59] - Select Operator [SEL_58] (rows=421657640 width=88) + Select Operator [SEL_58] (rows=108896978 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Merge Join Operator [MERGEJOIN_185] (rows=421657640 width=88) + Merge Join Operator [MERGEJOIN_185] (rows=108896978 width=1648) Conds:RS_55._col12, _col0=RS_56._col1, (_col0 - 52)(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13","_col16","_col17","_col18","_col19","_col20","_col21"] - <-Reducer 13 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col1, (_col0 - 52) - Select Operator [SEL_48] (rows=383325119 width=88) + Select Operator [SEL_48] (rows=738556 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_184] (rows=383325119 width=88) - Conds:RS_45._col1=RS_221._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"] - <-Map 19 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_221] + Merge Join Operator [MERGEJOIN_184] (rows=738556 width=776) + Conds:RS_45._col1=RS_207._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_207] PartitionCols:_col0 - Select Operator [SEL_220] (rows=1704 width=1910) + Select Operator [SEL_206] (rows=1704 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_219] (rows=1704 width=1910) + Filter Operator [FIL_205] (rows=1704 width=104) predicate:(s_store_id is not null and s_store_sk is not null) - TableScan [TS_39] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id"] - <-Reducer 12 [SIMPLE_EDGE] + TableScan [TS_39] (rows=1704 width=104) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_183] (rows=348477374 width=88) - Conds:RS_231._col0=RS_216._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] + Merge Join Operator [MERGEJOIN_183] (rows=738556 width=679) + Conds:RS_204._col0=RS_199._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_199] PartitionCols:_col1 - Select Operator [SEL_214] (rows=8116 width=1119) + Select Operator [SEL_197] (rows=8116 width=8) Output:["_col1"] - Filter Operator [FIL_212] (rows=8116 width=1119) + Filter Operator [FIL_195] (rows=8116 width=8) predicate:(d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) - TableScan [TS_15] (rows=73049 width=1119) - default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_week_seq"] - <-Reducer 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_231] + TableScan [TS_15] (rows=73049 width=8) + default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_week_seq"] + <-Reducer 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_204] PartitionCols:_col0 - Group By Operator [GBY_230] (rows=316797606 width=88) + Group By Operator [GBY_203] (rows=1196832 width=679) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)"],keys:KEY._col0, KEY._col1 - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col0, _col1 - Group By Operator [GBY_32] (rows=633595212 width=88) + Group By Operator [GBY_32] (rows=525329897 width=679) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)","sum(_col3)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 - Select Operator [SEL_30] (rows=633595212 width=88) + Select Operator [SEL_30] (rows=525329897 width=205) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_182] (rows=633595212 width=88) - Conds:RS_229._col0=RS_190._col0(Inner),Output:["_col1","_col2","_col4","_col5"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_190] + Merge Join Operator [MERGEJOIN_179] (rows=525329897 width=205) + Conds:RS_188._col0=RS_191._col0(Inner),Output:["_col1","_col2","_col4","_col5"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_188] PartitionCols:_col0 - Select Operator [SEL_187] (rows=73049 width=1119) + Select Operator [SEL_187] (rows=525329897 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_186] (rows=73049 width=1119) - predicate:(d_date_sk is not null and d_week_seq is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_week_seq","d_day_name"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_229] + Filter Operator [FIL_186] (rows=525329897 width=114) + predicate:(ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_191] PartitionCols:_col0 - Select Operator [SEL_228] (rows=575995635 width=88) + Select Operator [SEL_190] (rows=73049 width=99) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_227] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_46_store_s_store_sk_min) AND DynamicValue(RS_46_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_46_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_21] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_218] - Group By Operator [GBY_217] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_195] - Group By Operator [GBY_193] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_191] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_187] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_226] - Group By Operator [GBY_225] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_224] - Group By Operator [GBY_223] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_222] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_220] + Filter Operator [FIL_189] (rows=73049 width=99) + predicate:(d_date_sk is not null and d_week_seq is not null) + TableScan [TS_3] (rows=73049 width=99) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq","d_day_name"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col12, _col0 - Merge Join Operator [MERGEJOIN_181] (rows=383325119 width=88) - Conds:RS_52._col1=RS_200._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_200] + Merge Join Operator [MERGEJOIN_181] (rows=738556 width=976) + Conds:RS_52._col1=RS_202._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_202] PartitionCols:_col0 - Select Operator [SEL_199] (rows=1704 width=1910) + Select Operator [SEL_201] (rows=1704 width=192) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_198] (rows=1704 width=1910) + Filter Operator [FIL_200] (rows=1704 width=192) predicate:(s_store_id is not null and s_store_sk is not null) - TableScan [TS_18] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"] + TableScan [TS_18] (rows=1704 width=192) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_180] (rows=348477374 width=88) - Conds:RS_210._col0=RS_215._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_215] + Merge Join Operator [MERGEJOIN_180] (rows=738556 width=791) + Conds:RS_193._col0=RS_198._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_198] PartitionCols:_col1 - Select Operator [SEL_213] (rows=8116 width=1119) + Select Operator [SEL_196] (rows=8116 width=8) Output:["_col1"] - Filter Operator [FIL_211] (rows=8116 width=1119) + Filter Operator [FIL_194] (rows=8116 width=8) predicate:(d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) Please refer to the previous TableScan [TS_15] <-Reducer 3 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_210] + SHUFFLE [RS_193] PartitionCols:_col0 - Group By Operator [GBY_209] (rows=316797606 width=88) + Group By Operator [GBY_192] (rows=1196832 width=791) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col0, _col1 - Group By Operator [GBY_11] (rows=633595212 width=88) + Group By Operator [GBY_11] (rows=525329897 width=791) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 - Select Operator [SEL_9] (rows=633595212 width=88) + Select Operator [SEL_9] (rows=525329897 width=205) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_179] (rows=633595212 width=88) - Conds:RS_208._col0=RS_188._col0(Inner),Output:["_col1","_col2","_col4","_col5"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_188] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_187] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_208] - PartitionCols:_col0 - Select Operator [SEL_207] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_206] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_53_store_s_store_sk_min) AND DynamicValue(RS_53_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_53_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_205] - Group By Operator [GBY_204] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_203] - Group By Operator [GBY_202] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_201] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_199] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_197] - Group By Operator [GBY_196] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_194] - Group By Operator [GBY_192] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_189] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_187] + Please refer to the previous Merge Join Operator [MERGEJOIN_179] diff --git a/ql/src/test/results/clientpositive/perf/tez/query6.q.out b/ql/src/test/results/clientpositive/perf/tez/query6.q.out index a57f72c11d..fefcf2485b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query6.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query6.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[171][bigTable=?] in task 'Reducer 19' is a cross product +Warning: Map Join MAPJOIN[171][bigTable=?] in task 'Reducer 15' is a cross product PREHOOK: query: explain select a.ca_state state, count(*) cnt from customer_address a @@ -52,209 +52,175 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 13 <- Reducer 16 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (SIMPLE_EDGE) -Reducer 11 <- Map 9 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (SIMPLE_EDGE), Reducer 12 (BROADCAST_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (ONE_TO_ONE_EDGE) -Reducer 20 <- Map 22 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) -Reducer 21 <- Reducer 20 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 20 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 3 (BROADCAST_EDGE) +Map 16 <- Reducer 15 (BROADCAST_EDGE) +Map 6 <- Map 1 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Map 2 (SIMPLE_EDGE) +Reducer 4 <- Map 2 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 8 <- Map 16 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 7 vectorized - File Output Operator [FS_227] - Limit [LIM_226] (rows=100 width=88) + Reducer 10 vectorized + File Output Operator [FS_234] + Limit [LIM_233] (rows=1 width=94) Number of rows:100 - Select Operator [SEL_225] (rows=127775039 width=88) + Select Operator [SEL_232] (rows=1 width=94) Output:["_col0","_col1"] - <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_224] - Filter Operator [FIL_223] (rows=127775039 width=88) + <-Reducer 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_231] + Filter Operator [FIL_230] (rows=1 width=94) predicate:(_col1 >= 10L) - Group By Operator [GBY_222] (rows=383325119 width=88) + Group By Operator [GBY_229] (rows=1 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 5 [SIMPLE_EDGE] + <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col0 - Group By Operator [GBY_68] (rows=766650239 width=88) + Group By Operator [GBY_68] (rows=1 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col9 - Merge Join Operator [MERGEJOIN_174] (rows=766650239 width=88) - Conds:RS_64._col4=RS_65._col0(Inner),Output:["_col9"] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_65] + Merge Join Operator [MERGEJOIN_174] (rows=316 width=86) + Conds:RS_64._col4=RS_213._col0(Inner),Output:["_col9"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_213] PartitionCols:_col0 - Select Operator [SEL_54] (rows=169400 width=1436) + Select Operator [SEL_212] (rows=154000 width=227) Output:["_col0"] - Filter Operator [FIL_53] (rows=169400 width=1436) + Filter Operator [FIL_211] (rows=154000 width=227) predicate:(_col4 > (1.2 * CAST( _col0 AS decimal(16,6)))) - Merge Join Operator [MERGEJOIN_172] (rows=508200 width=1436) - Conds:RS_213._col1=RS_216._col2(Inner),Output:["_col0","_col3","_col4"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] - PartitionCols:_col2 - Select Operator [SEL_215] (rows=462000 width=1436) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_214] (rows=462000 width=1436) - predicate:(i_category is not null and i_item_sk is not null) - TableScan [TS_44] (rows=462000 width=1436) - default@item,i,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_category"] - <-Reducer 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_213] + Map Join Operator [MAPJOIN_210] (rows=462000 width=227) + Conds:RS_207._col1=SEL_209._col2(Inner),HybridGraceHashJoin:true,Output:["_col0","_col3","_col4"] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_207] PartitionCols:_col1 - Map Join Operator [MAPJOIN_212] (rows=231000 width=1445) + Map Join Operator [MAPJOIN_206] (rows=10 width=202) Conds:(Inner),Output:["_col0","_col1"] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_209] - Select Operator [SEL_208] (rows=1 width=8) - Filter Operator [FIL_207] (rows=1 width=8) + <-Reducer 5 [BROADCAST_EDGE] vectorized + BROADCAST [RS_203] + Select Operator [SEL_202] (rows=1 width=8) + Filter Operator [FIL_201] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_206] (rows=1 width=8) + Group By Operator [GBY_200] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_205] - Group By Operator [GBY_204] (rows=1 width=8) + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_199] + Group By Operator [GBY_198] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_203] (rows=9131 width=1119) - Group By Operator [GBY_202] (rows=9131 width=1119) + Select Operator [SEL_197] (rows=25 width=4) + Group By Operator [GBY_196] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 9 [SIMPLE_EDGE] vectorized + <-Map 2 [SIMPLE_EDGE] vectorized SHUFFLE [RS_186] PartitionCols:_col0 - Group By Operator [GBY_184] (rows=18262 width=1119) + Group By Operator [GBY_184] (rows=25 width=4) Output:["_col0"],keys:d_month_seq - Select Operator [SEL_182] (rows=18262 width=1119) + Select Operator [SEL_182] (rows=50 width=12) Output:["d_month_seq"] - Filter Operator [FIL_180] (rows=18262 width=1119) + Filter Operator [FIL_180] (rows=50 width=12) predicate:((d_moy = 2) and (d_year = 2000)) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] - <-Select Operator [SEL_211] (rows=231000 width=1436) + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_year","d_moy"] + <-Select Operator [SEL_205] (rows=10 width=202) Output:["_col0","_col1"] - Group By Operator [GBY_210] (rows=231000 width=1436) + Group By Operator [GBY_204] (rows=10 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_201] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_195] PartitionCols:_col0 - Group By Operator [GBY_200] (rows=462000 width=1436) + Group By Operator [GBY_194] (rows=10 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(i_current_price)","count(i_current_price)"],keys:i_category - Filter Operator [FIL_199] (rows=462000 width=1436) + Filter Operator [FIL_193] (rows=462000 width=201) predicate:i_category is not null - TableScan [TS_23] (rows=462000 width=1436) - default@item,j,Tbl:COMPLETE,Col:NONE,Output:["i_current_price","i_category"] - <-Reducer 4 [SIMPLE_EDGE] + TableScan [TS_23] (rows=462000 width=201) + default@item,j,Tbl:COMPLETE,Col:COMPLETE,Output:["i_current_price","i_category"] + <-Select Operator [SEL_209] (rows=462000 width=205) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_208] (rows=462000 width=205) + predicate:(i_category is not null and i_item_sk is not null) + TableScan [TS_44] (rows=462000 width=205) + default@item,i,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_category"] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_173] (rows=696954748 width=88) - Conds:RS_61._col5=RS_62._col0(Inner),Output:["_col4","_col9"] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_62] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_170] (rows=88000001 width=860) - Conds:RS_193._col1=RS_196._col0(Inner),Output:["_col0","_col3"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_193] - PartitionCols:_col1 - Select Operator [SEL_192] (rows=80000000 width=860) - Output:["_col0","_col1"] - Filter Operator [FIL_191] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_13] (rows=80000000 width=860) - default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_196] - PartitionCols:_col0 - Select Operator [SEL_195] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_194] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_16] (rows=40000000 width=1014) - default@customer_address,a,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_61] + Merge Join Operator [MERGEJOIN_173] (rows=7192227 width=90) + Conds:RS_222._col5=RS_62._col0(Inner),Output:["_col4","_col9"] + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_222] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_169] (rows=633595212 width=88) - Conds:RS_58._col0=RS_221._col0(Inner),Output:["_col4","_col5"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_58] + Map Join Operator [MAPJOIN_221] (rows=7192227 width=4) + Conds:RS_192._col0=SEL_220._col0(Inner),HybridGraceHashJoin:true,Output:["_col4","_col5"] + <-Map 1 [BROADCAST_EDGE] vectorized + BROADCAST [RS_192] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_168] (rows=80353 width=1119) - Conds:RS_178._col1=RS_188._col0(Inner),Output:["_col0"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_178] - PartitionCols:_col1 - Select Operator [SEL_177] (rows=73049 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_176] (rows=73049 width=1119) - predicate:(d_date_sk is not null and d_month_seq is not null) - TableScan [TS_0] (rows=73049 width=1119) - default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] - <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_188] + Map Join Operator [MAPJOIN_191] (rows=660 width=4) + Conds:SEL_190._col1=RS_188._col0(Inner),HybridGraceHashJoin:true,Output:["_col0"] + <-Reducer 3 [BROADCAST_EDGE] vectorized + BROADCAST [RS_188] PartitionCols:_col0 - Group By Operator [GBY_187] (rows=9131 width=1119) + Group By Operator [GBY_187] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 9 [SIMPLE_EDGE] vectorized + <-Map 2 [SIMPLE_EDGE] vectorized SHUFFLE [RS_185] PartitionCols:_col0 - Group By Operator [GBY_183] (rows=18262 width=1119) + Group By Operator [GBY_183] (rows=25 width=4) Output:["_col0"],keys:d_month_seq - Select Operator [SEL_181] (rows=18262 width=1119) + Select Operator [SEL_181] (rows=50 width=12) Output:["d_month_seq"] - Filter Operator [FIL_179] (rows=18262 width=1119) + Filter Operator [FIL_179] (rows=50 width=12) predicate:((d_moy = 2) and (d_year = 2000) and d_month_seq is not null) Please refer to the previous TableScan [TS_3] + <-Select Operator [SEL_190] (rows=73049 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_189] (rows=73049 width=8) + predicate:(d_date_sk is not null and d_month_seq is not null) + TableScan [TS_0] (rows=73049 width=8) + default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Select Operator [SEL_220] (rows=525327388 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_219] (rows=525327388 width=11) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_65_i_i_item_sk_min) AND DynamicValue(RS_65_i_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_65_i_i_item_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_10] (rows=575995635 width=11) + default@store_sales,s,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_218] + Group By Operator [GBY_217] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_216] + Group By Operator [GBY_215] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_214] (rows=154000 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_212] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_62] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_170] (rows=80000000 width=90) + Conds:RS_225._col1=RS_228._col0(Inner),Output:["_col0","_col3"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_225] + PartitionCols:_col1 + Select Operator [SEL_224] (rows=80000000 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_223] (rows=80000000 width=8) + predicate:(c_current_addr_sk is not null and c_customer_sk is not null) + TableScan [TS_13] (rows=80000000 width=8) + default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_221] + SHUFFLE [RS_228] PartitionCols:_col0 - Select Operator [SEL_220] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_219] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_62_c_c_customer_sk_min) AND DynamicValue(RS_62_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_62_c_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_65_i_i_item_sk_min) AND DynamicValue(RS_65_i_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_65_i_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_58_d_d_date_sk_min) AND DynamicValue(RS_58_d_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_58_d_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_10] (rows=575995635 width=88) - default@store_sales,s,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_198] - Group By Operator [GBY_197] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_130] - Group By Operator [GBY_129] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] - Select Operator [SEL_128] (rows=88000001 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_170] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_218] - Group By Operator [GBY_217] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 20 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_135] - Group By Operator [GBY_134] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_133] (rows=169400 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_54] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_190] - Group By Operator [GBY_189] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_125] - Group By Operator [GBY_124] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_123] (rows=80353 width=1119) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_168] + Select Operator [SEL_227] (rows=40000000 width=90) + Output:["_col0","_col1"] + Filter Operator [FIL_226] (rows=40000000 width=90) + predicate:ca_address_sk is not null + TableScan [TS_16] (rows=40000000 width=90) + default@customer_address,a,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query60.q.out b/ql/src/test/results/clientpositive/perf/tez/query60.q.out index 277dd5d01c..4a74c3c6ae 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query60.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query60.q.out @@ -190,100 +190,100 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_375] - Limit [LIM_374] (rows=100 width=108) + Limit [LIM_374] (rows=100 width=212) Number of rows:100 - Select Operator [SEL_373] (rows=335408073 width=108) + Select Operator [SEL_373] (rows=1717 width=212) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_372] - Group By Operator [GBY_371] (rows=335408073 width=108) + Group By Operator [GBY_371] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] <-Reducer 10 [CONTAINS] vectorized Reduce Output Operator [RS_388] PartitionCols:_col0 - Group By Operator [GBY_387] (rows=670816147 width=108) + Group By Operator [GBY_387] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_386] (rows=670816147 width=108) + Top N Key Operator [TNK_386] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_385] (rows=191657247 width=135) + Group By Operator [GBY_385] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_71] PartitionCols:_col0 - Group By Operator [GBY_70] (rows=383314495 width=135) + Group By Operator [GBY_70] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_304] (rows=746132 width=100) Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_294] (rows=508200 width=1436) + Merge Join Operator [MERGEJOIN_294] (rows=34340 width=104) Conds:RS_323._col1=RS_329._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_323] PartitionCols:_col1 - Select Operator [SEL_322] (rows=462000 width=1436) + Select Operator [SEL_322] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_321] (rows=462000 width=1436) + Filter Operator [FIL_321] (rows=462000 width=104) predicate:(i_item_id is not null and i_item_sk is not null) - TableScan [TS_0] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + TableScan [TS_0] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_329] PartitionCols:_col0 - Group By Operator [GBY_328] (rows=115500 width=1436) + Group By Operator [GBY_328] (rows=23100 width=100) Output:["_col0"],keys:KEY._col0 <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_327] PartitionCols:_col0 - Group By Operator [GBY_326] (rows=231000 width=1436) + Group By Operator [GBY_326] (rows=23100 width=100) Output:["_col0"],keys:i_item_id - Select Operator [SEL_325] (rows=231000 width=1436) + Select Operator [SEL_325] (rows=46200 width=190) Output:["i_item_id"] - Filter Operator [FIL_324] (rows=231000 width=1436) + Filter Operator [FIL_324] (rows=46200 width=190) predicate:((i_category = 'Children') and i_item_id is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_id","i_category"] + TableScan [TS_3] (rows=462000 width=190) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_category"] <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col4 - Select Operator [SEL_62] (rows=348467716 width=135) + Select Operator [SEL_62] (rows=1550375 width=13) Output:["_col4","_col5"] - Merge Join Operator [MERGEJOIN_299] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_299] (rows=1550375 width=13) Conds:RS_59._col1=RS_350._col0(Inner),Output:["_col2","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_350] PartitionCols:_col0 - Select Operator [SEL_347] (rows=20000000 width=1014) + Select Operator [SEL_347] (rows=8000000 width=116) Output:["_col0"] - Filter Operator [FIL_346] (rows=20000000 width=1014) + Filter Operator [FIL_346] (rows=8000000 width=112) predicate:((ca_gmt_offset = -6) and ca_address_sk is not null) - TableScan [TS_16] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"] + TableScan [TS_16] (rows=40000000 width=112) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_298] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_298] (rows=7751872 width=98) Conds:RS_384._col0=RS_334._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_334] PartitionCols:_col0 - Select Operator [SEL_331] (rows=18262 width=1119) + Select Operator [SEL_331] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_330] (rows=18262 width=1119) + Filter Operator [FIL_330] (rows=50 width=12) predicate:((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_13] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_13] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 32 [SIMPLE_EDGE] vectorized SHUFFLE [RS_384] PartitionCols:_col0 - Select Operator [SEL_383] (rows=287989836 width=135) + Select Operator [SEL_383] (rows=285117733 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_382] (rows=287989836 width=135) + Filter Operator [FIL_382] (rows=285117733 width=123) predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_66_item_i_item_sk_min) AND DynamicValue(RS_66_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_66_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_47] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] + TableScan [TS_47] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_381] Group By Operator [GBY_380] (rows=1 width=12) @@ -292,7 +292,7 @@ Stage-0 SHUFFLE [RS_241] Group By Operator [GBY_240] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_239] (rows=508200 width=1436) + Select Operator [SEL_239] (rows=34340 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_294] <-Reducer 24 [BROADCAST_EDGE] vectorized @@ -303,35 +303,35 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_342] Group By Operator [GBY_339] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_335] (rows=18262 width=1119) + Select Operator [SEL_335] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_331] <-Reducer 30 [BROADCAST_EDGE] vectorized BROADCAST [RS_379] Group By Operator [GBY_378] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_358] Group By Operator [GBY_355] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_351] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_351] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_347] <-Reducer 13 [CONTAINS] vectorized Reduce Output Operator [RS_401] PartitionCols:_col0 - Group By Operator [GBY_400] (rows=670816147 width=108) + Group By Operator [GBY_400] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_399] (rows=670816147 width=108) + Top N Key Operator [TNK_399] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_398] (rows=95833781 width=135) + Group By Operator [GBY_398] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col0 - Group By Operator [GBY_108] (rows=191667562 width=135) + Group By Operator [GBY_108] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_305] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_305] (rows=379339 width=201) Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] @@ -340,9 +340,9 @@ Stage-0 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_105] PartitionCols:_col3 - Select Operator [SEL_100] (rows=174243235 width=135) + Select Operator [SEL_100] (rows=788222 width=110) Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_302] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_302] (rows=788222 width=110) Conds:RS_97._col2=RS_352._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_352] @@ -351,7 +351,7 @@ Stage-0 <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_301] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_301] (rows=3941109 width=118) Conds:RS_397._col0=RS_336._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_336] @@ -360,12 +360,12 @@ Stage-0 <-Map 33 [SIMPLE_EDGE] vectorized SHUFFLE [RS_397] PartitionCols:_col0 - Select Operator [SEL_396] (rows=144002668 width=135) + Select Operator [SEL_396] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_395] (rows=144002668 width=135) + Filter Operator [FIL_395] (rows=143931246 width=123) predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_85] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] + TableScan [TS_85] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_394] Group By Operator [GBY_393] (rows=1 width=12) @@ -374,7 +374,7 @@ Stage-0 SHUFFLE [RS_281] Group By Operator [GBY_280] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_279] (rows=508200 width=1436) + Select Operator [SEL_279] (rows=34340 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_294] <-Reducer 27 [BROADCAST_EDGE] vectorized @@ -385,35 +385,35 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_343] Group By Operator [GBY_340] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_337] (rows=18262 width=1119) + Select Operator [SEL_337] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_331] <-Reducer 31 [BROADCAST_EDGE] vectorized BROADCAST [RS_392] Group By Operator [GBY_391] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_359] Group By Operator [GBY_356] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_353] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_353] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_347] <-Reducer 4 [CONTAINS] vectorized Reduce Output Operator [RS_370] PartitionCols:_col0 - Group By Operator [GBY_369] (rows=670816147 width=108) + Group By Operator [GBY_369] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_368] (rows=670816147 width=108) + Top N Key Operator [TNK_368] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_367] (rows=383325119 width=88) + Group By Operator [GBY_367] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Group By Operator [GBY_33] (rows=766650239 width=88) + Group By Operator [GBY_33] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_303] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_303] (rows=1384530 width=100) Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] @@ -422,9 +422,9 @@ Stage-0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col3 - Select Operator [SEL_25] (rows=696954748 width=88) + Select Operator [SEL_25] (rows=2876890 width=4) Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_296] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_296] (rows=2876890 width=4) Conds:RS_22._col2=RS_348._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_348] @@ -433,7 +433,7 @@ Stage-0 <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_295] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_295] (rows=14384447 width=4) Conds:RS_366._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_332] @@ -442,12 +442,12 @@ Stage-0 <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_366] PartitionCols:_col0 - Select Operator [SEL_365] (rows=575995635 width=88) + Select Operator [SEL_365] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_364] (rows=575995635 width=88) + Filter Operator [FIL_364] (rows=525327191 width=118) predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_10] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] + TableScan [TS_10] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 21 [BROADCAST_EDGE] vectorized BROADCAST [RS_345] Group By Operator [GBY_344] (rows=1 width=12) @@ -456,18 +456,18 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_341] Group By Operator [GBY_338] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_333] (rows=18262 width=1119) + Select Operator [SEL_333] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_331] <-Reducer 29 [BROADCAST_EDGE] vectorized BROADCAST [RS_361] Group By Operator [GBY_360] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_357] Group By Operator [GBY_354] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_349] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] + Select Operator [SEL_349] (rows=8000000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_347] <-Reducer 8 [BROADCAST_EDGE] vectorized @@ -478,7 +478,7 @@ Stage-0 SHUFFLE [RS_201] Group By Operator [GBY_200] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_199] (rows=508200 width=1436) + Select Operator [SEL_199] (rows=34340 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_294] diff --git a/ql/src/test/results/clientpositive/perf/tez/query61.q.out b/ql/src/test/results/clientpositive/perf/tez/query61.q.out index 87f07fdf02..3eb28e0dad 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query61.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query61.q.out @@ -88,15 +88,15 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 12 <- Reducer 18 (BROADCAST_EDGE), Reducer 24 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 30 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Map 31 <- Reducer 10 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE) +Map 12 <- Reducer 18 (BROADCAST_EDGE), Reducer 24 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Map 30 <- Reducer 10 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE) Reducer 10 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) Reducer 14 <- Map 23 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) Reducer 15 <- Map 26 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) Reducer 16 <- Map 29 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE) +Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 30 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Reducer 20 <- Map 23 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) Reducer 21 <- Map 26 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) @@ -106,7 +106,6 @@ Reducer 25 <- Map 23 (CUSTOM_SIMPLE_EDGE) Reducer 27 <- Map 26 (CUSTOM_SIMPLE_EDGE) Reducer 28 <- Map 26 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 30 <- Map 29 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) @@ -119,115 +118,115 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_339] - Limit [LIM_338] (rows=1 width=225) + File Output Operator [FS_334] + Limit [LIM_333] (rows=1 width=336) Number of rows:100 - Select Operator [SEL_337] (rows=1 width=225) + Select Operator [SEL_332] (rows=1 width=336) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_88] - Select Operator [SEL_87] (rows=1 width=225) + Select Operator [SEL_87] (rows=1 width=336) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_266] (rows=1 width=225) + Merge Join Operator [MERGEJOIN_266] (rows=1 width=224) Conds:(Inner),Output:["_col0","_col1"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_323] - Group By Operator [GBY_322] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_318] + Group By Operator [GBY_317] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_42] Group By Operator [GBY_41] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col9)"] - Merge Join Operator [MERGEJOIN_264] (rows=927646829 width=88) + Merge Join Operator [MERGEJOIN_264] (rows=505397 width=0) Conds:RS_37._col0=RS_38._col2(Inner),Output:["_col9"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_255] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_255] (rows=16000001 width=4) Conds:RS_269._col1=RS_272._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_269] PartitionCols:_col1 - Select Operator [SEL_268] (rows=80000000 width=860) + Select Operator [SEL_268] (rows=80000000 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_267] (rows=80000000 width=860) + Filter Operator [FIL_267] (rows=80000000 width=8) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] + TableScan [TS_0] (rows=80000000 width=8) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_272] PartitionCols:_col0 - Select Operator [SEL_271] (rows=20000000 width=1014) + Select Operator [SEL_271] (rows=8000000 width=116) Output:["_col0"] - Filter Operator [FIL_270] (rows=20000000 width=1014) + Filter Operator [FIL_270] (rows=8000000 width=112) predicate:((ca_gmt_offset = -7) and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"] + TableScan [TS_3] (rows=40000000 width=112) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_259] (rows=843315281 width=88) - Conds:RS_30._col4=RS_311._col0(Inner),Output:["_col2","_col5"] + Merge Join Operator [MERGEJOIN_259] (rows=2526982 width=0) + Conds:RS_30._col4=RS_316._col0(Inner),Output:["_col2","_col5"] <-Map 29 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_311] + SHUFFLE [RS_316] PartitionCols:_col0 - Select Operator [SEL_310] (rows=2300 width=1179) + Select Operator [SEL_315] (rows=2300 width=259) Output:["_col0"] - Filter Operator [FIL_309] (rows=2300 width=1179) + Filter Operator [FIL_314] (rows=2300 width=259) predicate:(((p_channel_dmail = 'Y') or (p_channel_email = 'Y') or (p_channel_tv = 'Y')) and p_promo_sk is not null) - TableScan [TS_18] (rows=2300 width=1179) - default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_dmail","p_channel_email","p_channel_tv"] + TableScan [TS_18] (rows=2300 width=259) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk","p_channel_dmail","p_channel_email","p_channel_tv"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_258] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_258] (rows=2526982 width=0) Conds:RS_27._col3=RS_299._col0(Inner),Output:["_col2","_col4","_col5"] <-Map 26 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_299] PartitionCols:_col0 - Select Operator [SEL_298] (rows=852 width=1910) + Select Operator [SEL_298] (rows=341 width=116) Output:["_col0"] - Filter Operator [FIL_297] (rows=852 width=1910) + Filter Operator [FIL_297] (rows=341 width=115) predicate:((s_gmt_offset = -7) and s_store_sk is not null) - TableScan [TS_15] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_gmt_offset"] + TableScan [TS_15] (rows=1704 width=115) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_gmt_offset"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_257] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_257] (rows=12627499 width=0) Conds:RS_24._col1=RS_287._col0(Inner),Output:["_col2","_col3","_col4","_col5"] <-Map 23 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_287] PartitionCols:_col0 - Select Operator [SEL_286] (rows=231000 width=1436) + Select Operator [SEL_286] (rows=46200 width=99) Output:["_col0"] - Filter Operator [FIL_285] (rows=231000 width=1436) + Filter Operator [FIL_285] (rows=46200 width=94) predicate:((i_category = 'Electronics') and i_item_sk is not null) - TableScan [TS_12] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_category"] + TableScan [TS_12] (rows=462000 width=94) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category"] <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_256] (rows=633595212 width=88) - Conds:RS_321._col0=RS_275._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_256] (rows=13119234 width=4) + Conds:RS_313._col0=RS_275._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_275] PartitionCols:_col0 - Select Operator [SEL_274] (rows=18262 width=1119) + Select Operator [SEL_274] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_273] (rows=18262 width=1119) + Filter Operator [FIL_273] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_9] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] + SHUFFLE [RS_313] PartitionCols:_col0 - Select Operator [SEL_320] (rows=575995635 width=88) + Select Operator [SEL_312] (rows=479120970 width=126) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_319] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_37_customer_c_customer_sk_min) AND DynamicValue(RS_37_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_37_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_31_promotion_p_promo_sk_min) AND DynamicValue(RS_31_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_31_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_28_store_s_store_sk_min) AND DynamicValue(RS_28_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_28_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_promo_sk","ss_ext_sales_price"] + Filter Operator [FIL_311] (rows=479120970 width=126) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_37_customer_c_customer_sk_min) AND DynamicValue(RS_37_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_37_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_28_store_s_store_sk_min) AND DynamicValue(RS_28_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_28_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (rows=575995635 width=126) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_promo_sk","ss_ext_sales_price"] <-Reducer 18 [BROADCAST_EDGE] vectorized BROADCAST [RS_284] Group By Operator [GBY_283] (rows=1 width=12) @@ -236,7 +235,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_281] Group By Operator [GBY_279] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_276] (rows=18262 width=1119) + Select Operator [SEL_276] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_274] <-Reducer 24 [BROADCAST_EDGE] vectorized @@ -247,7 +246,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_293] Group By Operator [GBY_291] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_288] (rows=231000 width=1436) + Select Operator [SEL_288] (rows=46200 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_286] <-Reducer 27 [BROADCAST_EDGE] vectorized @@ -258,40 +257,29 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_305] Group By Operator [GBY_303] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_300] (rows=852 width=1910) + Select Operator [SEL_300] (rows=341 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_298] - <-Reducer 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_316] - Group By Operator [GBY_315] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 29 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_314] - Group By Operator [GBY_313] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_312] (rows=2300 width=1179) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_310] <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_318] - Group By Operator [GBY_317] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] + BROADCAST [RS_310] + Group By Operator [GBY_309] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=14591048)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] SHUFFLE [RS_182] Group By Operator [GBY_181] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] - Select Operator [SEL_180] (rows=88000001 width=860) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=14591048)"] + Select Operator [SEL_180] (rows=16000001 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_255] <-Reducer 9 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_336] - Group By Operator [GBY_335] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_331] + Group By Operator [GBY_330] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_81] Group By Operator [GBY_80] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col8)"] - Merge Join Operator [MERGEJOIN_265] (rows=843315281 width=88) + Merge Join Operator [MERGEJOIN_265] (rows=529208 width=0) Conds:RS_76._col0=RS_77._col2(Inner),Output:["_col8"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_76] @@ -300,7 +288,7 @@ Stage-0 <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_263] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_263] (rows=2646038 width=0) Conds:RS_69._col3=RS_301._col0(Inner),Output:["_col2","_col4"] <-Map 26 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_301] @@ -309,7 +297,7 @@ Stage-0 <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_262] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_262] (rows=13222427 width=0) Conds:RS_66._col1=RS_289._col0(Inner),Output:["_col2","_col3","_col4"] <-Map 23 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_289] @@ -318,63 +306,63 @@ Stage-0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_261] (rows=633595212 width=88) - Conds:RS_334._col0=RS_277._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_261] (rows=13737330 width=4) + Conds:RS_329._col0=RS_277._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_277] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_274] - <-Map 31 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_334] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_329] PartitionCols:_col0 - Select Operator [SEL_333] (rows=575995635 width=88) + Select Operator [SEL_328] (rows=501694138 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_332] (rows=575995635 width=88) + Filter Operator [FIL_327] (rows=501694138 width=122) predicate:((ss_customer_sk BETWEEN DynamicValue(RS_76_customer_c_customer_sk_min) AND DynamicValue(RS_76_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_76_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_67_item_i_item_sk_min) AND DynamicValue(RS_67_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_67_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_64_date_dim_d_date_sk_min) AND DynamicValue(RS_64_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_64_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_70_store_s_store_sk_min) AND DynamicValue(RS_70_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_70_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_51] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ext_sales_price"] + TableScan [TS_51] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ext_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_331] - Group By Operator [GBY_330] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] + BROADCAST [RS_326] + Group By Operator [GBY_325] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=14591048)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] SHUFFLE [RS_237] Group By Operator [GBY_236] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] - Select Operator [SEL_235] (rows=88000001 width=860) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=14591048)"] + Select Operator [SEL_235] (rows=16000001 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_255] <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_325] - Group By Operator [GBY_324] (rows=1 width=12) + BROADCAST [RS_320] + Group By Operator [GBY_319] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_282] Group By Operator [GBY_280] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_278] (rows=18262 width=1119) + Select Operator [SEL_278] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_274] <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_327] - Group By Operator [GBY_326] (rows=1 width=12) + BROADCAST [RS_322] + Group By Operator [GBY_321] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 23 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_294] Group By Operator [GBY_292] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_290] (rows=231000 width=1436) + Select Operator [SEL_290] (rows=46200 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_286] <-Reducer 28 [BROADCAST_EDGE] vectorized - BROADCAST [RS_329] - Group By Operator [GBY_328] (rows=1 width=12) + BROADCAST [RS_324] + Group By Operator [GBY_323] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_306] Group By Operator [GBY_304] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_302] (rows=852 width=1910) + Select Operator [SEL_302] (rows=341 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_298] diff --git a/ql/src/test/results/clientpositive/perf/tez/query63.q.out b/ql/src/test/results/clientpositive/perf/tez/query63.q.out index c9502f04d2..522ee976af 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query63.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query63.q.out @@ -57,9 +57,8 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) @@ -72,78 +71,78 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_116] - Limit [LIM_115] (rows=100 width=88) + File Output Operator [FS_111] + Limit [LIM_110] (rows=71 width=228) Number of rows:100 - Select Operator [SEL_114] (rows=191662559 width=88) + Select Operator [SEL_109] (rows=71 width=228) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_33] - Select Operator [SEL_30] (rows=191662559 width=88) + Select Operator [SEL_30] (rows=71 width=228) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_46] (rows=191662559 width=88) + Filter Operator [FIL_46] (rows=71 width=228) predicate:CASE WHEN ((avg_window_0 > 0)) THEN (((abs((_col2 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END - Select Operator [SEL_29] (rows=383325119 width=88) + Select Operator [SEL_29] (rows=143 width=116) Output:["avg_window_0","_col0","_col2"] - PTF Operator [PTF_28] (rows=383325119 width=88) + PTF Operator [PTF_28] (rows=143 width=116) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col0 ASC NULLS FIRST","partition by:":"_col0"}] - Select Operator [SEL_25] (rows=383325119 width=88) + Select Operator [SEL_25] (rows=143 width=116) Output:["_col0","_col2"] - Group By Operator [GBY_24] (rows=383325119 width=88) + Group By Operator [GBY_24] (rows=143 width=120) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0 - Group By Operator [GBY_22] (rows=766650239 width=88) + Group By Operator [GBY_22] (rows=156 width=120) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col11 - Merge Join Operator [MERGEJOIN_84] (rows=766650239 width=88) - Conds:RS_18._col2=RS_103._col0(Inner),Output:["_col3","_col8","_col11"] + Merge Join Operator [MERGEJOIN_84] (rows=1318594 width=8) + Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col8","_col11"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] + SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_102] (rows=1704 width=1910) + Select Operator [SEL_105] (rows=1704 width=4) Output:["_col0"] - Filter Operator [FIL_101] (rows=1704 width=1910) + Filter Operator [FIL_104] (rows=1704 width=4) predicate:s_store_sk is not null - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"] + TableScan [TS_9] (rows=1704 width=4) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_83] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_83] (rows=1318594 width=8) Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col8","_col11"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=73049 width=1119) + Select Operator [SEL_94] (rows=317 width=12) Output:["_col0","_col2"] - Filter Operator [FIL_93] (rows=73049 width=1119) + Filter Operator [FIL_93] (rows=317 width=12) predicate:((d_month_seq) IN (1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq","d_moy"] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq","d_moy"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_82] (rows=633595212 width=88) - Conds:RS_111._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col8"] + Merge Join Operator [MERGEJOIN_82] (rows=7595537 width=4) + Conds:RS_103._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col8"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=462000 width=1436) + Select Operator [SEL_86] (rows=694 width=289) Output:["_col0","_col4"] - Filter Operator [FIL_85] (rows=462000 width=1436) + Filter Operator [FIL_85] (rows=694 width=289) predicate:((((i_category) IN ('Books', 'Children', 'Electronics') and (i_class) IN ('personal', 'portable', 'refernece', 'self-help') and (i_brand) IN ('scholaramalgamalg #14', 'scholaramalgamalg #7', 'exportiunivamalg #9', 'scholaramalgamalg #9')) or ((i_category) IN ('Women', 'Music', 'Men') and (i_class) IN ('accessories', 'classical', 'fragrances', 'pants') and (i_brand) IN ('amalgimporto #1', 'edu packscholar #1', 'exportiimporto #1', 'importoamalg #1'))) and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_manager_id"] + TableScan [TS_3] (rows=462000 width=289) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category","i_manager_id"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] + SHUFFLE [RS_103] PartitionCols:_col1 - Select Operator [SEL_110] (rows=575995635 width=88) + Select Operator [SEL_102] (rows=525329897 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_109] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + Filter Operator [FIL_101] (rows=525329897 width=118) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_100] Group By Operator [GBY_99] (rows=1 width=12) @@ -152,20 +151,9 @@ Stage-0 SHUFFLE [RS_98] Group By Operator [GBY_97] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_96] (rows=73049 width=1119) + Select Operator [SEL_96] (rows=317 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_94] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_108] - Group By Operator [GBY_107] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_104] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_92] Group By Operator [GBY_91] (rows=1 width=12) @@ -174,7 +162,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_90] Group By Operator [GBY_89] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_88] (rows=462000 width=1436) + Select Operator [SEL_88] (rows=694 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_86] diff --git a/ql/src/test/results/clientpositive/perf/tez/query64.q.out b/ql/src/test/results/clientpositive/perf/tez/query64.q.out index e3eea5886c..35bb91247e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query64.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query64.q.out @@ -237,67 +237,50 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 40 <- Reducer 23 (BROADCAST_EDGE), Reducer 34 (BROADCAST_EDGE), Reducer 38 (BROADCAST_EDGE), Reducer 43 (BROADCAST_EDGE), Reducer 47 (BROADCAST_EDGE), Reducer 52 (BROADCAST_EDGE), Reducer 62 (BROADCAST_EDGE), Reducer 65 (BROADCAST_EDGE), Reducer 66 (BROADCAST_EDGE), Reducer 70 (BROADCAST_EDGE) -Map 49 <- Reducer 43 (BROADCAST_EDGE), Reducer 54 (BROADCAST_EDGE), Reducer 55 (BROADCAST_EDGE), Reducer 65 (BROADCAST_EDGE) -Map 72 <- Reducer 31 (BROADCAST_EDGE), Reducer 35 (BROADCAST_EDGE), Reducer 39 (BROADCAST_EDGE), Reducer 43 (BROADCAST_EDGE), Reducer 45 (BROADCAST_EDGE), Reducer 48 (BROADCAST_EDGE), Reducer 58 (BROADCAST_EDGE), Reducer 63 (BROADCAST_EDGE), Reducer 67 (BROADCAST_EDGE), Reducer 68 (BROADCAST_EDGE), Reducer 71 (BROADCAST_EDGE) -Map 73 <- Reducer 45 (BROADCAST_EDGE), Reducer 59 (BROADCAST_EDGE), Reducer 60 (BROADCAST_EDGE), Reducer 67 (BROADCAST_EDGE) -Reducer 10 <- Reducer 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Map 37 <- Reducer 24 (BROADCAST_EDGE), Reducer 40 (BROADCAST_EDGE), Reducer 47 (BROADCAST_EDGE) +Map 44 <- Reducer 40 (BROADCAST_EDGE) +Map 55 <- Reducer 12 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE), Reducer 42 (BROADCAST_EDGE), Reducer 51 (BROADCAST_EDGE) +Map 56 <- Reducer 42 (BROADCAST_EDGE) +Reducer 10 <- Reducer 15 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Reducer 30 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 13 <- Map 69 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE), Reducer 41 (SIMPLE_EDGE) -Reducer 17 <- Map 46 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) -Reducer 18 <- Reducer 17 (SIMPLE_EDGE), Reducer 33 (SIMPLE_EDGE) -Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 51 (ONE_TO_ONE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) -Reducer 20 <- Map 61 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) -Reducer 21 <- Map 37 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) -Reducer 22 <- Map 64 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 23 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 24 <- Map 15 (SIMPLE_EDGE), Reducer 44 (SIMPLE_EDGE) -Reducer 25 <- Map 46 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) -Reducer 26 <- Reducer 25 (SIMPLE_EDGE), Reducer 33 (SIMPLE_EDGE) -Reducer 27 <- Reducer 26 (SIMPLE_EDGE), Reducer 57 (ONE_TO_ONE_EDGE) -Reducer 28 <- Map 61 (SIMPLE_EDGE), Reducer 27 (SIMPLE_EDGE) -Reducer 29 <- Map 37 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE) -Reducer 3 <- Map 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 30 <- Map 64 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE) -Reducer 31 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 32 (SIMPLE_EDGE), Map 36 (SIMPLE_EDGE) -Reducer 34 <- Reducer 33 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Reducer 33 (CUSTOM_SIMPLE_EDGE) -Reducer 38 <- Map 37 (CUSTOM_SIMPLE_EDGE) -Reducer 39 <- Map 37 (CUSTOM_SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 33 (SIMPLE_EDGE) -Reducer 41 <- Map 40 (SIMPLE_EDGE), Map 42 (SIMPLE_EDGE) -Reducer 43 <- Map 42 (CUSTOM_SIMPLE_EDGE) -Reducer 44 <- Map 42 (SIMPLE_EDGE), Map 72 (SIMPLE_EDGE) -Reducer 45 <- Map 42 (CUSTOM_SIMPLE_EDGE) -Reducer 47 <- Map 46 (CUSTOM_SIMPLE_EDGE) -Reducer 48 <- Map 46 (CUSTOM_SIMPLE_EDGE) -Reducer 5 <- Map 37 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 50 <- Map 49 (SIMPLE_EDGE), Map 53 (SIMPLE_EDGE) -Reducer 51 <- Reducer 50 (SIMPLE_EDGE) -Reducer 52 <- Reducer 51 (CUSTOM_SIMPLE_EDGE) -Reducer 54 <- Map 53 (CUSTOM_SIMPLE_EDGE) -Reducer 55 <- Map 53 (CUSTOM_SIMPLE_EDGE) -Reducer 56 <- Map 53 (SIMPLE_EDGE), Map 73 (SIMPLE_EDGE) -Reducer 57 <- Reducer 56 (SIMPLE_EDGE) -Reducer 58 <- Reducer 57 (CUSTOM_SIMPLE_EDGE) -Reducer 59 <- Map 53 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Map 69 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 60 <- Map 53 (CUSTOM_SIMPLE_EDGE) -Reducer 62 <- Map 61 (CUSTOM_SIMPLE_EDGE) -Reducer 63 <- Map 61 (CUSTOM_SIMPLE_EDGE) -Reducer 65 <- Map 64 (CUSTOM_SIMPLE_EDGE) -Reducer 66 <- Map 64 (CUSTOM_SIMPLE_EDGE) -Reducer 67 <- Map 64 (CUSTOM_SIMPLE_EDGE) -Reducer 68 <- Map 64 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 22 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 70 <- Map 69 (CUSTOM_SIMPLE_EDGE) -Reducer 71 <- Map 69 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Map 69 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 12 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Reducer 31 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 14 <- Map 54 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE) +Reducer 17 <- Map 16 (SIMPLE_EDGE), Reducer 38 (SIMPLE_EDGE) +Reducer 18 <- Map 43 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) +Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 46 (ONE_TO_ONE_EDGE) +Reducer 21 <- Map 52 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 22 <- Map 36 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) +Reducer 23 <- Map 53 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 24 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 25 <- Map 16 (SIMPLE_EDGE), Reducer 41 (SIMPLE_EDGE) +Reducer 26 <- Map 43 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) +Reducer 27 <- Reducer 26 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) +Reducer 28 <- Reducer 27 (SIMPLE_EDGE), Reducer 50 (ONE_TO_ONE_EDGE) +Reducer 29 <- Map 52 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE) +Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 30 <- Map 36 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE) +Reducer 31 <- Map 53 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE) +Reducer 32 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 34 <- Map 33 (SIMPLE_EDGE), Map 35 (SIMPLE_EDGE) +Reducer 38 <- Map 37 (SIMPLE_EDGE), Map 39 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE) +Reducer 40 <- Map 39 (CUSTOM_SIMPLE_EDGE) +Reducer 41 <- Map 39 (SIMPLE_EDGE), Map 55 (SIMPLE_EDGE) +Reducer 42 <- Map 39 (CUSTOM_SIMPLE_EDGE) +Reducer 45 <- Map 44 (SIMPLE_EDGE), Map 48 (SIMPLE_EDGE) +Reducer 46 <- Reducer 45 (SIMPLE_EDGE) +Reducer 47 <- Reducer 46 (CUSTOM_SIMPLE_EDGE) +Reducer 49 <- Map 48 (SIMPLE_EDGE), Map 56 (SIMPLE_EDGE) +Reducer 5 <- Map 36 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 50 <- Reducer 49 (SIMPLE_EDGE) +Reducer 51 <- Reducer 50 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Map 54 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 23 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Map 54 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 @@ -305,697 +288,501 @@ Stage-0 limit:-1 Stage-1 Reducer 11 vectorized - File Output Operator [FS_1283] - Select Operator [SEL_1282] (rows=273897192 width=88) + File Output Operator [FS_1201] + Select Operator [SEL_1200] (rows=2231770001 width=1702) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_259] - Select Operator [SEL_258] (rows=273897192 width=88) + Select Operator [SEL_258] (rows=2231770001 width=1694) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"] - Filter Operator [FIL_257] (rows=273897192 width=88) + Filter Operator [FIL_257] (rows=2231770001 width=1694) predicate:(_col19 <= _col12) - Merge Join Operator [MERGEJOIN_1087] (rows=821691577 width=88) - Conds:RS_1239._col2, _col1, _col3=RS_1281._col1, _col0, _col2(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col19","_col20","_col21","_col22"] - <-Reducer 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1281] - PartitionCols:_col1, _col0, _col2 - Select Operator [SEL_1280] (rows=746992327 width=88) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_1279] (rows=746992327 width=88) + Merge Join Operator [MERGEJOIN_1087] (rows=6695310003 width=1694) + Conds:RS_1171._col2, _col1, _col3=RS_1199._col1, _col0, _col2(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col19","_col20","_col21","_col22"] + <-Reducer 9 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1171] + PartitionCols:_col2, _col1, _col3 + Select Operator [SEL_1170] (rows=2331650 width=1354) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] + Group By Operator [GBY_1169] (rows=2331650 width=1362) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9, KEY._col10, KEY._col11, KEY._col12, KEY._col13 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_251] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_124] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Group By Operator [GBY_250] (rows=1493984654 width=88) + Group By Operator [GBY_123] (rows=2331650 width=1362) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col43)","sum(_col44)","sum(_col45)"],keys:_col28, _col46, _col29, _col7, _col9, _col14, _col15, _col16, _col17, _col23, _col24, _col25, _col26, _col49 - Select Operator [SEL_249] (rows=1493984654 width=88) + Select Operator [SEL_122] (rows=2331650 width=1292) Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49"] - Filter Operator [FIL_248] (rows=1493984654 width=88) + Filter Operator [FIL_121] (rows=2331650 width=1292) predicate:(_col56 <> _col19) - Merge Join Operator [MERGEJOIN_1086] (rows=1493984654 width=88) - Conds:RS_245._col37=RS_1129._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49","_col56"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1129] + Merge Join Operator [MERGEJOIN_1068] (rows=2331650 width=1292) + Conds:RS_118._col37=RS_1120._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49","_col56"] + <-Map 54 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1120] PartitionCols:_col0 - Select Operator [SEL_1125] (rows=1861800 width=385) + Select Operator [SEL_1119] (rows=1861800 width=89) Output:["_col0","_col1"] - Filter Operator [FIL_1124] (rows=1861800 width=385) + Filter Operator [FIL_1118] (rows=1861800 width=89) predicate:cd_demo_sk is not null - TableScan [TS_97] (rows=1861800 width=385) - default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_245] + TableScan [TS_97] (rows=1861800 width=89) + default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status"] + <-Reducer 7 [SIMPLE_EDGE] + SHUFFLE [RS_118] PartitionCols:_col37 - Merge Join Operator [MERGEJOIN_1085] (rows=1358167838 width=88) - Conds:RS_242._col0=RS_243._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col49"] + Merge Join Operator [MERGEJOIN_1067] (rows=2299138 width=1205) + Conds:RS_115._col0=RS_116._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col49"] <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_242] + SHUFFLE [RS_115] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1056] (rows=128840811 width=860) - Conds:RS_112._col1=RS_1128._col0(Inner),Output:["_col0","_col7","_col9","_col14","_col15","_col16","_col17","_col19"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1128] + Merge Join Operator [MERGEJOIN_1056] (rows=70357394 width=458) + Conds:RS_112._col1=RS_1121._col0(Inner),Output:["_col0","_col7","_col9","_col14","_col15","_col16","_col17","_col19"] + <-Map 54 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1121] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1125] + Please refer to the previous Select Operator [SEL_1119] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_112] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_1055] (rows=117128008 width=860) + Merge Join Operator [MERGEJOIN_1055] (rows=69376329 width=376) Conds:RS_109._col3=RS_1115._col0(Inner),Output:["_col0","_col1","_col7","_col9","_col14","_col15","_col16","_col17"] - <-Map 37 [SIMPLE_EDGE] vectorized + <-Map 36 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1115] PartitionCols:_col0 - Select Operator [SEL_1114] (rows=40000000 width=1014) + Select Operator [SEL_1114] (rows=40000000 width=365) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_1113] (rows=40000000 width=1014) + Filter Operator [FIL_1113] (rows=40000000 width=365) predicate:ca_address_sk is not null - TableScan [TS_19] (rows=40000000 width=1014) - default@customer_address,ad2,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] + TableScan [TS_19] (rows=40000000 width=365) + default@customer_address,ad2,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_city","ca_zip"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_1054] (rows=106480005 width=860) + Merge Join Operator [MERGEJOIN_1054] (rows=69376329 width=19) Conds:RS_106._col2=RS_107._col0(Inner),Output:["_col0","_col1","_col3","_col7","_col9"] - <-Reducer 33 [SIMPLE_EDGE] + <-Reducer 34 [SIMPLE_EDGE] SHUFFLE [RS_107] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1053] (rows=7920 width=107) + Merge Join Operator [MERGEJOIN_1053] (rows=7200 width=4) Conds:RS_1109._col1=RS_1112._col0(Inner),Output:["_col0"] - <-Map 32 [SIMPLE_EDGE] vectorized + <-Map 33 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1109] PartitionCols:_col1 - Select Operator [SEL_1108] (rows=7200 width=107) + Select Operator [SEL_1108] (rows=7200 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_1107] (rows=7200 width=107) + Filter Operator [FIL_1107] (rows=7200 width=8) predicate:(hd_demo_sk is not null and hd_income_band_sk is not null) - TableScan [TS_9] (rows=7200 width=107) - default@household_demographics,hd2,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"] - <-Map 36 [SIMPLE_EDGE] vectorized + TableScan [TS_9] (rows=7200 width=8) + default@household_demographics,hd2,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_income_band_sk"] + <-Map 35 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1112] PartitionCols:_col0 - Select Operator [SEL_1111] (rows=20 width=12) + Select Operator [SEL_1111] (rows=20 width=4) Output:["_col0"] - Filter Operator [FIL_1110] (rows=20 width=12) + Filter Operator [FIL_1110] (rows=20 width=4) predicate:ib_income_band_sk is not null - TableScan [TS_12] (rows=20 width=12) - default@income_band,ib2,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk"] + TableScan [TS_12] (rows=20 width=4) + default@income_band,ib2,Tbl:COMPLETE,Col:COMPLETE,Output:["ib_income_band_sk"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_106] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_1052] (rows=96800003 width=860) + Merge Join Operator [MERGEJOIN_1052] (rows=69376329 width=23) Conds:RS_103._col4=RS_1098._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col7","_col9"] - <-Map 15 [SIMPLE_EDGE] vectorized + <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1098] PartitionCols:_col0 - Select Operator [SEL_1094] (rows=73049 width=1119) + Select Operator [SEL_1094] (rows=73049 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_1091] (rows=73049 width=1119) + Filter Operator [FIL_1091] (rows=73049 width=8) predicate:d_date_sk is not null - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_103] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_1051] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_1051] (rows=69376329 width=23) Conds:RS_1090._col5=RS_1097._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col7"] - <-Map 15 [SIMPLE_EDGE] vectorized + <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_1097] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1094] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_1090] PartitionCols:_col5 - Select Operator [SEL_1089] (rows=80000000 width=860) + Select Operator [SEL_1089] (rows=69376329 width=23) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_1088] (rows=80000000 width=860) + Filter Operator [FIL_1088] (rows=69376329 width=23) predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_customer_sk is not null and c_first_sales_date_sk is not null and c_first_shipto_date_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk","c_first_shipto_date_sk","c_first_sales_date_sk"] - <-Reducer 30 [SIMPLE_EDGE] - SHUFFLE [RS_243] + TableScan [TS_0] (rows=80000000 width=23) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk","c_first_shipto_date_sk","c_first_sales_date_sk"] + <-Reducer 23 [SIMPLE_EDGE] + SHUFFLE [RS_116] PartitionCols:_col16 - Select Operator [SEL_223] (rows=1234698008 width=88) + Select Operator [SEL_96] (rows=2651207 width=784) Output:["_col3","_col4","_col5","_col6","_col8","_col9","_col16","_col17","_col23","_col24","_col25","_col26","_col29"] - Merge Join Operator [MERGEJOIN_1084] (rows=1234698008 width=88) - Conds:RS_220._col5, _col12=RS_1190._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] - <-Map 64 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1190] + Merge Join Operator [MERGEJOIN_1066] (rows=2651207 width=784) + Conds:RS_93._col5, _col12=RS_1167._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + <-Map 53 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1167] PartitionCols:_col0, _col1 - Select Operator [SEL_1186] (rows=57591150 width=77) + Select Operator [SEL_1166] (rows=57591150 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_1185] (rows=57591150 width=77) + Filter Operator [FIL_1165] (rows=57591150 width=8) predicate:(sr_item_sk is not null and sr_ticket_number is not null) - TableScan [TS_75] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"] - <-Reducer 29 [SIMPLE_EDGE] - SHUFFLE [RS_220] + TableScan [TS_75] (rows=57591150 width=8) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] + <-Reducer 22 [SIMPLE_EDGE] + SHUFFLE [RS_93] PartitionCols:_col5, _col12 - Merge Join Operator [MERGEJOIN_1083] (rows=1122452711 width=88) - Conds:RS_217._col9=RS_1118._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] - <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1118] + Merge Join Operator [MERGEJOIN_1065] (rows=1608052 width=657) + Conds:RS_90._col9=RS_1116._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + <-Map 36 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1116] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1114] - <-Reducer 28 [SIMPLE_EDGE] - SHUFFLE [RS_217] + <-Reducer 21 [SIMPLE_EDGE] + SHUFFLE [RS_90] PartitionCols:_col9 - Merge Join Operator [MERGEJOIN_1082] (rows=1020411534 width=88) - Conds:RS_214._col10=RS_1220._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27"] - <-Map 61 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1220] + Merge Join Operator [MERGEJOIN_1064] (rows=1608052 width=296) + Conds:RS_87._col10=RS_1163._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27"] + <-Map 52 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1163] PartitionCols:_col0 - Select Operator [SEL_1217] (rows=1704 width=1910) + Select Operator [SEL_1162] (rows=1704 width=181) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1216] (rows=1704 width=1910) + Filter Operator [FIL_1161] (rows=1704 width=181) predicate:(s_store_name is not null and s_store_sk is not null and s_zip is not null) - TableScan [TS_69] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_zip"] - <-Reducer 27 [SIMPLE_EDGE] - SHUFFLE [RS_214] + TableScan [TS_69] (rows=1704 width=181) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_zip"] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_87] PartitionCols:_col10 - Merge Join Operator [MERGEJOIN_1081] (rows=927646829 width=88) - Conds:RS_211._col5=RS_1262._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 57 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1262] + Merge Join Operator [MERGEJOIN_1063] (rows=1608052 width=119) + Conds:RS_84._col5=RS_1148._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] + <-Reducer 46 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1148] PartitionCols:_col0 - Select Operator [SEL_1261] (rows=52798137 width=135) + Select Operator [SEL_1147] (rows=13257 width=228) Output:["_col0"] - Filter Operator [FIL_1260] (rows=52798137 width=135) + Filter Operator [FIL_1146] (rows=13257 width=228) predicate:(_col1 > (2 * _col2)) - Group By Operator [GBY_1259] (rows=158394413 width=135) + Group By Operator [GBY_1145] (rows=39773 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 - <-Reducer 56 [SIMPLE_EDGE] - SHUFFLE [RS_192] + <-Reducer 45 [SIMPLE_EDGE] + SHUFFLE [RS_65] PartitionCols:_col0 - Group By Operator [GBY_191] (rows=316788826 width=135) + Group By Operator [GBY_64] (rows=12806906 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0 - Select Operator [SEL_189] (rows=316788826 width=135) + Select Operator [SEL_62] (rows=183085709 width=450) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_1079] (rows=316788826 width=135) - Conds:RS_1258._col0, _col1=RS_1170._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] - <-Map 53 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1170] + Merge Join Operator [MERGEJOIN_1061] (rows=183085709 width=450) + Conds:RS_1140._col0, _col1=RS_1143._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] + <-Map 48 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1143] PartitionCols:_col0, _col1 - Select Operator [SEL_1166] (rows=28798881 width=106) + Select Operator [SEL_1142] (rows=28798881 width=337) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_1165] (rows=28798881 width=106) + Filter Operator [FIL_1141] (rows=28798881 width=337) predicate:(cr_item_sk is not null and cr_order_number is not null) - TableScan [TS_56] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash","cr_reversed_charge","cr_store_credit"] - <-Map 73 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1258] + TableScan [TS_56] (rows=28798881 width=337) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash","cr_reversed_charge","cr_store_credit"] + <-Map 44 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1140] PartitionCols:_col0, _col1 - Select Operator [SEL_1257] (rows=287989836 width=135) + Select Operator [SEL_1139] (rows=287989836 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1256] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_171_item_i_item_sk_min) AND DynamicValue(RS_171_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_171_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_187_catalog_returns_cr_item_sk_min) AND DynamicValue(RS_187_catalog_returns_cr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_187_catalog_returns_cr_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_221_store_returns_sr_item_sk_min) AND DynamicValue(RS_221_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_221_store_returns_sr_item_sk_bloom_filter))) and (cs_order_number BETWEEN DynamicValue(RS_187_catalog_returns_cr_order_number_min) AND DynamicValue(RS_187_catalog_returns_cr_order_number_max) and in_bloom_filter(cs_order_number, DynamicValue(RS_187_catalog_returns_cr_order_number_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) - TableScan [TS_180] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] - <-Reducer 45 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1242] - Group By Operator [GBY_1240] (rows=1 width=12) + Filter Operator [FIL_1138] (rows=287989836 width=119) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_44_item_i_item_sk_min) AND DynamicValue(RS_44_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_44_item_i_item_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) + TableScan [TS_53] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] + <-Reducer 40 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1135] + Group By Operator [GBY_1133] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 42 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1144] - Group By Operator [GBY_1142] (rows=1 width=12) + <-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1131] + Group By Operator [GBY_1129] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1140] (rows=5703 width=1436) + Select Operator [SEL_1126] (rows=518 width=4) Output:["_col0"] - Select Operator [SEL_1136] (rows=5703 width=1436) + Select Operator [SEL_1124] (rows=518 width=312) Output:["_col0","_col3"] - Filter Operator [FIL_1135] (rows=5703 width=1436) + Filter Operator [FIL_1123] (rows=518 width=312) predicate:((i_color) IN ('maroon', 'burnished', 'dim', 'steel', 'navajo', 'chocolate') and i_current_price BETWEEN 35 AND 45 and i_current_price BETWEEN 36 AND 50 and i_item_sk is not null) - TableScan [TS_34] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] - <-Reducer 67 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1255] - Group By Operator [GBY_1253] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 64 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1199] - Group By Operator [GBY_1195] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_1191] (rows=57591150 width=77) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1186] - <-Reducer 59 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1250] - Group By Operator [GBY_1249] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=28798880)"] - <-Map 53 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1179] - Group By Operator [GBY_1175] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=28798880)"] - Select Operator [SEL_1171] (rows=28798881 width=106) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1166] - <-Reducer 60 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1252] - Group By Operator [GBY_1251] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=28798880)"] - <-Map 53 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1180] - Group By Operator [GBY_1176] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=28798880)"] - Select Operator [SEL_1172] (rows=28798881 width=106) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1166] - <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_211] + TableScan [TS_34] (rows=462000 width=311) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_color","i_product_name"] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_84] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_1080] (rows=843315281 width=88) - Conds:RS_208._col0=RS_209._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 33 [SIMPLE_EDGE] - SHUFFLE [RS_208] + Merge Join Operator [MERGEJOIN_1062] (rows=1608052 width=119) + Conds:RS_81._col0=RS_82._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] + <-Reducer 34 [SIMPLE_EDGE] + SHUFFLE [RS_81] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_1053] - <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_209] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_82] PartitionCols:_col5 - Select Operator [SEL_179] (rows=766650239 width=88) + Select Operator [SEL_52] (rows=1608052 width=119) Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col13","_col16"] - Merge Join Operator [MERGEJOIN_1078] (rows=766650239 width=88) - Conds:RS_176._col7=RS_1155._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 46 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1155] + Merge Join Operator [MERGEJOIN_1060] (rows=1608052 width=119) + Conds:RS_49._col7=RS_1159._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col15"] + <-Map 43 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1159] PartitionCols:_col0 - Select Operator [SEL_1152] (rows=2300 width=1179) + Select Operator [SEL_1158] (rows=2300 width=4) Output:["_col0"] - Filter Operator [FIL_1151] (rows=2300 width=1179) + Filter Operator [FIL_1157] (rows=2300 width=4) predicate:p_promo_sk is not null - TableScan [TS_40] (rows=2300 width=1179) - default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"] - <-Reducer 24 [SIMPLE_EDGE] - SHUFFLE [RS_176] + TableScan [TS_40] (rows=2300 width=4) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk"] + <-Reducer 17 [SIMPLE_EDGE] + SHUFFLE [RS_49] PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_1077] (rows=696954748 width=88) - Conds:RS_173._col0=RS_1101._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 15 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1101] + Merge Join Operator [MERGEJOIN_1059] (rows=1608052 width=119) + Conds:RS_46._col0=RS_1099._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1099] PartitionCols:_col0 - Select Operator [SEL_1096] (rows=36524 width=1119) + Select Operator [SEL_1095] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_1093] (rows=36524 width=1119) - predicate:((d_year = 2001) and d_date_sk is not null) + Filter Operator [FIL_1092] (rows=652 width=8) + predicate:((d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Reducer 44 [SIMPLE_EDGE] - SHUFFLE [RS_173] + <-Reducer 38 [SIMPLE_EDGE] + SHUFFLE [RS_46] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1076] (rows=633595212 width=88) - Conds:RS_1278._col1=RS_1139._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 42 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1139] + Merge Join Operator [MERGEJOIN_1058] (rows=4503592 width=119) + Conds:RS_1156._col1=RS_1125._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + <-Map 39 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1125] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1136] - <-Map 72 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1278] + Please refer to the previous Select Operator [SEL_1124] + <-Map 37 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1156] PartitionCols:_col1 - Select Operator [SEL_1277] (rows=575995635 width=88) + Select Operator [SEL_1155] (rows=417313408 width=355) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_1276] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_218_ad1_ca_address_sk_min) AND DynamicValue(RS_218_ad1_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_218_ad1_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_246_cd1_cd_demo_sk_min) AND DynamicValue(RS_246_cd1_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_246_cd1_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_208_hd1_hd_demo_sk_min) AND DynamicValue(RS_208_hd1_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_208_hd1_hd_demo_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_171_item_i_item_sk_min) AND DynamicValue(RS_171_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_171_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_212_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_212_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_212_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_221_store_returns_sr_item_sk_min) AND DynamicValue(RS_221_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_221_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_44_item_i_item_sk_min) AND DynamicValue(RS_44_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_44_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_177_promotion_p_promo_sk_min) AND DynamicValue(RS_177_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_177_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_174_d1_d_date_sk_min) AND DynamicValue(RS_174_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_174_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_215_store_s_store_sk_min) AND DynamicValue(RS_215_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_215_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_221_store_returns_sr_ticket_number_min) AND DynamicValue(RS_221_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_221_store_returns_sr_ticket_number_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_158] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] - <-Reducer 43 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1148] - Group By Operator [GBY_1145] (rows=1 width=12) + Filter Operator [FIL_1154] (rows=417313408 width=355) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_44_item_i_item_sk_min) AND DynamicValue(RS_44_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_44_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_85_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_85_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_85_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_47_d1_d_date_sk_min) AND DynamicValue(RS_47_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_47_d1_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_31] (rows=575995635 width=355) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] + <-Reducer 40 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1134] + Please refer to the previous Group By Operator [GBY_1133] + <-Reducer 24 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1137] + Group By Operator [GBY_1136] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 42 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1143] - Group By Operator [GBY_1141] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1138] (rows=5703 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1136] - <-Reducer 45 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1241] - Please refer to the previous Group By Operator [GBY_1240] - <-Reducer 67 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1254] - Please refer to the previous Group By Operator [GBY_1253] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1244] - Group By Operator [GBY_1243] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1106] - Group By Operator [GBY_1104] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1102] (rows=36524 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1096] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1248] - Group By Operator [GBY_1247] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 33 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_909] - Group By Operator [GBY_908] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_907] (rows=7920 width=107) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_1053] - <-Reducer 39 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1271] - Group By Operator [GBY_1270] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1123] - Group By Operator [GBY_1121] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_1119] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1114] - <-Reducer 48 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1246] - Group By Operator [GBY_1245] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 46 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1160] - Group By Operator [GBY_1158] (rows=1 width=12) + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1105] + Group By Operator [GBY_1103] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1156] (rows=2300 width=1179) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1152] - <-Reducer 58 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1267] - Group By Operator [GBY_1266] (rows=1 width=228) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=52798136)"] - <-Reducer 57 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1265] - Group By Operator [GBY_1264] (rows=1 width=228) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=52798136)"] - Select Operator [SEL_1263] (rows=52798137 width=135) + Select Operator [SEL_1100] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1261] - <-Reducer 63 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1269] - Group By Operator [GBY_1268] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_1095] + <-Reducer 47 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1153] + Group By Operator [GBY_1152] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 61 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1225] - Group By Operator [GBY_1223] (rows=1 width=12) + <-Reducer 46 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1151] + Group By Operator [GBY_1150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1221] (rows=1704 width=1910) + Select Operator [SEL_1149] (rows=13257 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1217] - <-Reducer 68 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1273] - Group By Operator [GBY_1272] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 64 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1200] - Group By Operator [GBY_1196] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_1192] (rows=57591150 width=77) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1186] - <-Reducer 71 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1275] - Group By Operator [GBY_1274] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1861800)"] - <-Map 69 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1134] - Group By Operator [GBY_1132] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1861800)"] - Select Operator [SEL_1130] (rows=1861800 width=385) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1125] - <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1239] - PartitionCols:_col2, _col1, _col3 - Select Operator [SEL_1238] (rows=746992327 width=88) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - Group By Operator [GBY_1237] (rows=746992327 width=88) + Please refer to the previous Select Operator [SEL_1147] + <-Reducer 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1199] + PartitionCols:_col1, _col0, _col2 + Select Operator [SEL_1198] (rows=2331650 width=525) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Group By Operator [GBY_1197] (rows=2331650 width=1362) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9, KEY._col10, KEY._col11, KEY._col12, KEY._col13 - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_124] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_251] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Group By Operator [GBY_123] (rows=1493984654 width=88) + Group By Operator [GBY_250] (rows=2331650 width=1362) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"],aggregations:["count()","sum(_col43)","sum(_col44)","sum(_col45)"],keys:_col28, _col46, _col29, _col7, _col9, _col14, _col15, _col16, _col17, _col23, _col24, _col25, _col26, _col49 - Select Operator [SEL_122] (rows=1493984654 width=88) + Select Operator [SEL_249] (rows=2331650 width=1292) Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49"] - Filter Operator [FIL_121] (rows=1493984654 width=88) + Filter Operator [FIL_248] (rows=2331650 width=1292) predicate:(_col56 <> _col19) - Merge Join Operator [MERGEJOIN_1068] (rows=1493984654 width=88) - Conds:RS_118._col37=RS_1126._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49","_col56"] - <-Map 69 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1126] + Merge Join Operator [MERGEJOIN_1086] (rows=2331650 width=1292) + Conds:RS_245._col37=RS_1122._col0(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col43","_col44","_col45","_col46","_col49","_col56"] + <-Map 54 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1122] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1125] - <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_118] + Please refer to the previous Select Operator [SEL_1119] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_245] PartitionCols:_col37 - Merge Join Operator [MERGEJOIN_1067] (rows=1358167838 width=88) - Conds:RS_115._col0=RS_116._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col49"] + Merge Join Operator [MERGEJOIN_1085] (rows=2299138 width=1205) + Conds:RS_242._col0=RS_243._col16(Inner),Output:["_col7","_col9","_col14","_col15","_col16","_col17","_col19","_col23","_col24","_col25","_col26","_col28","_col29","_col37","_col43","_col44","_col45","_col46","_col49"] <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_115] + SHUFFLE [RS_242] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_1056] - <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_116] + <-Reducer 31 [SIMPLE_EDGE] + SHUFFLE [RS_243] PartitionCols:_col16 - Select Operator [SEL_96] (rows=1234698008 width=88) + Select Operator [SEL_223] (rows=2651207 width=784) Output:["_col3","_col4","_col5","_col6","_col8","_col9","_col16","_col17","_col23","_col24","_col25","_col26","_col29"] - Merge Join Operator [MERGEJOIN_1066] (rows=1234698008 width=88) - Conds:RS_93._col5, _col12=RS_1187._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] - <-Map 64 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1187] + Merge Join Operator [MERGEJOIN_1084] (rows=2651207 width=784) + Conds:RS_220._col5, _col12=RS_1168._col0, _col1(Inner),Output:["_col6","_col7","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + <-Map 53 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1168] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_1186] - <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_93] + Please refer to the previous Select Operator [SEL_1166] + <-Reducer 30 [SIMPLE_EDGE] + SHUFFLE [RS_220] PartitionCols:_col5, _col12 - Merge Join Operator [MERGEJOIN_1065] (rows=1122452711 width=88) - Conds:RS_90._col9=RS_1116._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] - <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1116] + Merge Join Operator [MERGEJOIN_1083] (rows=1608052 width=657) + Conds:RS_217._col9=RS_1117._col0(Inner),Output:["_col5","_col6","_col7","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27","_col29","_col30","_col31","_col32"] + <-Map 36 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1117] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_1114] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_90] + <-Reducer 29 [SIMPLE_EDGE] + SHUFFLE [RS_217] PartitionCols:_col9 - Merge Join Operator [MERGEJOIN_1064] (rows=1020411534 width=88) - Conds:RS_87._col10=RS_1218._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27"] - <-Map 61 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1218] + Merge Join Operator [MERGEJOIN_1082] (rows=1608052 width=296) + Conds:RS_214._col10=RS_1164._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col12","_col13","_col14","_col15","_col16","_col19","_col26","_col27"] + <-Map 52 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1164] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1217] - <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_87] + Please refer to the previous Select Operator [SEL_1162] + <-Reducer 28 [SIMPLE_EDGE] + SHUFFLE [RS_214] PartitionCols:_col10 - Merge Join Operator [MERGEJOIN_1063] (rows=927646829 width=88) - Conds:RS_84._col5=RS_1210._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 51 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1210] + Merge Join Operator [MERGEJOIN_1081] (rows=1608052 width=119) + Conds:RS_211._col5=RS_1186._col0(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] + <-Reducer 50 [ONE_TO_ONE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1186] PartitionCols:_col0 - Select Operator [SEL_1209] (rows=52798137 width=135) + Select Operator [SEL_1185] (rows=13257 width=228) Output:["_col0"] - Filter Operator [FIL_1208] (rows=52798137 width=135) + Filter Operator [FIL_1184] (rows=13257 width=228) predicate:(_col1 > (2 * _col2)) - Group By Operator [GBY_1207] (rows=158394413 width=135) + Group By Operator [GBY_1183] (rows=39773 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 - <-Reducer 50 [SIMPLE_EDGE] - SHUFFLE [RS_65] + <-Reducer 49 [SIMPLE_EDGE] + SHUFFLE [RS_192] PartitionCols:_col0 - Group By Operator [GBY_64] (rows=316788826 width=135) + Group By Operator [GBY_191] (rows=12806906 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","sum(_col2)"],keys:_col0 - Select Operator [SEL_62] (rows=316788826 width=135) + Select Operator [SEL_189] (rows=183085709 width=450) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_1061] (rows=316788826 width=135) - Conds:RS_1206._col0, _col1=RS_1167._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] - <-Map 53 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1167] + Merge Join Operator [MERGEJOIN_1079] (rows=183085709 width=450) + Conds:RS_1182._col0, _col1=RS_1144._col0, _col1(Inner),Output:["_col0","_col2","_col5","_col6","_col7"] + <-Map 48 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1144] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_1166] - <-Map 49 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1206] + Please refer to the previous Select Operator [SEL_1142] + <-Map 56 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1182] PartitionCols:_col0, _col1 - Select Operator [SEL_1205] (rows=287989836 width=135) + Select Operator [SEL_1181] (rows=287989836 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_1204] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_44_item_i_item_sk_min) AND DynamicValue(RS_44_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_44_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_60_catalog_returns_cr_item_sk_min) AND DynamicValue(RS_60_catalog_returns_cr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_60_catalog_returns_cr_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_94_store_returns_sr_item_sk_min) AND DynamicValue(RS_94_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_94_store_returns_sr_item_sk_bloom_filter))) and (cs_order_number BETWEEN DynamicValue(RS_60_catalog_returns_cr_order_number_min) AND DynamicValue(RS_60_catalog_returns_cr_order_number_max) and in_bloom_filter(cs_order_number, DynamicValue(RS_60_catalog_returns_cr_order_number_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) - TableScan [TS_53] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] - <-Reducer 43 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1147] - Please refer to the previous Group By Operator [GBY_1145] - <-Reducer 65 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1203] - Group By Operator [GBY_1201] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 64 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1197] - Group By Operator [GBY_1193] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_1188] (rows=57591150 width=77) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1186] - <-Reducer 54 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1182] - Group By Operator [GBY_1181] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=28798880)"] - <-Map 53 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1177] - Group By Operator [GBY_1173] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=28798880)"] - Select Operator [SEL_1168] (rows=28798881 width=106) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1166] - <-Reducer 55 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1184] - Group By Operator [GBY_1183] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=28798880)"] - <-Map 53 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1178] - Group By Operator [GBY_1174] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=28798880)"] - Select Operator [SEL_1169] (rows=28798881 width=106) + Filter Operator [FIL_1180] (rows=287989836 width=119) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_171_item_i_item_sk_min) AND DynamicValue(RS_171_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_171_item_i_item_sk_bloom_filter))) and cs_item_sk is not null and cs_order_number is not null) + TableScan [TS_180] (rows=287989836 width=119) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_item_sk","cs_order_number","cs_ext_list_price"] + <-Reducer 42 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1177] + Group By Operator [GBY_1175] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1132] + Group By Operator [GBY_1130] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_1128] (rows=518 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1166] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_84] + Please refer to the previous Select Operator [SEL_1124] + <-Reducer 27 [SIMPLE_EDGE] + SHUFFLE [RS_211] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_1062] (rows=843315281 width=88) - Conds:RS_81._col0=RS_82._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] - <-Reducer 33 [SIMPLE_EDGE] - SHUFFLE [RS_81] + Merge Join Operator [MERGEJOIN_1080] (rows=1608052 width=119) + Conds:RS_208._col0=RS_209._col5(Inner),Output:["_col5","_col6","_col7","_col9","_col10","_col12","_col13","_col14","_col15","_col16","_col19"] + <-Reducer 34 [SIMPLE_EDGE] + SHUFFLE [RS_208] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_1053] - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_82] + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_209] PartitionCols:_col5 - Select Operator [SEL_52] (rows=766650239 width=88) + Select Operator [SEL_179] (rows=1608052 width=119) Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col13","_col16"] - Merge Join Operator [MERGEJOIN_1060] (rows=766650239 width=88) - Conds:RS_49._col7=RS_1153._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 46 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1153] + Merge Join Operator [MERGEJOIN_1078] (rows=1608052 width=119) + Conds:RS_176._col7=RS_1160._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11","_col12","_col15"] + <-Map 43 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1160] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1152] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_49] + Please refer to the previous Select Operator [SEL_1158] + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_176] PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_1059] (rows=696954748 width=88) - Conds:RS_46._col0=RS_1099._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 15 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1099] + Merge Join Operator [MERGEJOIN_1077] (rows=1608052 width=119) + Conds:RS_173._col0=RS_1101._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1101] PartitionCols:_col0 - Select Operator [SEL_1095] (rows=36524 width=1119) + Select Operator [SEL_1096] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_1092] (rows=36524 width=1119) - predicate:((d_year = 2000) and d_date_sk is not null) + Filter Operator [FIL_1093] (rows=652 width=8) + predicate:((d_year = 2001) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Reducer 41 [SIMPLE_EDGE] - SHUFFLE [RS_46] + SHUFFLE [RS_173] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_1058] (rows=633595212 width=88) - Conds:RS_1236._col1=RS_1137._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] - <-Map 42 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1137] + Merge Join Operator [MERGEJOIN_1076] (rows=4503592 width=119) + Conds:RS_1196._col1=RS_1127._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col15"] + <-Map 39 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1127] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_1136] - <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_1236] + Please refer to the previous Select Operator [SEL_1124] + <-Map 55 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_1196] PartitionCols:_col1 - Select Operator [SEL_1235] (rows=575995635 width=88) + Select Operator [SEL_1195] (rows=417313408 width=355) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_1234] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_91_ad1_ca_address_sk_min) AND DynamicValue(RS_91_ad1_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_91_ad1_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_119_cd1_cd_demo_sk_min) AND DynamicValue(RS_119_cd1_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_119_cd1_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_81_hd1_hd_demo_sk_min) AND DynamicValue(RS_81_hd1_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_81_hd1_hd_demo_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_44_item_i_item_sk_min) AND DynamicValue(RS_44_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_44_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_85_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_85_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_85_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_94_store_returns_sr_item_sk_min) AND DynamicValue(RS_94_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_94_store_returns_sr_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_50_promotion_p_promo_sk_min) AND DynamicValue(RS_50_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_50_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_47_d1_d_date_sk_min) AND DynamicValue(RS_47_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_47_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_88_store_s_store_sk_min) AND DynamicValue(RS_88_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_88_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_94_store_returns_sr_ticket_number_min) AND DynamicValue(RS_94_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_94_store_returns_sr_ticket_number_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_31] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] - <-Reducer 43 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1146] - Please refer to the previous Group By Operator [GBY_1145] - <-Reducer 65 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1202] - Please refer to the previous Group By Operator [GBY_1201] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1150] - Group By Operator [GBY_1149] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1105] - Group By Operator [GBY_1103] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1100] (rows=36524 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1095] - <-Reducer 34 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1164] - Group By Operator [GBY_1163] (rows=1 width=12) + Filter Operator [FIL_1194] (rows=417313408 width=355) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_171_item_i_item_sk_min) AND DynamicValue(RS_171_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_171_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_212_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_212_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_212_catalog_sales_cs_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_254_item_i_item_sk_min) AND DynamicValue(RS_254_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_254_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_174_d1_d_date_sk_min) AND DynamicValue(RS_174_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_174_d1_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_158] (rows=575995635 width=355) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] + <-Reducer 42 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1176] + Please refer to the previous Group By Operator [GBY_1175] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1193] + Group By Operator [GBY_1192] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 33 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_674] - Group By Operator [GBY_673] (rows=1 width=12) + <-Reducer 9 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1174] + Group By Operator [GBY_1173] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_672] (rows=7920 width=107) + Select Operator [SEL_1172] (rows=2331650 width=8) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_1053] - <-Reducer 38 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1229] - Group By Operator [GBY_1228] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1122] - Group By Operator [GBY_1120] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_1117] (rows=40000000 width=1014) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1114] - <-Reducer 47 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1162] - Group By Operator [GBY_1161] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_1170] + <-Reducer 32 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1179] + Group By Operator [GBY_1178] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 46 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1159] - Group By Operator [GBY_1157] (rows=1 width=12) + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1106] + Group By Operator [GBY_1104] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1154] (rows=2300 width=1179) + Select Operator [SEL_1102] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1152] - <-Reducer 52 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1215] - Group By Operator [GBY_1214] (rows=1 width=228) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=52798136)"] - <-Reducer 51 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1213] - Group By Operator [GBY_1212] (rows=1 width=228) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=52798136)"] - Select Operator [SEL_1211] (rows=52798137 width=135) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1209] - <-Reducer 62 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1227] - Group By Operator [GBY_1226] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_1096] + <-Reducer 51 [BROADCAST_EDGE] vectorized + BROADCAST [RS_1191] + Group By Operator [GBY_1190] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 61 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1224] - Group By Operator [GBY_1222] (rows=1 width=12) + <-Reducer 50 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_1189] + Group By Operator [GBY_1188] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_1219] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1217] - <-Reducer 66 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1231] - Group By Operator [GBY_1230] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] - <-Map 64 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_1198] - Group By Operator [GBY_1194] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] - Select Operator [SEL_1189] (rows=57591150 width=77) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_1186] - <-Reducer 70 [BROADCAST_EDGE] vectorized - BROADCAST [RS_1233] - Group By Operator [GBY_1232] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1861800)"] - <-Map 69 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_1133] - Group By Operator [GBY_1131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1861800)"] - Select Operator [SEL_1127] (rows=1861800 width=385) + Select Operator [SEL_1187] (rows=13257 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_1125] + Please refer to the previous Select Operator [SEL_1185] diff --git a/ql/src/test/results/clientpositive/perf/tez/query65.q.out b/ql/src/test/results/clientpositive/perf/tez/query65.q.out index c9759c396d..12e9e7cedf 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query65.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query65.q.out @@ -57,167 +57,152 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 12 <- Reducer 11 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) +Map 13 <- Reducer 12 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Reducer 10 <- Map 13 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Map 15 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_176] - Limit [LIM_175] (rows=100 width=88) + File Output Operator [FS_170] + Limit [LIM_169] (rows=100 width=701) Number of rows:100 - Select Operator [SEL_174] (rows=255550079 width=88) + Select Operator [SEL_168] (rows=28035 width=698) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_48] - Select Operator [SEL_47] (rows=255550079 width=88) + Select Operator [SEL_47] (rows=28035 width=698) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_129] (rows=255550079 width=88) - Conds:RS_44._col1=RS_153._col0(Inner),Output:["_col2","_col6","_col8","_col9","_col10","_col11"] + Merge Join Operator [MERGEJOIN_129] (rows=28035 width=698) + Conds:RS_44._col1=RS_167._col0(Inner),Output:["_col2","_col6","_col8","_col9","_col10","_col11"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_153] + SHUFFLE [RS_167] PartitionCols:_col0 - Select Operator [SEL_152] (rows=462000 width=1436) + Select Operator [SEL_166] (rows=462000 width=511) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_151] (rows=462000 width=1436) + Filter Operator [FIL_165] (rows=462000 width=511) predicate:i_item_sk is not null - TableScan [TS_36] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc","i_current_price","i_wholesale_cost","i_brand"] + TableScan [TS_36] (rows=462000 width=511) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc","i_current_price","i_wholesale_cost","i_brand"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col1 - Filter Operator [FIL_43] (rows=232318249 width=88) + Filter Operator [FIL_43] (rows=28035 width=316) predicate:(_col2 <= (0.1 * _col4)) - Merge Join Operator [MERGEJOIN_128] (rows=696954748 width=88) - Conds:RS_163._col0=RS_173._col0(Inner),RS_163._col0=RS_144._col0(Inner),Output:["_col1","_col2","_col4","_col6"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_144] + Merge Join Operator [MERGEJOIN_128] (rows=84107 width=316) + Conds:RS_146._col0=RS_161._col0(Inner),RS_146._col0=RS_164._col0(Inner),Output:["_col1","_col2","_col4","_col6"] + <-Reducer 3 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_146] + PartitionCols:_col0 + Group By Operator [GBY_145] (rows=76461 width=118) + Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_11] + PartitionCols:_col0, _col1 + Group By Operator [GBY_10] (rows=1299837 width=118) + Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 + Merge Join Operator [MERGEJOIN_126] (rows=58365993 width=73) + Conds:RS_144._col0=RS_132._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_132] + PartitionCols:_col0 + Select Operator [SEL_131] (rows=8116 width=8) + Output:["_col0"] + Filter Operator [FIL_130] (rows=8116 width=8) + predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_144] + PartitionCols:_col0 + Select Operator [SEL_143] (rows=525329897 width=118) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_142] (rows=525329897 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_141] + Group By Operator [GBY_140] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_138] + Group By Operator [GBY_136] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_133] (rows=8116 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_131] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_164] PartitionCols:_col0 - Select Operator [SEL_143] (rows=1704 width=1910) + Select Operator [SEL_163] (rows=1704 width=92) Output:["_col0","_col1"] - Filter Operator [FIL_142] (rows=1704 width=1910) + Filter Operator [FIL_162] (rows=1704 width=92) predicate:s_store_sk is not null - TableScan [TS_33] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name"] - <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_173] + TableScan [TS_33] (rows=1704 width=92) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name"] + <-Reducer 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_161] PartitionCols:_col0 - Select Operator [SEL_172] (rows=158398803 width=88) + Select Operator [SEL_160] (rows=11 width=114) Output:["_col0","_col1"] - Group By Operator [GBY_171] (rows=158398803 width=88) + Group By Operator [GBY_159] (rows=11 width=122) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Select Operator [SEL_170] (rows=316797606 width=88) + Select Operator [SEL_158] (rows=76461 width=118) Output:["_col1","_col2"] - Group By Operator [GBY_169] (rows=316797606 width=88) + Group By Operator [GBY_157] (rows=76461 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Group By Operator [GBY_24] (rows=633595212 width=88) + Group By Operator [GBY_24] (rows=1299837 width=118) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_127] (rows=633595212 width=88) - Conds:RS_168._col0=RS_134._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_134] + Merge Join Operator [MERGEJOIN_127] (rows=58365993 width=73) + Conds:RS_156._col0=RS_134._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_134] PartitionCols:_col0 - Select Operator [SEL_131] (rows=8116 width=1119) - Output:["_col0"] - Filter Operator [FIL_130] (rows=8116 width=1119) - predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_168] + Please refer to the previous Select Operator [SEL_131] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_156] PartitionCols:_col0 - Select Operator [SEL_167] (rows=575995635 width=88) + Select Operator [SEL_155] (rows=525329897 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_166] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_21_date_dim_d_date_sk_min) AND DynamicValue(RS_21_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_21_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_41_store_s_store_sk_min) AND DynamicValue(RS_41_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_41_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_14] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_150] - Group By Operator [GBY_148] (rows=1 width=12) + Filter Operator [FIL_154] (rows=525329897 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_21_date_dim_d_date_sk_min) AND DynamicValue(RS_21_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_21_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_39_store_sales_ss_store_sk_min) AND DynamicValue(RS_39_store_sales_ss_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_39_store_sales_ss_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_14] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_151] + Group By Operator [GBY_150] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_147] - Group By Operator [GBY_146] (rows=1 width=12) + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_139] + Group By Operator [GBY_137] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_145] (rows=1704 width=1910) + Select Operator [SEL_135] (rows=8116 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_143] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_165] - Group By Operator [GBY_164] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_131] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_153] + Group By Operator [GBY_152] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_139] - Group By Operator [GBY_137] (rows=1 width=12) + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_149] + Group By Operator [GBY_148] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_135] (rows=8116 width=1119) + Select Operator [SEL_147] (rows=76461 width=2) Output:["_col0"] - Please refer to the previous Select Operator [SEL_131] - <-Reducer 3 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_163] - PartitionCols:_col0 - Group By Operator [GBY_162] (rows=316797606 width=88) - Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_11] - PartitionCols:_col0, _col1 - Group By Operator [GBY_10] (rows=633595212 width=88) - Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_126] (rows=633595212 width=88) - Conds:RS_161._col0=RS_132._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_132] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_131] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_161] - PartitionCols:_col0 - Select Operator [SEL_160] (rows=575995635 width=88) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_159] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_45_item_i_item_sk_min) AND DynamicValue(RS_45_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_45_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_41_store_s_store_sk_min) AND DynamicValue(RS_41_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_41_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_149] - Please refer to the previous Group By Operator [GBY_148] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_158] - Group By Operator [GBY_157] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_156] - Group By Operator [GBY_155] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_154] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_152] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_141] - Group By Operator [GBY_140] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_138] - Group By Operator [GBY_136] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_133] (rows=8116 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_131] + Please refer to the previous Group By Operator [GBY_145] diff --git a/ql/src/test/results/clientpositive/perf/tez/query66.q.out b/ql/src/test/results/clientpositive/perf/tez/query66.q.out index 432dd7e710..62642ba39c 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query66.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query66.q.out @@ -443,10 +443,10 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE) -Map 27 <- Reducer 17 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE) +Map 25 <- Reducer 17 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 10 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE) +Reducer 12 <- Map 10 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE) Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Map 21 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) Reducer 15 <- Map 24 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) @@ -457,8 +457,6 @@ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) Reducer 20 <- Map 18 (CUSTOM_SIMPLE_EDGE) Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) Reducer 23 <- Map 21 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 24 (CUSTOM_SIMPLE_EDGE) -Reducer 26 <- Map 24 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 18 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Map 24 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) @@ -471,170 +469,159 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_278] - Select Operator [SEL_277] (rows=100 width=135) + File Output Operator [FS_270] + Select Operator [SEL_269] (rows=100 width=4614) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41","_col42","_col43"] - Limit [LIM_276] (rows=100 width=135) + Limit [LIM_268] (rows=100 width=4510) Number of rows:100 - Select Operator [SEL_275] (rows=158120068 width=135) + Select Operator [SEL_267] (rows=2513700 width=4509) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_274] - Group By Operator [GBY_273] (rows=158120068 width=135) + SHUFFLE [RS_266] + Group By Operator [GBY_265] (rows=2513700 width=4509) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","sum(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)","sum(VALUE._col12)","sum(VALUE._col13)","sum(VALUE._col14)","sum(VALUE._col15)","sum(VALUE._col16)","sum(VALUE._col17)","sum(VALUE._col18)","sum(VALUE._col19)","sum(VALUE._col20)","sum(VALUE._col21)","sum(VALUE._col22)","sum(VALUE._col23)","sum(VALUE._col24)","sum(VALUE._col25)","sum(VALUE._col26)","sum(VALUE._col27)","sum(VALUE._col28)","sum(VALUE._col29)","sum(VALUE._col30)","sum(VALUE._col31)","sum(VALUE._col32)","sum(VALUE._col33)","sum(VALUE._col34)","sum(VALUE._col35)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 7 [SIMPLE_EDGE] <-Reducer 16 [CONTAINS] vectorized - Reduce Output Operator [RS_294] + Reduce Output Operator [RS_284] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_293] (rows=316240137 width=135) + Group By Operator [GBY_283] (rows=5027400 width=4509) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)","sum(_col30)","sum(_col31)","sum(_col32)","sum(_col33)","sum(_col34)","sum(_col35)","sum(_col36)","sum(_col37)","sum(_col38)","sum(_col39)","sum(_col40)","sum(_col41)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Top N Key Operator [TNK_292] (rows=316240137 width=135) + Top N Key Operator [TNK_282] (rows=5027400 width=3166) keys:_col0, _col1, _col2, _col3, _col4, _col5,sort order:++++++,top n:100 - Select Operator [SEL_291] (rows=316240137 width=135) + Select Operator [SEL_281] (rows=5027400 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41"] - Group By Operator [GBY_290] (rows=210822976 width=135) + Group By Operator [GBY_280] (rows=2513700 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","sum(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)","sum(VALUE._col12)","sum(VALUE._col13)","sum(VALUE._col14)","sum(VALUE._col15)","sum(VALUE._col16)","sum(VALUE._col17)","sum(VALUE._col18)","sum(VALUE._col19)","sum(VALUE._col20)","sum(VALUE._col21)","sum(VALUE._col22)","sum(VALUE._col23)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_62] (rows=421645953 width=135) + Group By Operator [GBY_62] (rows=5559759 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_60] (rows=421645953 width=135) + Select Operator [SEL_60] (rows=5559759 width=680) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_204] (rows=421645953 width=135) - Conds:RS_57._col3=RS_257._col0(Inner),Output:["_col4","_col5","_col6","_col11","_col15","_col16","_col17","_col18","_col19","_col20"] + Merge Join Operator [MERGEJOIN_204] (rows=5559759 width=680) + Conds:RS_57._col3=RS_259._col0(Inner),Output:["_col4","_col5","_col6","_col11","_col15","_col16","_col17","_col18","_col19","_col20"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_257] + SHUFFLE [RS_259] PartitionCols:_col0 - Select Operator [SEL_254] (rows=27 width=1029) + Select Operator [SEL_257] (rows=27 width=482) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_253] (rows=27 width=1029) + Filter Operator [FIL_256] (rows=27 width=482) predicate:w_warehouse_sk is not null - TableScan [TS_12] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name","w_warehouse_sq_ft","w_city","w_county","w_state","w_country"] + TableScan [TS_12] (rows=27 width=482) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name","w_warehouse_sq_ft","w_city","w_county","w_state","w_country"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_203] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_203] (rows=5559759 width=205) Conds:RS_54._col2=RS_245._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col11"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_245] PartitionCols:_col0 - Select Operator [SEL_242] (rows=1 width=0) + Select Operator [SEL_242] (rows=1 width=88) Output:["_col0"] - Filter Operator [FIL_241] (rows=1 width=0) + Filter Operator [FIL_241] (rows=1 width=88) predicate:((sm_carrier) IN ('DIAMOND', 'AIRBORNE') and sm_ship_mode_sk is not null) - TableScan [TS_9] (rows=1 width=0) - default@ship_mode,ship_mode,Tbl:PARTIAL,Col:NONE,Output:["sm_ship_mode_sk","sm_carrier"] + TableScan [TS_9] (rows=1 width=88) + default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_carrier"] <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_54] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_202] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_202] (rows=11119518 width=224) Conds:RS_51._col0=RS_233._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col11"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_233] PartitionCols:_col0 - Select Operator [SEL_230] (rows=36524 width=1119) + Select Operator [SEL_230] (rows=652 width=12) Output:["_col0","_col2"] - Filter Operator [FIL_229] (rows=36524 width=1119) + Filter Operator [FIL_229] (rows=652 width=12) predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_51] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_201] (rows=316788826 width=135) - Conds:RS_289._col1=RS_221._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6"] + Merge Join Operator [MERGEJOIN_201] (rows=31363607 width=234) + Conds:RS_279._col1=RS_221._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_218] (rows=9600 width=471) + Select Operator [SEL_218] (rows=9600 width=8) Output:["_col0"] - Filter Operator [FIL_217] (rows=9600 width=471) + Filter Operator [FIL_217] (rows=9600 width=8) predicate:(t_time BETWEEN 49530 AND 78330 and t_time_sk is not null) - TableScan [TS_3] (rows=86400 width=471) - default@time_dim,time_dim,Tbl:COMPLETE,Col:NONE,Output:["t_time_sk","t_time"] - <-Map 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_289] + TableScan [TS_3] (rows=86400 width=8) + default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_time"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_279] PartitionCols:_col1 - Select Operator [SEL_288] (rows=287989836 width=135) + Select Operator [SEL_278] (rows=282272460 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_287] (rows=287989836 width=135) - predicate:((cs_ship_mode_sk BETWEEN DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_52_date_dim_d_date_sk_min) AND DynamicValue(RS_52_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_52_date_dim_d_date_sk_bloom_filter))) and (cs_sold_time_sk BETWEEN DynamicValue(RS_49_time_dim_t_time_sk_min) AND DynamicValue(RS_49_time_dim_t_time_sk_max) and in_bloom_filter(cs_sold_time_sk, DynamicValue(RS_49_time_dim_t_time_sk_bloom_filter))) and (cs_warehouse_sk BETWEEN DynamicValue(RS_58_warehouse_w_warehouse_sk_min) AND DynamicValue(RS_58_warehouse_w_warehouse_sk_max) and in_bloom_filter(cs_warehouse_sk, DynamicValue(RS_58_warehouse_w_warehouse_sk_bloom_filter))) and cs_ship_mode_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null and cs_warehouse_sk is not null) - TableScan [TS_33] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_sold_time_sk","cs_ship_mode_sk","cs_warehouse_sk","cs_quantity","cs_ext_sales_price","cs_net_paid_inc_ship_tax"] + Filter Operator [FIL_277] (rows=282272460 width=243) + predicate:((cs_ship_mode_sk BETWEEN DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_55_ship_mode_sm_ship_mode_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_52_date_dim_d_date_sk_min) AND DynamicValue(RS_52_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_52_date_dim_d_date_sk_bloom_filter))) and (cs_sold_time_sk BETWEEN DynamicValue(RS_49_time_dim_t_time_sk_min) AND DynamicValue(RS_49_time_dim_t_time_sk_max) and in_bloom_filter(cs_sold_time_sk, DynamicValue(RS_49_time_dim_t_time_sk_bloom_filter))) and cs_ship_mode_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null and cs_warehouse_sk is not null) + TableScan [TS_33] (rows=287989836 width=243) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_sold_time_sk","cs_ship_mode_sk","cs_warehouse_sk","cs_quantity","cs_ext_sales_price","cs_net_paid_inc_ship_tax"] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_280] - Group By Operator [GBY_279] (rows=1 width=12) + BROADCAST [RS_272] + Group By Operator [GBY_271] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_226] Group By Operator [GBY_224] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_222] (rows=9600 width=471) + Select Operator [SEL_222] (rows=9600 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_218] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_282] - Group By Operator [GBY_281] (rows=1 width=12) + BROADCAST [RS_274] + Group By Operator [GBY_273] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_238] Group By Operator [GBY_236] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_234] (rows=36524 width=1119) + Select Operator [SEL_234] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_230] <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_284] - Group By Operator [GBY_283] (rows=1 width=12) + BROADCAST [RS_276] + Group By Operator [GBY_275] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_250] Group By Operator [GBY_248] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_246] (rows=1 width=0) + Select Operator [SEL_246] (rows=1 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_242] - <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_286] - Group By Operator [GBY_285] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_262] - Group By Operator [GBY_260] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_258] (rows=27 width=1029) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_254] <-Reducer 6 [CONTAINS] vectorized - Reduce Output Operator [RS_272] + Reduce Output Operator [RS_264] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_271] (rows=316240137 width=135) + Group By Operator [GBY_263] (rows=5027400 width=4509) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)","sum(_col30)","sum(_col31)","sum(_col32)","sum(_col33)","sum(_col34)","sum(_col35)","sum(_col36)","sum(_col37)","sum(_col38)","sum(_col39)","sum(_col40)","sum(_col41)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Top N Key Operator [TNK_270] (rows=316240137 width=135) + Top N Key Operator [TNK_262] (rows=5027400 width=3166) keys:_col0, _col1, _col2, _col3, _col4, _col5,sort order:++++++,top n:100 - Select Operator [SEL_269] (rows=316240137 width=135) + Select Operator [SEL_261] (rows=5027400 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41"] - Group By Operator [GBY_268] (rows=105417161 width=135) + Group By Operator [GBY_260] (rows=2513700 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","sum(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)","sum(VALUE._col12)","sum(VALUE._col13)","sum(VALUE._col14)","sum(VALUE._col15)","sum(VALUE._col16)","sum(VALUE._col17)","sum(VALUE._col18)","sum(VALUE._col19)","sum(VALUE._col20)","sum(VALUE._col21)","sum(VALUE._col22)","sum(VALUE._col23)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_29] (rows=210834322 width=135) + Group By Operator [GBY_29] (rows=2853684 width=3166) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)","sum(_col9)","sum(_col10)","sum(_col11)","sum(_col12)","sum(_col13)","sum(_col14)","sum(_col15)","sum(_col16)","sum(_col17)","sum(_col18)","sum(_col19)","sum(_col20)","sum(_col21)","sum(_col22)","sum(_col23)","sum(_col24)","sum(_col25)","sum(_col26)","sum(_col27)","sum(_col28)","sum(_col29)"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_27] (rows=210834322 width=135) + Select Operator [SEL_27] (rows=2853684 width=707) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29"] - Merge Join Operator [MERGEJOIN_200] (rows=210834322 width=135) - Conds:RS_24._col3=RS_255._col0(Inner),Output:["_col4","_col5","_col6","_col11","_col15","_col16","_col17","_col18","_col19","_col20"] + Merge Join Operator [MERGEJOIN_200] (rows=2853684 width=707) + Conds:RS_24._col3=RS_258._col0(Inner),Output:["_col4","_col5","_col6","_col11","_col15","_col16","_col17","_col18","_col19","_col20"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_255] + SHUFFLE [RS_258] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_254] + Please refer to the previous Select Operator [SEL_257] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_199] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_199] (rows=2853684 width=233) Conds:RS_21._col2=RS_243._col0(Inner),Output:["_col3","_col4","_col5","_col6","_col11"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_243] @@ -643,7 +630,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_198] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_198] (rows=5707369 width=238) Conds:RS_18._col0=RS_231._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col11"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_231] @@ -652,21 +639,21 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_197] (rows=158402938 width=135) - Conds:RS_267._col1=RS_219._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6"] + Merge Join Operator [MERGEJOIN_197] (rows=15984351 width=239) + Conds:RS_255._col1=RS_219._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_219] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_218] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_267] + SHUFFLE [RS_255] PartitionCols:_col1 - Select Operator [SEL_266] (rows=144002668 width=135) + Select Operator [SEL_254] (rows=143859154 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_265] (rows=144002668 width=135) - predicate:((ws_ship_mode_sk BETWEEN DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(ws_ship_mode_sk, DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_16_time_dim_t_time_sk_min) AND DynamicValue(RS_16_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_16_time_dim_t_time_sk_bloom_filter))) and (ws_warehouse_sk BETWEEN DynamicValue(RS_25_warehouse_w_warehouse_sk_min) AND DynamicValue(RS_25_warehouse_w_warehouse_sk_max) and in_bloom_filter(ws_warehouse_sk, DynamicValue(RS_25_warehouse_w_warehouse_sk_bloom_filter))) and ws_ship_mode_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null and ws_warehouse_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_sold_time_sk","ws_ship_mode_sk","ws_warehouse_sk","ws_quantity","ws_sales_price","ws_net_paid_inc_tax"] + Filter Operator [FIL_253] (rows=143859154 width=243) + predicate:((ws_ship_mode_sk BETWEEN DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(ws_ship_mode_sk, DynamicValue(RS_22_ship_mode_sm_ship_mode_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_16_time_dim_t_time_sk_min) AND DynamicValue(RS_16_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_16_time_dim_t_time_sk_bloom_filter))) and ws_ship_mode_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null and ws_warehouse_sk is not null) + TableScan [TS_0] (rows=144002668 width=243) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_sold_time_sk","ws_ship_mode_sk","ws_warehouse_sk","ws_quantity","ws_sales_price","ws_net_paid_inc_tax"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_228] Group By Operator [GBY_227] (rows=1 width=12) @@ -675,7 +662,7 @@ Stage-0 SHUFFLE [RS_225] Group By Operator [GBY_223] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_220] (rows=9600 width=471) + Select Operator [SEL_220] (rows=9600 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_218] <-Reducer 19 [BROADCAST_EDGE] vectorized @@ -686,7 +673,7 @@ Stage-0 SHUFFLE [RS_237] Group By Operator [GBY_235] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_232] (rows=36524 width=1119) + Select Operator [SEL_232] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_230] <-Reducer 22 [BROADCAST_EDGE] vectorized @@ -697,18 +684,7 @@ Stage-0 SHUFFLE [RS_249] Group By Operator [GBY_247] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_244] (rows=1 width=0) + Select Operator [SEL_244] (rows=1 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_242] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_264] - Group By Operator [GBY_263] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_261] - Group By Operator [GBY_259] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_256] (rows=27 width=1029) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_254] diff --git a/ql/src/test/results/clientpositive/perf/tez/query67.q.out b/ql/src/test/results/clientpositive/perf/tez/query67.q.out index 960e66861c..88d9569292 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query67.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query67.q.out @@ -87,12 +87,10 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) @@ -103,105 +101,83 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_122] - Limit [LIM_121] (rows=100 width=88) + File Output Operator [FS_112] + Limit [LIM_111] (rows=100 width=617) Number of rows:100 - Select Operator [SEL_120] (rows=1149975358 width=88) + Select Operator [SEL_110] (rows=175097979 width=617) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_119] - Select Operator [SEL_118] (rows=1149975358 width=88) + SHUFFLE [RS_109] + Select Operator [SEL_108] (rows=175097979 width=617) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Filter Operator [FIL_117] (rows=1149975358 width=88) + Filter Operator [FIL_107] (rows=175097979 width=613) predicate:(rank_window_0 <= 100) - PTF Operator [PTF_116] (rows=3449926075 width=88) + PTF Operator [PTF_106] (rows=525293937 width=613) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col8 DESC NULLS LAST","partition by:":"_col0"}] - Select Operator [SEL_115] (rows=3449926075 width=88) + Select Operator [SEL_105] (rows=525293937 width=613) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_114] + SHUFFLE [RS_104] PartitionCols:_col0 - Select Operator [SEL_113] (rows=3449926075 width=88) + Select Operator [SEL_103] (rows=525293937 width=613) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Group By Operator [GBY_112] (rows=3449926075 width=88) + Group By Operator [GBY_102] (rows=525293937 width=621) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Group By Operator [GBY_23] (rows=6899852151 width=88) + Group By Operator [GBY_23] (rows=525293937 width=621) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col8)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, 0L - Select Operator [SEL_21] (rows=766650239 width=88) + Select Operator [SEL_21] (rows=58365993 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_84] (rows=766650239 width=88) - Conds:RS_18._col1=RS_103._col0(Inner),Output:["_col3","_col4","_col7","_col8","_col9","_col11","_col13","_col14","_col15","_col16"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] + Merge Join Operator [MERGEJOIN_84] (rows=58365993 width=570) + Conds:RS_18._col1=RS_101._col0(Inner),Output:["_col3","_col4","_col7","_col8","_col9","_col11","_col13","_col14","_col15","_col16"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_101] PartitionCols:_col0 - Select Operator [SEL_102] (rows=462000 width=1436) + Select Operator [SEL_100] (rows=462000 width=393) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_101] (rows=462000 width=1436) + Filter Operator [FIL_99] (rows=462000 width=393) predicate:i_item_sk is not null - TableScan [TS_9] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category","i_product_name"] + TableScan [TS_9] (rows=462000 width=393) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category","i_product_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_83] (rows=696954748 width=88) - Conds:RS_15._col2=RS_95._col0(Inner),Output:["_col1","_col3","_col4","_col7","_col8","_col9","_col11"] + Merge Join Operator [MERGEJOIN_83] (rows=58365993 width=185) + Conds:RS_15._col2=RS_98._col0(Inner),Output:["_col1","_col3","_col4","_col7","_col8","_col9","_col11"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_95] + SHUFFLE [RS_98] PartitionCols:_col0 - Select Operator [SEL_94] (rows=1704 width=1910) + Select Operator [SEL_97] (rows=1704 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_93] (rows=1704 width=1910) + Filter Operator [FIL_96] (rows=1704 width=104) predicate:s_store_sk is not null - TableScan [TS_6] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id"] + TableScan [TS_6] (rows=1704 width=104) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_82] (rows=633595212 width=88) - Conds:RS_111._col0=RS_87._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9"] + Merge Join Operator [MERGEJOIN_82] (rows=58365993 width=87) + Conds:RS_95._col0=RS_87._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=8116 width=1119) + Select Operator [SEL_86] (rows=8116 width=20) Output:["_col0","_col2","_col3","_col4"] - Filter Operator [FIL_85] (rows=8116 width=1119) + Filter Operator [FIL_85] (rows=8116 width=20) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq","d_year","d_moy","d_qoy"] + TableScan [TS_3] (rows=73049 width=20) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq","d_year","d_moy","d_qoy"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] + SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_110] (rows=575995635 width=88) + Select Operator [SEL_94] (rows=525329897 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_109] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_16_store_s_store_sk_min) AND DynamicValue(RS_16_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_16_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_quantity","ss_sales_price"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_100] - Group By Operator [GBY_99] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_98] - Group By Operator [GBY_97] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_96] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_94] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_108] - Group By Operator [GBY_107] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_104] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] + Filter Operator [FIL_93] (rows=525329897 width=122) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_quantity","ss_sales_price"] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_92] Group By Operator [GBY_91] (rows=1 width=12) @@ -210,7 +186,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_90] Group By Operator [GBY_89] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_88] (rows=8116 width=1119) + Select Operator [SEL_88] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_86] diff --git a/ql/src/test/results/clientpositive/perf/tez/query68.q.out b/ql/src/test/results/clientpositive/perf/tez/query68.q.out index fd1e04b328..c95d6bb431 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query68.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query68.q.out @@ -83,184 +83,160 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 10 <- Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 5 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) -Reducer 12 <- Map 16 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Map 8 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 16 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Map 6 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) -Reducer 8 <- Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Map 6 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_192] - Limit [LIM_191] (rows=100 width=88) + File Output Operator [FS_185] + Limit [LIM_184] (rows=100 width=706) Number of rows:100 - Select Operator [SEL_190] (rows=463823414 width=88) + Select Operator [SEL_183] (rows=16946760 width=706) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_46] - Select Operator [SEL_45] (rows=463823414 width=88) + Select Operator [SEL_45] (rows=16946760 width=706) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_44] (rows=463823414 width=88) + Filter Operator [FIL_44] (rows=16946760 width=706) predicate:(_col5 <> _col8) - Merge Join Operator [MERGEJOIN_145] (rows=463823414 width=88) - Conds:RS_41._col0=RS_189._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10","_col11"] + Merge Join Operator [MERGEJOIN_145] (rows=16946760 width=706) + Conds:RS_41._col0=RS_182._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10","_col11"] <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_41] + SHUFFLE [RS_41] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_140] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_140] (rows=80000000 width=277) Conds:RS_148._col1=RS_151._col0(Inner),Output:["_col0","_col2","_col3","_col5"] - <-Map 6 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_151] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] PartitionCols:_col0 - Select Operator [SEL_150] (rows=40000000 width=1014) + Select Operator [SEL_150] (rows=40000000 width=97) Output:["_col0","_col1"] - Filter Operator [FIL_149] (rows=40000000 width=1014) + Filter Operator [FIL_149] (rows=40000000 width=97) predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,current_addr,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_city"] + TableScan [TS_3] (rows=40000000 width=97) + default@customer_address,current_addr,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_148] PartitionCols:_col1 - Select Operator [SEL_147] (rows=80000000 width=860) + Select Operator [SEL_147] (rows=80000000 width=188) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_146] (rows=80000000 width=860) + Filter Operator [FIL_146] (rows=80000000 width=188) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] - <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_189] + TableScan [TS_0] (rows=80000000 width=188) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] + <-Reducer 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_182] PartitionCols:_col1 - Select Operator [SEL_188] (rows=421657640 width=88) + Select Operator [SEL_181] (rows=16946760 width=433) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_187] (rows=421657640 width=88) + Group By Operator [GBY_180] (rows=16946760 width=433) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 7 [SIMPLE_EDGE] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_34] (rows=843315281 width=88) + Group By Operator [GBY_34] (rows=16946760 width=433) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col1, _col18, _col3, _col5 - Merge Join Operator [MERGEJOIN_144] (rows=843315281 width=88) + Merge Join Operator [MERGEJOIN_144] (rows=16946760 width=97) Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col18"] - <-Map 6 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_152] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_152] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_150] - <-Reducer 13 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_143] (rows=766650239 width=88) - Conds:RS_27._col2=RS_174._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8"] - <-Map 18 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_174] + Merge Join Operator [MERGEJOIN_143] (rows=16946760 width=4) + Conds:RS_27._col2=RS_171._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_173] (rows=7200 width=107) + Select Operator [SEL_170] (rows=1855 width=12) Output:["_col0"] - Filter Operator [FIL_172] (rows=7200 width=107) + Filter Operator [FIL_169] (rows=1855 width=12) predicate:(((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) - TableScan [TS_15] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] - <-Reducer 12 [SIMPLE_EDGE] + TableScan [TS_15] (rows=7200 width=12) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_142] (rows=696954748 width=88) - Conds:RS_24._col4=RS_166._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_166] + Merge Join Operator [MERGEJOIN_142] (rows=65777178 width=243) + Conds:RS_24._col4=RS_163._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] + <-Map 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_165] (rows=1704 width=1910) + Select Operator [SEL_162] (rows=85 width=97) Output:["_col0"] - Filter Operator [FIL_164] (rows=1704 width=1910) + Filter Operator [FIL_161] (rows=85 width=97) predicate:((s_city) IN ('Cedar Grove', 'Wildwood') and s_store_sk is not null) - TableScan [TS_12] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_city"] - <-Reducer 11 [SIMPLE_EDGE] + TableScan [TS_12] (rows=1704 width=97) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_city"] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_141] (rows=633595212 width=88) - Conds:RS_186._col0=RS_158._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_158] + Merge Join Operator [MERGEJOIN_141] (rows=163378059 width=311) + Conds:RS_179._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_157] (rows=8116 width=1119) + Select Operator [SEL_154] (rows=652 width=12) Output:["_col0"] - Filter Operator [FIL_156] (rows=8116 width=1119) + Filter Operator [FIL_153] (rows=652 width=12) predicate:((d_year) IN (1998, 1999, 2000) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dom"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_186] + TableScan [TS_9] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dom"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_179] PartitionCols:_col0 - Select Operator [SEL_185] (rows=575995635 width=88) + Select Operator [SEL_178] (rows=457565061 width=343) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_184] (rows=575995635 width=88) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_31_customer_address_ca_address_sk_min) AND DynamicValue(RS_31_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_31_customer_address_ca_address_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_41_customer_c_customer_sk_min) AND DynamicValue(RS_41_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_41_customer_c_customer_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_28_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_28_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_28_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_25_store_s_store_sk_min) AND DynamicValue(RS_25_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_25_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_ext_sales_price","ss_ext_list_price","ss_ext_tax"] + Filter Operator [FIL_177] (rows=457565061 width=343) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_28_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_28_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_28_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_25_store_s_store_sk_min) AND DynamicValue(RS_25_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_25_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_6] (rows=575995635 width=343) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_ext_sales_price","ss_ext_list_price","ss_ext_tax"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_160] + Group By Operator [GBY_159] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_158] + Group By Operator [GBY_157] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_156] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_154] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_163] - Group By Operator [GBY_162] (rows=1 width=12) + BROADCAST [RS_168] + Group By Operator [GBY_167] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_161] - Group By Operator [GBY_160] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_166] + Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_159] (rows=8116 width=1119) + Select Operator [SEL_164] (rows=85 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_157] + Please refer to the previous Select Operator [SEL_162] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_171] - Group By Operator [GBY_170] (rows=1 width=12) + BROADCAST [RS_176] + Group By Operator [GBY_175] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_169] - Group By Operator [GBY_168] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_167] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_165] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_179] - Group By Operator [GBY_178] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_177] - Group By Operator [GBY_176] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_174] + Group By Operator [GBY_173] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_175] (rows=7200 width=107) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_173] - <-Reducer 5 [BROADCAST_EDGE] vectorized - BROADCAST [RS_183] - Group By Operator [GBY_182] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_117] - Group By Operator [GBY_116] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] - Select Operator [SEL_115] (rows=88000001 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_140] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_181] - Group By Operator [GBY_180] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] - <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_155] - Group By Operator [GBY_154] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] - Select Operator [SEL_153] (rows=40000000 width=1014) + Select Operator [SEL_172] (rows=1855 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_150] + Please refer to the previous Select Operator [SEL_170] diff --git a/ql/src/test/results/clientpositive/perf/tez/query69.q.out b/ql/src/test/results/clientpositive/perf/tez/query69.q.out index 4aad667ba3..87b8e097a0 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query69.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query69.q.out @@ -93,223 +93,250 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 11 <- Reducer 14 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 21 <- Reducer 17 (BROADCAST_EDGE) -Map 22 <- Reducer 20 (BROADCAST_EDGE) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 13 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (SIMPLE_EDGE) -Reducer 17 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 13 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) -Reducer 19 <- Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 20 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 16 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 19 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) +Map 12 <- Reducer 16 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 23 <- Reducer 14 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 24 <- Reducer 22 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Reducer 13 <- Map 12 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 15 (SIMPLE_EDGE), Map 23 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (SIMPLE_EDGE) +Reducer 19 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 20 <- Map 15 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) +Reducer 21 <- Reducer 20 (SIMPLE_EDGE) +Reducer 22 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 18 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 21 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_233] - Limit [LIM_232] (rows=100 width=88) + File Output Operator [FS_238] + Limit [LIM_237] (rows=1 width=383) Number of rows:100 - Select Operator [SEL_231] (rows=191662559 width=88) + Select Operator [SEL_236] (rows=1 width=383) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_230] - Select Operator [SEL_229] (rows=191662559 width=88) + SHUFFLE [RS_235] + Select Operator [SEL_234] (rows=1 width=383) Output:["_col0","_col1","_col2","_col3","_col4","_col6"] - Group By Operator [GBY_228] (rows=191662559 width=88) + Group By Operator [GBY_233] (rows=1 width=367) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_66] (rows=383325119 width=88) + Group By Operator [GBY_66] (rows=1 width=367) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count()"],keys:_col6, _col7, _col8, _col9, _col10 - Top N Key Operator [TNK_105] (rows=383325119 width=88) + Top N Key Operator [TNK_105] (rows=1 width=363) keys:_col6, _col7, _col8, _col9, _col10,sort order:+++++,top n:100 - Select Operator [SEL_65] (rows=383325119 width=88) + Select Operator [SEL_65] (rows=1 width=363) Output:["_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_64] (rows=383325119 width=88) + Filter Operator [FIL_64] (rows=1 width=363) predicate:_col14 is null - Merge Join Operator [MERGEJOIN_181] (rows=766650239 width=88) - Conds:RS_61._col0=RS_227._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col14"] - <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_227] - PartitionCols:_col0 - Select Operator [SEL_226] (rows=158394413 width=135) - Output:["_col0","_col1"] - Group By Operator [GBY_225] (rows=158394413 width=135) - Output:["_col0"],keys:KEY._col0 - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_58] - PartitionCols:_col0 - Group By Operator [GBY_57] (rows=316788826 width=135) - Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_179] (rows=316788826 width=135) - Conds:RS_224._col0=RS_197._col0(Inner),Output:["_col1"] - <-Map 13 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_197] - PartitionCols:_col0 - Select Operator [SEL_192] (rows=4058 width=1119) - Output:["_col0"] - Filter Operator [FIL_191] (rows=4058 width=1119) - predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) - TableScan [TS_12] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_224] - PartitionCols:_col0 - Select Operator [SEL_223] (rows=287989836 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_222] (rows=287989836 width=135) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_54_date_dim_d_date_sk_min) AND DynamicValue(RS_54_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_54_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_47] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_221] - Group By Operator [GBY_220] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_204] - Group By Operator [GBY_201] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_198] (rows=4058 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_192] + Merge Join Operator [MERGEJOIN_181] (rows=844 width=363) + Conds:RS_61._col0=RS_232._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col14"] <-Reducer 4 [ONE_TO_ONE_EDGE] - FORWARD [RS_61] + PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 - Select Operator [SEL_46] (rows=696954748 width=88) + Select Operator [SEL_46] (rows=1 width=367) Output:["_col0","_col6","_col7","_col8","_col9","_col10"] - Filter Operator [FIL_45] (rows=696954748 width=88) + Filter Operator [FIL_45] (rows=1 width=367) predicate:_col12 is null - Merge Join Operator [MERGEJOIN_180] (rows=1393909496 width=88) - Conds:RS_41._col0=RS_42._col0(Left Semi),RS_41._col0=RS_219._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"] - <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_41] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_176] (rows=96800003 width=860) - Conds:RS_36._col1=RS_190._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_190] - PartitionCols:_col0 - Select Operator [SEL_189] (rows=1861800 width=385) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_188] (rows=1861800 width=385) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_36] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_175] (rows=88000001 width=860) - Conds:RS_184._col2=RS_187._col0(Inner),Output:["_col0","_col1"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_184] - PartitionCols:_col2 - Select Operator [SEL_183] (rows=80000000 width=860) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_182] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_187] - PartitionCols:_col0 - Select Operator [SEL_186] (rows=40000000 width=1014) - Output:["_col0"] - Filter Operator [FIL_185] (rows=40000000 width=1014) - predicate:((ca_state) IN ('CO', 'IL', 'MN') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] - <-Reducer 12 [SIMPLE_EDGE] + Merge Join Operator [MERGEJOIN_180] (rows=9896 width=367) + Conds:RS_41._col0=RS_42._col0(Left Semi),RS_41._col0=RS_222._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col12"] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Group By Operator [GBY_40] (rows=633595212 width=88) + Group By Operator [GBY_40] (rows=168231 width=2) Output:["_col0"],keys:_col0 - Select Operator [SEL_18] (rows=633595212 width=88) + Select Operator [SEL_18] (rows=62428523 width=2) Output:["_col0"] - Merge Join Operator [MERGEJOIN_177] (rows=633595212 width=88) - Conds:RS_211._col0=RS_193._col0(Inner),Output:["_col1"] - <-Map 13 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_177] (rows=62428523 width=2) + Conds:RS_212._col0=RS_193._col0(Inner),Output:["_col1"] + <-Map 15 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_193] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_192] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_211] + Select Operator [SEL_192] (rows=217 width=12) + Output:["_col0"] + Filter Operator [FIL_191] (rows=217 width=12) + predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) + TableScan [TS_12] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_212] PartitionCols:_col0 - Select Operator [SEL_210] (rows=575995635 width=88) + Select Operator [SEL_211] (rows=525327388 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_209] (rows=575995635 width=88) + Filter Operator [FIL_210] (rows=525327388 width=7) predicate:((ss_customer_sk BETWEEN DynamicValue(RS_41_c_c_customer_sk_min) AND DynamicValue(RS_41_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_41_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_9] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] - <-Reducer 14 [BROADCAST_EDGE] vectorized + TableScan [TS_9] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_208] + Group By Operator [GBY_207] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4291485)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_138] + Group By Operator [GBY_137] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4291485)"] + Select Operator [SEL_136] (rows=4605476 width=4) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_176] (rows=4605476 width=363) + Conds:RS_36._col1=RS_190._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_190] + PartitionCols:_col0 + Select Operator [SEL_189] (rows=1861800 width=363) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_188] (rows=1861800 width=363) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=363) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status","cd_purchase_estimate","cd_credit_rating"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_36] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_175] (rows=4541258 width=5) + Conds:RS_184._col2=RS_187._col0(Inner),Output:["_col0","_col1"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_184] + PartitionCols:_col2 + Select Operator [SEL_183] (rows=77201384 width=11) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_182] (rows=77201384 width=11) + predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=11) + default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_187] + PartitionCols:_col0 + Select Operator [SEL_186] (rows=2352941 width=90) + Output:["_col0"] + Filter Operator [FIL_185] (rows=2352941 width=90) + predicate:((ca_state) IN ('CO', 'IL', 'MN') and ca_address_sk is not null) + TableScan [TS_3] (rows=40000000 width=90) + default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] + <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_206] Group By Operator [GBY_205] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_202] Group By Operator [GBY_199] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_194] (rows=4058 width=1119) + Select Operator [SEL_194] (rows=217 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_192] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_208] - Group By Operator [GBY_207] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=96800000)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_138] - Group By Operator [GBY_137] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"] - Select Operator [SEL_136] (rows=96800003 width=860) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_176] - <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_219] + <-Reducer 3 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_41] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_176] + <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_222] PartitionCols:_col0 - Select Operator [SEL_218] (rows=79201469 width=135) + Select Operator [SEL_221] (rows=168231 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_217] (rows=79201469 width=135) + Group By Operator [GBY_220] (rows=168231 width=3) Output:["_col0"],keys:KEY._col0 - <-Reducer 15 [SIMPLE_EDGE] + <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 - Group By Operator [GBY_29] (rows=158402938 width=135) + Group By Operator [GBY_29] (rows=168231 width=3) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_178] (rows=158402938 width=135) - Conds:RS_216._col0=RS_195._col0(Inner),Output:["_col1"] - <-Map 13 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_178] (rows=17104380 width=3) + Conds:RS_219._col0=RS_195._col0(Inner),Output:["_col1"] + <-Map 15 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_195] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_192] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_219] PartitionCols:_col0 - Select Operator [SEL_215] (rows=144002668 width=135) + Select Operator [SEL_218] (rows=143930993 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_214] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_19] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_213] - Group By Operator [GBY_212] (rows=1 width=12) + Filter Operator [FIL_217] (rows=143930993 width=7) + predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_41_c_c_customer_sk_min) AND DynamicValue(RS_41_c_c_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_41_c_c_customer_sk_bloom_filter))) and (ws_bill_customer_sk BETWEEN DynamicValue(RS_42_store_sales_ss_customer_sk_min) AND DynamicValue(RS_42_store_sales_ss_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_42_store_sales_ss_customer_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_19] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_209] + Please refer to the previous Group By Operator [GBY_207] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_216] + Group By Operator [GBY_215] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_118] + Group By Operator [GBY_117] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_116] (rows=168231 width=2) + Output:["_col0"] + Please refer to the previous Group By Operator [GBY_40] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_214] + Group By Operator [GBY_213] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_203] Group By Operator [GBY_200] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_196] (rows=4058 width=1119) + Select Operator [SEL_196] (rows=217 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_192] + <-Reducer 21 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_232] + PartitionCols:_col0 + Select Operator [SEL_231] (rows=167041 width=7) + Output:["_col0","_col1"] + Group By Operator [GBY_230] (rows=167041 width=3) + Output:["_col0"],keys:KEY._col0 + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_58] + PartitionCols:_col0 + Group By Operator [GBY_57] (rows=167041 width=3) + Output:["_col0"],keys:_col1 + Merge Join Operator [MERGEJOIN_179] (rows=33642830 width=3) + Conds:RS_229._col0=RS_197._col0(Inner),Output:["_col1"] + <-Map 15 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_197] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_192] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_229] + PartitionCols:_col0 + Select Operator [SEL_228] (rows=285115246 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_227] (rows=285115246 width=7) + predicate:((cs_ship_customer_sk BETWEEN DynamicValue(RS_61_c_c_customer_sk_min) AND DynamicValue(RS_61_c_c_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_61_c_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_54_date_dim_d_date_sk_min) AND DynamicValue(RS_54_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_54_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_47] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] + <-Reducer 22 [BROADCAST_EDGE] vectorized + BROADCAST [RS_224] + Group By Operator [GBY_223] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_204] + Group By Operator [GBY_201] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_198] (rows=217 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_192] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_226] + Group By Operator [GBY_225] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_165] + Group By Operator [GBY_164] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_163] (rows=1 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_46] diff --git a/ql/src/test/results/clientpositive/perf/tez/query7.q.out b/ql/src/test/results/clientpositive/perf/tez/query7.q.out index c78e1e65d3..09822b8660 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query7.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query7.q.out @@ -41,14 +41,12 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) @@ -58,86 +56,86 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_140] - Limit [LIM_139] (rows=100 width=88) + File Output Operator [FS_130] + Limit [LIM_129] (rows=100 width=444) Number of rows:100 - Select Operator [SEL_138] (rows=421657640 width=88) + Select Operator [SEL_128] (rows=310774 width=444) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_137] - Select Operator [SEL_136] (rows=421657640 width=88) + SHUFFLE [RS_127] + Select Operator [SEL_126] (rows=310774 width=444) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_135] (rows=421657640 width=88) + Group By Operator [GBY_125] (rows=310774 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 - Group By Operator [GBY_28] (rows=843315281 width=88) + Group By Operator [GBY_28] (rows=1441769 width=476) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18 - Top N Key Operator [TNK_55] (rows=843315281 width=88) + Top N Key Operator [TNK_55] (rows=1441769 width=100) keys:_col18,sort order:+,top n:100 - Merge Join Operator [MERGEJOIN_99] (rows=843315281 width=88) - Conds:RS_24._col1=RS_126._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] + Merge Join Operator [MERGEJOIN_99] (rows=1441769 width=100) + Conds:RS_24._col1=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_124] PartitionCols:_col0 - Select Operator [SEL_125] (rows=462000 width=1436) + Select Operator [SEL_123] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_124] (rows=462000 width=1436) + Filter Operator [FIL_122] (rows=462000 width=104) predicate:i_item_sk is not null - TableScan [TS_12] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + TableScan [TS_12] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_98] (rows=766650239 width=88) - Conds:RS_21._col3=RS_118._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_98] (rows=1441769 width=4) + Conds:RS_21._col3=RS_121._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] + SHUFFLE [RS_121] PartitionCols:_col0 - Select Operator [SEL_117] (rows=2300 width=1179) + Select Operator [SEL_120] (rows=2300 width=174) Output:["_col0"] - Filter Operator [FIL_116] (rows=2300 width=1179) + Filter Operator [FIL_119] (rows=2300 width=174) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) - TableScan [TS_9] (rows=2300 width=1179) - default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"] + TableScan [TS_9] (rows=2300 width=174) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk","p_channel_email","p_channel_event"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_97] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_97] (rows=1441769 width=4) Conds:RS_18._col0=RS_110._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=36524 width=1119) + Select Operator [SEL_109] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_108] (rows=36524 width=1119) + Filter Operator [FIL_108] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_6] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_96] (rows=633595212 width=88) - Conds:RS_134._col2=RS_102._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_96] (rows=4037893 width=4) + Conds:RS_118._col2=RS_102._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] PartitionCols:_col0 - Select Operator [SEL_101] (rows=232725 width=385) + Select Operator [SEL_101] (rows=14776 width=265) Output:["_col0"] - Filter Operator [FIL_100] (rows=232725 width=385) + Filter Operator [FIL_100] (rows=14776 width=268) predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) - TableScan [TS_3] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] + TableScan [TS_3] (rows=1861800 width=268) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_134] + SHUFFLE [RS_118] PartitionCols:_col2 - Select Operator [SEL_133] (rows=575995635 width=88) + Select Operator [SEL_117] (rows=501686735 width=340) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_132] (rows=575995635 width=88) - predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_22_promotion_p_promo_sk_min) AND DynamicValue(RS_22_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_22_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_promo_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] + Filter Operator [FIL_116] (rows=501686735 width=340) + predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_0] (rows=575995635 width=340) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_promo_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_115] Group By Operator [GBY_114] (rows=1 width=12) @@ -146,31 +144,9 @@ Stage-0 SHUFFLE [RS_113] Group By Operator [GBY_112] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_111] (rows=36524 width=1119) + Select Operator [SEL_111] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_109] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] - Group By Operator [GBY_120] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_119] (rows=2300 width=1179) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_117] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_131] - Group By Operator [GBY_130] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_129] - Group By Operator [GBY_128] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_127] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_125] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_107] Group By Operator [GBY_106] (rows=1 width=12) @@ -179,7 +155,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_105] Group By Operator [GBY_104] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_103] (rows=232725 width=385) + Select Operator [SEL_103] (rows=14776 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_101] diff --git a/ql/src/test/results/clientpositive/perf/tez/query70.q.out b/ql/src/test/results/clientpositive/perf/tez/query70.q.out index 4efb85a52c..ec9bcbd243 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query70.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query70.q.out @@ -75,186 +75,134 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 16 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Map 17 <- Reducer 14 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE) -Reducer 10 <- Map 17 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Map 18 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_187] - Limit [LIM_186] (rows=100 width=88) + File Output Operator [FS_168] + Limit [LIM_167] (rows=100 width=492) Number of rows:100 - Select Operator [SEL_185] (rows=1149975358 width=88) + Select Operator [SEL_166] (rows=240 width=492) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_184] - Select Operator [SEL_183] (rows=1149975358 width=88) + SHUFFLE [RS_165] + Select Operator [SEL_164] (rows=240 width=492) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - PTF Operator [PTF_182] (rows=1149975358 width=88) + PTF Operator [PTF_163] (rows=240 width=304) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 DESC NULLS LAST","partition by:":"(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END"}] - Select Operator [SEL_181] (rows=1149975358 width=88) + Select Operator [SEL_162] (rows=240 width=304) Output:["_col0","_col1","_col2","_col3"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_180] + SHUFFLE [RS_161] PartitionCols:(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END - Select Operator [SEL_179] (rows=1149975358 width=88) + Select Operator [SEL_160] (rows=240 width=304) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_178] (rows=1149975358 width=88) + Group By Operator [GBY_159] (rows=240 width=304) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_48] (rows=2299950717 width=88) + Group By Operator [GBY_48] (rows=10080 width=304) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col0, _col1, 0L - Select Operator [SEL_46] (rows=766650239 width=88) + Select Operator [SEL_46] (rows=19058283 width=184) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_134] (rows=766650239 width=88) - Conds:RS_43._col7=RS_177._col0(Inner),Output:["_col2","_col6","_col7"] - <-Reducer 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_177] + Merge Join Operator [MERGEJOIN_134] (rows=19058283 width=184) + Conds:RS_43._col7=RS_158._col0(Inner),Output:["_col2","_col6","_col7"] + <-Reducer 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_158] PartitionCols:_col0 - Select Operator [SEL_176] (rows=116159124 width=88) + Select Operator [SEL_157] (rows=16 width=86) Output:["_col0"] - Filter Operator [FIL_175] (rows=116159124 width=88) + Filter Operator [FIL_156] (rows=16 width=198) predicate:(rank_window_0 <= 5) - PTF Operator [PTF_174] (rows=348477374 width=88) + PTF Operator [PTF_155] (rows=49 width=198) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS LAST","partition by:":"_col0"}] - Select Operator [SEL_173] (rows=348477374 width=88) + Select Operator [SEL_154] (rows=49 width=198) Output:["_col0","_col1"] - <-Reducer 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_172] + <-Reducer 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_153] PartitionCols:_col0 - Group By Operator [GBY_171] (rows=348477374 width=88) + Group By Operator [GBY_152] (rows=49 width=198) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 11 [SIMPLE_EDGE] + <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0 - Group By Operator [GBY_25] (rows=696954748 width=88) + Group By Operator [GBY_25] (rows=1715 width=198) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col6 - Merge Join Operator [MERGEJOIN_133] (rows=696954748 width=88) - Conds:RS_21._col1=RS_162._col0(Inner),Output:["_col2","_col6"] - <-Map 18 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_162] - PartitionCols:_col0 - Select Operator [SEL_161] (rows=1704 width=1910) - Output:["_col0","_col1"] - Filter Operator [FIL_160] (rows=1704 width=1910) - predicate:(s_state is not null and s_store_sk is not null) - TableScan [TS_15] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] - <-Reducer 10 [SIMPLE_EDGE] + Merge Join Operator [MERGEJOIN_133] (rows=58365993 width=152) + Conds:RS_21._col1=RS_151._col0(Inner),Output:["_col2","_col6"] + <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_132] (rows=633595212 width=88) - Conds:RS_170._col0=RS_139._col0(Inner),Output:["_col1","_col2"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_139] + Merge Join Operator [MERGEJOIN_130] (rows=58365993 width=69) + Conds:RS_145._col0=RS_137._col0(Inner),Output:["_col1","_col2"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_137] PartitionCols:_col0 - Select Operator [SEL_136] (rows=8116 width=1119) + Select Operator [SEL_136] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_135] (rows=8116 width=1119) + Filter Operator [FIL_135] (rows=8116 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_170] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_145] PartitionCols:_col0 - Select Operator [SEL_169] (rows=575995635 width=88) + Select Operator [SEL_144] (rows=525329897 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_168] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_9] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_159] - Group By Operator [GBY_158] (rows=1 width=12) + Filter Operator [FIL_143] (rows=525329897 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_38_d1_d_date_sk_min) AND DynamicValue(RS_38_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_38_d1_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_142] + Group By Operator [GBY_141] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_144] - Group By Operator [GBY_142] (rows=1 width=12) + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_140] + Group By Operator [GBY_139] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_140] (rows=8116 width=1119) + Select Operator [SEL_138] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_136] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_167] - Group By Operator [GBY_166] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_165] - Group By Operator [GBY_164] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_163] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_161] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_151] + PartitionCols:_col0 + Select Operator [SEL_150] (rows=1704 width=90) + Output:["_col0","_col1"] + Filter Operator [FIL_149] (rows=1704 width=90) + predicate:(s_state is not null and s_store_sk is not null) + TableScan [TS_15] (rows=1704 width=90) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col7 - Merge Join Operator [MERGEJOIN_131] (rows=696954748 width=88) - Conds:RS_40._col1=RS_149._col0(Inner),Output:["_col2","_col6","_col7"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_149] - PartitionCols:_col0 - Select Operator [SEL_148] (rows=1704 width=1910) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_147] (rows=1704 width=1910) - predicate:(s_state is not null and s_store_sk is not null) - TableScan [TS_6] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_county","s_state"] + Merge Join Operator [MERGEJOIN_131] (rows=58365993 width=250) + Conds:RS_40._col1=RS_148._col0(Inner),Output:["_col2","_col6","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_130] (rows=633595212 width=88) - Conds:RS_157._col0=RS_137._col0(Inner),Output:["_col1","_col2"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_137] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_136] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_157] - PartitionCols:_col0 - Select Operator [SEL_156] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_155] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_38_d1_d_date_sk_min) AND DynamicValue(RS_38_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_38_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_41_store_s_store_sk_min) AND DynamicValue(RS_41_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_41_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_154] - Group By Operator [GBY_153] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_152] - Group By Operator [GBY_151] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_150] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_148] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_146] - Group By Operator [GBY_145] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_143] - Group By Operator [GBY_141] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_138] (rows=8116 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_136] + Please refer to the previous Merge Join Operator [MERGEJOIN_130] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_148] + PartitionCols:_col0 + Select Operator [SEL_147] (rows=1704 width=188) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_146] (rows=1704 width=188) + predicate:(s_state is not null and s_store_sk is not null) + TableScan [TS_6] (rows=1704 width=188) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_county","s_state"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query71.q.out b/ql/src/test/results/clientpositive/perf/tez/query71.q.out index ca62fa3a8e..c75c89002e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query71.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query71.q.out @@ -99,70 +99,70 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_188] - Select Operator [SEL_187] (rows=670816149 width=108) + Select Operator [SEL_187] (rows=1991967 width=223) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_186] - Select Operator [SEL_185] (rows=670816149 width=108) + Select Operator [SEL_185] (rows=1991967 width=227) Output:["_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_184] (rows=670816149 width=108) + Group By Operator [GBY_184] (rows=1991967 width=223) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_46] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_45] (rows=1341632299 width=108) + Group By Operator [GBY_45] (rows=1991967 width=223) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col0)"],keys:_col4, _col8, _col9, _col5 - Merge Join Operator [MERGEJOIN_140] (rows=1341632299 width=108) + Merge Join Operator [MERGEJOIN_140] (rows=1991967 width=112) Conds:RS_41._col2=RS_173._col0(Inner),Output:["_col0","_col4","_col5","_col8","_col9"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_173] PartitionCols:_col0 - Select Operator [SEL_172] (rows=86400 width=471) + Select Operator [SEL_172] (rows=43200 width=99) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_171] (rows=86400 width=471) + Filter Operator [FIL_171] (rows=43200 width=99) predicate:((t_meal_time) IN ('breakfast', 'dinner') and t_time_sk is not null) - TableScan [TS_35] (rows=86400 width=471) - default@time_dim,time_dim,Tbl:COMPLETE,Col:NONE,Output:["t_time_sk","t_hour","t_minute","t_meal_time"] + TableScan [TS_35] (rows=86400 width=99) + default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute","t_meal_time"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_139] (rows=1219665700 width=108) + Merge Join Operator [MERGEJOIN_139] (rows=3983933 width=104) Conds:Union 3._col1=RS_163._col0(Inner),Output:["_col0","_col2","_col4","_col5"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_162] (rows=231000 width=1436) + Select Operator [SEL_162] (rows=7333 width=111) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_161] (rows=231000 width=1436) + Filter Operator [FIL_161] (rows=7333 width=111) predicate:((i_manager_id = 1) and i_item_sk is not null) - TableScan [TS_32] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_brand","i_manager_id"] + TableScan [TS_32] (rows=462000 width=111) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manager_id"] <-Union 3 [SIMPLE_EDGE] <-Reducer 11 [CONTAINS] Reduce Output Operator [RS_148] PartitionCols:_col1 - Select Operator [SEL_146] (rows=316788826 width=135) + Select Operator [SEL_146] (rows=7751851 width=98) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_145] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_145] (rows=7751851 width=98) Conds:RS_199._col0=RS_191._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 12 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_191] PartitionCols:_col0 - Select Operator [SEL_190] (rows=18262 width=1119) + Select Operator [SEL_190] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_189] (rows=18262 width=1119) + Filter Operator [FIL_189] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) - TableScan [TS_13] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_13] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_199] PartitionCols:_col0 - Select Operator [SEL_198] (rows=287989836 width=135) + Select Operator [SEL_198] (rows=285116947 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_197] (rows=287989836 width=135) + Filter Operator [FIL_197] (rows=285116947 width=123) predicate:((cs_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_17_date_dim_d_date_sk_min) AND DynamicValue(RS_17_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_17_date_dim_d_date_sk_bloom_filter))) and (cs_sold_time_sk BETWEEN DynamicValue(RS_42_time_dim_t_time_sk_min) AND DynamicValue(RS_42_time_dim_t_time_sk_max) and in_bloom_filter(cs_sold_time_sk, DynamicValue(RS_42_time_dim_t_time_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null and cs_sold_time_sk is not null) - TableScan [TS_10] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_sold_time_sk","cs_item_sk","cs_ext_sales_price"] + TableScan [TS_10] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_sold_time_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 19 [BROADCAST_EDGE] vectorized BROADCAST [RS_169] Group By Operator [GBY_167] (rows=1 width=12) @@ -171,7 +171,7 @@ Stage-0 SHUFFLE [RS_166] Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_164] (rows=231000 width=1436) + Select Operator [SEL_164] (rows=7333 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_162] <-Reducer 21 [BROADCAST_EDGE] vectorized @@ -182,7 +182,7 @@ Stage-0 SHUFFLE [RS_176] Group By Operator [GBY_175] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_174] (rows=86400 width=471) + Select Operator [SEL_174] (rows=43200 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_172] <-Reducer 13 [BROADCAST_EDGE] vectorized @@ -193,34 +193,34 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_194] Group By Operator [GBY_193] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_192] (rows=18262 width=1119) + Select Operator [SEL_192] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_190] <-Reducer 15 [CONTAINS] Reduce Output Operator [RS_152] PartitionCols:_col1 - Select Operator [SEL_150] (rows=633595212 width=88) + Select Operator [SEL_150] (rows=14384397 width=4) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_149] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_149] (rows=14384397 width=4) Conds:RS_210._col0=RS_202._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_202] PartitionCols:_col0 - Select Operator [SEL_201] (rows=18262 width=1119) + Select Operator [SEL_201] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_200] (rows=18262 width=1119) + Filter Operator [FIL_200] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) - TableScan [TS_24] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_24] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_210] PartitionCols:_col0 - Select Operator [SEL_209] (rows=575995635 width=88) + Select Operator [SEL_209] (rows=525325345 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_208] (rows=575995635 width=88) + Filter Operator [FIL_208] (rows=525325345 width=118) predicate:((ss_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_42_time_dim_t_time_sk_min) AND DynamicValue(RS_42_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_42_time_dim_t_time_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_sold_time_sk is not null) - TableScan [TS_21] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_sold_time_sk","ss_item_sk","ss_ext_sales_price"] + TableScan [TS_21] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_sold_time_sk","ss_item_sk","ss_ext_sales_price"] <-Reducer 19 [BROADCAST_EDGE] vectorized BROADCAST [RS_170] Please refer to the previous Group By Operator [GBY_167] @@ -235,34 +235,34 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_205] Group By Operator [GBY_204] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_203] (rows=18262 width=1119) + Select Operator [SEL_203] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_201] <-Reducer 2 [CONTAINS] Reduce Output Operator [RS_144] PartitionCols:_col1 - Select Operator [SEL_142] (rows=158402938 width=135) + Select Operator [SEL_142] (rows=3941098 width=118) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_141] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_141] (rows=3941098 width=118) Conds:RS_183._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_154] (rows=18262 width=1119) + Select Operator [SEL_154] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_153] (rows=18262 width=1119) + Filter Operator [FIL_153] (rows=50 width=12) predicate:((d_moy = 12) and (d_year = 2001) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_183] PartitionCols:_col0 - Select Operator [SEL_182] (rows=144002668 width=135) + Select Operator [SEL_182] (rows=143930836 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_181] (rows=144002668 width=135) + Filter Operator [FIL_181] (rows=143930836 width=123) predicate:((ws_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_42_time_dim_t_time_sk_min) AND DynamicValue(RS_42_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_42_time_dim_t_time_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null and ws_sold_time_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_sold_time_sk","ws_item_sk","ws_ext_sales_price"] + TableScan [TS_0] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_sold_time_sk","ws_item_sk","ws_ext_sales_price"] <-Reducer 19 [BROADCAST_EDGE] vectorized BROADCAST [RS_168] Please refer to the previous Group By Operator [GBY_167] @@ -277,7 +277,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_158] Group By Operator [GBY_157] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_156] (rows=18262 width=1119) + Select Operator [SEL_156] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_154] diff --git a/ql/src/test/results/clientpositive/perf/tez/query72.q.out b/ql/src/test/results/clientpositive/perf/tez/query72.q.out index 65a60ea30a..428766a55e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query72.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query72.q.out @@ -61,263 +61,227 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 10 <- Reducer 18 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) -Reducer 12 <- Map 19 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 21 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Map 9 <- Reducer 17 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE) +Reducer 10 <- Map 16 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 11 <- Map 18 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Map 20 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 22 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Map 23 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) Reducer 15 <- Map 24 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) -Reducer 16 <- Map 26 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 24 (CUSTOM_SIMPLE_EDGE) -Reducer 27 <- Map 26 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 28 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 29 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 25 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 26 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_315] - Limit [LIM_314] (rows=100 width=135) + File Output Operator [FS_303] + Limit [LIM_302] (rows=100 width=312) Number of rows:100 - Select Operator [SEL_313] (rows=37725837 width=135) + Select Operator [SEL_301] (rows=384313734 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_312] - Group By Operator [GBY_311] (rows=37725837 width=135) + SHUFFLE [RS_300] + Group By Operator [GBY_299] (rows=384313734 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_68] (rows=75451675 width=135) + Group By Operator [GBY_68] (rows=963870346 width=312) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col3)","count(_col4)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_66] (rows=75451675 width=135) + Select Operator [SEL_66] (rows=963870346 width=292) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_251] (rows=75451675 width=135) - Conds:RS_63._col4, _col6=RS_310._col0, _col1(Left Outer),Output:["_col13","_col15","_col22","_col28"] - <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_310] + Merge Join Operator [MERGEJOIN_251] (rows=963870346 width=292) + Conds:RS_63._col4, _col6=RS_298._col0, _col1(Left Outer),Output:["_col13","_col15","_col22","_col28"] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_298] PartitionCols:_col0, _col1 - Select Operator [SEL_309] (rows=28798881 width=106) + Select Operator [SEL_297] (rows=28798881 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_308] (rows=28798881 width=106) + Filter Operator [FIL_296] (rows=28798881 width=8) predicate:cr_item_sk is not null - TableScan [TS_60] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number"] + TableScan [TS_60] (rows=28798881 width=8) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col4, _col6 - Select Operator [SEL_59] (rows=68592431 width=135) + Select Operator [SEL_59] (rows=610435044 width=300) Output:["_col4","_col6","_col13","_col15","_col22","_col28"] - Merge Join Operator [MERGEJOIN_250] (rows=68592431 width=135) - Conds:RS_56._col0, _col20=RS_307._col0, _col1(Inner),Output:["_col5","_col9","_col14","_col16","_col20","_col26"] - <-Map 28 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_307] + Merge Join Operator [MERGEJOIN_250] (rows=610435044 width=300) + Conds:RS_56._col0, _col20=RS_295._col0, _col1(Inner),Output:["_col5","_col9","_col14","_col16","_col20","_col26"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_295] PartitionCols:_col0, _col1 - Select Operator [SEL_306] (rows=73049 width=1119) + Select Operator [SEL_294] (rows=73049 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_305] (rows=73049 width=1119) + Filter Operator [FIL_293] (rows=73049 width=8) predicate:(d_date_sk is not null and d_week_seq is not null) - TableScan [TS_46] (rows=73049 width=1119) - default@date_dim,d2,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_week_seq"] + TableScan [TS_46] (rows=73049 width=8) + default@date_dim,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0, _col20 - Filter Operator [FIL_55] (rows=62356755 width=135) + Filter Operator [FIL_55] (rows=545947820 width=311) predicate:(_col3 < _col17) - Merge Join Operator [MERGEJOIN_249] (rows=187070265 width=135) + Merge Join Operator [MERGEJOIN_249] (rows=1637843460 width=311) Conds:RS_52._col1=RS_53._col8(Inner),Output:["_col0","_col3","_col5","_col9","_col14","_col16","_col17","_col20","_col26"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_52] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_242] (rows=41342400 width=15) - Conds:RS_254._col2=RS_257._col0(Inner),Output:["_col0","_col1","_col3","_col5"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_254] - PartitionCols:_col2 - Select Operator [SEL_253] (rows=37584000 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_252] (rows=37584000 width=15) - predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) - TableScan [TS_0] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_257] - PartitionCols:_col0 - Select Operator [SEL_256] (rows=27 width=1029) - Output:["_col0","_col1"] - Filter Operator [FIL_255] (rows=27 width=1029) - predicate:w_warehouse_sk is not null - TableScan [TS_3] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"] - <-Reducer 16 [SIMPLE_EDGE] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col8 - Select Operator [SEL_45] (rows=170063874 width=135) + Select Operator [SEL_45] (rows=2726340 width=391) Output:["_col3","_col8","_col10","_col11","_col14","_col20"] - Filter Operator [FIL_44] (rows=170063874 width=135) + Filter Operator [FIL_44] (rows=2726340 width=391) predicate:(UDFToDouble(_col20) > (UDFToDouble(_col9) + 5.0D)) - Merge Join Operator [MERGEJOIN_248] (rows=510191624 width=135) - Conds:RS_41._col1=RS_294._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col16","_col18","_col20"] - <-Map 26 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_294] + Merge Join Operator [MERGEJOIN_248] (rows=8179022 width=391) + Conds:RS_41._col1=RS_292._col0(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col16","_col18","_col20"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_292] PartitionCols:_col0 - Select Operator [SEL_293] (rows=73049 width=1119) + Select Operator [SEL_291] (rows=73049 width=98) Output:["_col0","_col1"] - Filter Operator [FIL_292] (rows=73049 width=1119) + Filter Operator [FIL_290] (rows=73049 width=98) predicate:d_date_sk is not null - TableScan [TS_23] (rows=73049 width=1119) - default@date_dim,d3,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Reducer 15 [SIMPLE_EDGE] + TableScan [TS_23] (rows=73049 width=98) + default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_247] (rows=463810558 width=135) - Conds:RS_38._col4=RS_284._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16","_col18"] - <-Map 24 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_284] + Merge Join Operator [MERGEJOIN_247] (rows=8179022 width=300) + Conds:RS_38._col4=RS_289._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16","_col18"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_289] PartitionCols:_col0 - Select Operator [SEL_283] (rows=462000 width=1436) + Select Operator [SEL_288] (rows=462000 width=188) Output:["_col0","_col1"] - Filter Operator [FIL_282] (rows=462000 width=1436) + Filter Operator [FIL_287] (rows=462000 width=188) predicate:i_item_sk is not null - TableScan [TS_20] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"] - <-Reducer 14 [SIMPLE_EDGE] + TableScan [TS_20] (rows=462000 width=188) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_246] (rows=421645953 width=135) - Conds:RS_35._col5=RS_304._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_304] + Merge Join Operator [MERGEJOIN_246] (rows=8179022 width=116) + Conds:RS_35._col5=RS_286._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_286] PartitionCols:_col0 - Select Operator [SEL_303] (rows=2300 width=1179) + Select Operator [SEL_285] (rows=2300 width=4) Output:["_col0"] - TableScan [TS_18] (rows=2300 width=1179) - default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk"] - <-Reducer 13 [SIMPLE_EDGE] + TableScan [TS_18] (rows=2300 width=4) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk"] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_245] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_245] (rows=8179022 width=115) Conds:RS_32._col3=RS_276._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col9","_col10"] - <-Map 21 [SIMPLE_EDGE] vectorized + <-Map 20 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_276] PartitionCols:_col0 - Select Operator [SEL_275] (rows=3600 width=107) + Select Operator [SEL_275] (rows=1440 width=97) Output:["_col0"] - Filter Operator [FIL_274] (rows=3600 width=107) + Filter Operator [FIL_274] (rows=1440 width=96) predicate:((hd_buy_potential = '1001-5000') and hd_demo_sk is not null) - TableScan [TS_15] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential"] - <-Reducer 12 [SIMPLE_EDGE] + TableScan [TS_15] (rows=7200 width=96) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential"] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_244] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_244] (rows=40895108 width=121) Conds:RS_29._col2=RS_268._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] - <-Map 19 [SIMPLE_EDGE] vectorized + <-Map 18 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_268] PartitionCols:_col0 - Select Operator [SEL_267] (rows=930900 width=385) + Select Operator [SEL_267] (rows=265971 width=89) Output:["_col0"] - Filter Operator [FIL_266] (rows=930900 width=385) + Filter Operator [FIL_266] (rows=265971 width=89) predicate:((cd_marital_status = 'M') and cd_demo_sk is not null) - TableScan [TS_12] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status"] - <-Reducer 11 [SIMPLE_EDGE] + TableScan [TS_12] (rows=1861800 width=89) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status"] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_243] (rows=316788826 width=135) - Conds:RS_302._col0=RS_260._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] - <-Map 17 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_243] (rows=100076475 width=125) + Conds:RS_284._col0=RS_260._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10"] + <-Map 16 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_260] PartitionCols:_col0 - Select Operator [SEL_259] (rows=36524 width=1119) + Select Operator [SEL_259] (rows=652 width=106) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_258] (rows=36524 width=1119) + Filter Operator [FIL_258] (rows=652 width=106) predicate:((d_year = 2001) and d_date_sk is not null and d_week_seq is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_week_seq","d_year"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_302] + TableScan [TS_9] (rows=73049 width=106) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_week_seq","d_year"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_284] PartitionCols:_col0 - Select Operator [SEL_301] (rows=287989836 width=135) + Select Operator [SEL_283] (rows=282274763 width=31) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_300] (rows=287989836 width=135) - predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_30_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_30_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_30_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_bill_hdemo_sk BETWEEN DynamicValue(RS_33_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_33_household_demographics_hd_demo_sk_max) and in_bloom_filter(cs_bill_hdemo_sk, DynamicValue(RS_33_household_demographics_hd_demo_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_52_inventory_inv_item_sk_min) AND DynamicValue(RS_52_inventory_inv_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_52_inventory_inv_item_sk_bloom_filter))) and (cs_ship_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_42_d3_d_date_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_27_d1_d_date_sk_min) AND DynamicValue(RS_27_d1_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_27_d1_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_6] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_bill_cdemo_sk","cs_bill_hdemo_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_quantity"] - <-Reducer 18 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_282] (rows=282274763 width=31) + predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_30_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_30_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_30_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_bill_hdemo_sk BETWEEN DynamicValue(RS_33_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_33_household_demographics_hd_demo_sk_max) and in_bloom_filter(cs_bill_hdemo_sk, DynamicValue(RS_33_household_demographics_hd_demo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_27_d1_d_date_sk_min) AND DynamicValue(RS_27_d1_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_27_d1_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_6] (rows=287989836 width=31) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_bill_cdemo_sk","cs_bill_hdemo_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_quantity"] + <-Reducer 17 [BROADCAST_EDGE] vectorized BROADCAST [RS_265] Group By Operator [GBY_264] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_263] Group By Operator [GBY_262] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_261] (rows=36524 width=1119) + Select Operator [SEL_261] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_259] - <-Reducer 20 [BROADCAST_EDGE] vectorized + <-Reducer 19 [BROADCAST_EDGE] vectorized BROADCAST [RS_273] Group By Operator [GBY_272] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_271] Group By Operator [GBY_270] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_269] (rows=930900 width=385) + Select Operator [SEL_269] (rows=265971 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_267] - <-Reducer 22 [BROADCAST_EDGE] vectorized + <-Reducer 21 [BROADCAST_EDGE] vectorized BROADCAST [RS_281] Group By Operator [GBY_280] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_279] Group By Operator [GBY_278] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_277] (rows=3600 width=107) + Select Operator [SEL_277] (rows=1440 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_275] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_289] - Group By Operator [GBY_288] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_287] - Group By Operator [GBY_286] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_285] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_283] - <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_299] - Group By Operator [GBY_298] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_297] - Group By Operator [GBY_296] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_295] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_293] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_291] - Group By Operator [GBY_290] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=41342400)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_174] - Group By Operator [GBY_173] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=41342400)"] - Select Operator [SEL_172] (rows=41342400 width=15) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_242] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_52] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_242] (rows=37584000 width=111) + Conds:RS_254._col2=RS_257._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_254] + PartitionCols:_col2 + Select Operator [SEL_253] (rows=37584000 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_252] (rows=37584000 width=15) + predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) + TableScan [TS_0] (rows=37584000 width=15) + default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_warehouse_sk","inv_quantity_on_hand"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_257] + PartitionCols:_col0 + Select Operator [SEL_256] (rows=27 width=104) + Output:["_col0","_col1"] + Filter Operator [FIL_255] (rows=27 width=104) + predicate:w_warehouse_sk is not null + TableScan [TS_3] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query73.q.out b/ql/src/test/results/clientpositive/perf/tez/query73.q.out index b18b8608db..7fbec7e416 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query73.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query73.q.out @@ -55,145 +55,133 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 5 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 4 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Map 4 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Map 10 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) -Reducer 7 <- Map 12 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Map 14 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 6 <- Map 11 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 13 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_141] - Select Operator [SEL_140] (rows=88000001 width=860) + File Output Operator [FS_136] + Select Operator [SEL_135] (rows=510193 width=364) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_35] - Select Operator [SEL_34] (rows=88000001 width=860) + Select Operator [SEL_34] (rows=510193 width=364) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_100] (rows=88000001 width=860) - Conds:RS_103._col0=RS_139._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] + Merge Join Operator [MERGEJOIN_100] (rows=510193 width=364) + Conds:RS_103._col0=RS_134._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_103] + SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_102] (rows=80000000 width=860) + Select Operator [SEL_102] (rows=80000000 width=356) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_101] (rows=80000000 width=860) + Filter Operator [FIL_101] (rows=80000000 width=356) predicate:c_customer_sk is not null - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag"] - <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_139] + TableScan [TS_0] (rows=80000000 width=356) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag"] + <-Reducer 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_134] PartitionCols:_col1 - Filter Operator [FIL_138] (rows=42591679 width=88) + Filter Operator [FIL_133] (rows=510193 width=12) predicate:_col2 BETWEEN 1 AND 5 - Select Operator [SEL_137] (rows=383325119 width=88) + Select Operator [SEL_132] (rows=4591740 width=12) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_136] (rows=383325119 width=88) + Group By Operator [GBY_131] (rows=4591740 width=12) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 8 [SIMPLE_EDGE] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1 - Group By Operator [GBY_25] (rows=766650239 width=88) + Group By Operator [GBY_25] (rows=4591740 width=12) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_99] (rows=766650239 width=88) - Conds:RS_21._col3=RS_125._col0(Inner),Output:["_col1","_col4"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] + Merge Join Operator [MERGEJOIN_99] (rows=4591740 width=4) + Conds:RS_21._col3=RS_122._col0(Inner),Output:["_col1","_col4"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] PartitionCols:_col0 - Select Operator [SEL_124] (rows=1704 width=1910) + Select Operator [SEL_121] (rows=85 width=102) Output:["_col0"] - Filter Operator [FIL_123] (rows=1704 width=1910) + Filter Operator [FIL_120] (rows=85 width=102) predicate:((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') and s_store_sk is not null) - TableScan [TS_12] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_county"] - <-Reducer 7 [SIMPLE_EDGE] + TableScan [TS_12] (rows=1704 width=102) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_county"] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_98] (rows=696954748 width=88) - Conds:RS_18._col2=RS_117._col0(Inner),Output:["_col1","_col3","_col4"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] + Merge Join Operator [MERGEJOIN_98] (rows=11405013 width=4) + Conds:RS_18._col2=RS_114._col0(Inner),Output:["_col1","_col3","_col4"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_116] (rows=1200 width=107) + Select Operator [SEL_113] (rows=480 width=104) Output:["_col0"] - Filter Operator [FIL_115] (rows=1200 width=107) + Filter Operator [FIL_112] (rows=480 width=104) predicate:((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (null) END and hd_demo_sk is not null) - TableScan [TS_9] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] - <-Reducer 6 [SIMPLE_EDGE] + TableScan [TS_9] (rows=7200 width=104) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_97] (rows=633595212 width=88) - Conds:RS_135._col0=RS_109._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_109] + Merge Join Operator [MERGEJOIN_97] (rows=171075172 width=14) + Conds:RS_130._col0=RS_106._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_108] (rows=8116 width=1119) + Select Operator [SEL_105] (rows=652 width=12) Output:["_col0"] - Filter Operator [FIL_107] (rows=8116 width=1119) + Filter Operator [FIL_104] (rows=652 width=12) predicate:((d_year) IN (2000, 2001, 2002) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dom"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dom"] + <-Map 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_130] PartitionCols:_col0 - Select Operator [SEL_134] (rows=575995635 width=88) + Select Operator [SEL_129] (rows=479121995 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_133] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_31_customer_c_customer_sk_min) AND DynamicValue(RS_31_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_31_customer_c_customer_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_114] - Group By Operator [GBY_113] (rows=1 width=12) + Filter Operator [FIL_128] (rows=479121995 width=19) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_3] (rows=575995635 width=19) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_111] + Group By Operator [GBY_110] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] - Group By Operator [GBY_111] (rows=1 width=12) + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_109] + Group By Operator [GBY_108] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_110] (rows=8116 width=1119) + Select Operator [SEL_107] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_108] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_122] - Group By Operator [GBY_121] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_105] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_119] + Group By Operator [GBY_118] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] - Group By Operator [GBY_119] (rows=1 width=12) + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_117] + Group By Operator [GBY_116] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_118] (rows=1200 width=107) + Select Operator [SEL_115] (rows=480 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_116] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_130] - Group By Operator [GBY_129] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_113] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_127] + Group By Operator [GBY_126] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_128] - Group By Operator [GBY_127] (rows=1 width=12) + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] + Group By Operator [GBY_124] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_126] (rows=1704 width=1910) + Select Operator [SEL_123] (rows=85 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_124] - <-Reducer 4 [BROADCAST_EDGE] vectorized - BROADCAST [RS_132] - Group By Operator [GBY_131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_104] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] + Please refer to the previous Select Operator [SEL_121] diff --git a/ql/src/test/results/clientpositive/perf/tez/query74.q.out b/ql/src/test/results/clientpositive/perf/tez/query74.q.out index 82f6655515..70d2d38b7c 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query74.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query74.q.out @@ -123,8 +123,8 @@ Plan optimized by CBO. Vertex dependency in root stage Map 1 <- Reducer 21 (BROADCAST_EDGE) Map 11 <- Reducer 23 (BROADCAST_EDGE) -Map 15 <- Reducer 20 (BROADCAST_EDGE), Reducer 25 (BROADCAST_EDGE) -Map 7 <- Reducer 22 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE) +Map 15 <- Reducer 20 (BROADCAST_EDGE) +Map 7 <- Reducer 22 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) @@ -137,8 +137,6 @@ Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 21 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 22 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 23 <- Map 19 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 24 (CUSTOM_SIMPLE_EDGE) -Reducer 26 <- Map 24 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 24 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 10 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) @@ -151,159 +149,148 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_356] - Limit [LIM_355] (rows=100 width=88) + File Output Operator [FS_346] + Limit [LIM_345] (rows=100 width=280) Number of rows:100 - Select Operator [SEL_354] (rows=574987679 width=88) + Select Operator [SEL_344] (rows=93786629 width=280) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_89] - Select Operator [SEL_88] (rows=574987679 width=88) + Select Operator [SEL_88] (rows=93786629 width=280) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_87] (rows=574987679 width=88) + Filter Operator [FIL_87] (rows=93786629 width=728) predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col9 / _col3))) ELSE ((null > (_col9 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END - Merge Join Operator [MERGEJOIN_279] (rows=1149975359 width=88) - Conds:RS_321._col0=RS_333._col0(Inner),RS_333._col0=RS_343._col0(Inner),RS_333._col0=RS_353._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col9"] + Merge Join Operator [MERGEJOIN_279] (rows=187573258 width=728) + Conds:RS_315._col0=RS_325._col0(Inner),RS_325._col0=RS_335._col0(Inner),RS_325._col0=RS_343._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_333] + SHUFFLE [RS_325] PartitionCols:_col0 - Select Operator [SEL_332] (rows=116159124 width=88) + Select Operator [SEL_324] (rows=62524419 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_331] (rows=116159124 width=88) + Filter Operator [FIL_323] (rows=62524419 width=212) predicate:(_col4 > 0) - Select Operator [SEL_330] (rows=348477374 width=88) + Select Operator [SEL_322] (rows=187573258 width=212) Output:["_col0","_col4"] - Group By Operator [GBY_329] (rows=348477374 width=88) + Group By Operator [GBY_321] (rows=187573258 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_36] (rows=696954748 width=88) + Group By Operator [GBY_36] (rows=187573258 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_274] (rows=696954748 width=88) - Conds:RS_32._col1=RS_312._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_274] (rows=187573258 width=381) + Conds:RS_32._col1=RS_311._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_312] + SHUFFLE [RS_311] PartitionCols:_col0 - Select Operator [SEL_308] (rows=80000000 width=860) + Select Operator [SEL_308] (rows=80000000 width=284) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_307] (rows=80000000 width=860) + Filter Operator [FIL_307] (rows=80000000 width=284) predicate:(c_customer_id is not null and c_customer_sk is not null) - TableScan [TS_68] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name"] + TableScan [TS_68] (rows=80000000 width=284) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_273] (rows=633595212 width=88) - Conds:RS_328._col0=RS_290._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_273] (rows=187573258 width=105) + Conds:RS_320._col0=RS_290._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_290] PartitionCols:_col0 - Select Operator [SEL_284] (rows=36524 width=1119) + Select Operator [SEL_284] (rows=652 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_281] (rows=36524 width=1119) + Filter Operator [FIL_281] (rows=652 width=8) predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) - TableScan [TS_65] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_65] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_328] + SHUFFLE [RS_320] PartitionCols:_col0 - Select Operator [SEL_327] (rows=575995635 width=88) + Select Operator [SEL_319] (rows=525327388 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_326] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_33_customer_c_customer_sk_min) AND DynamicValue(RS_33_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_33_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_20] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] + Filter Operator [FIL_318] (rows=525327388 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_20] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_323] - Group By Operator [GBY_322] (rows=1 width=12) + BROADCAST [RS_317] + Group By Operator [GBY_316] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_300] Group By Operator [GBY_296] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_291] (rows=36524 width=1119) + Select Operator [SEL_291] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_284] - <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_325] - Group By Operator [GBY_324] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] - Group By Operator [GBY_316] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_313] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_308] <-Reducer 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_343] + SHUFFLE [RS_335] PartitionCols:_col0 - Select Operator [SEL_342] (rows=29040539 width=135) + Select Operator [SEL_334] (rows=17130654 width=212) Output:["_col0","_col1"] - Filter Operator [FIL_341] (rows=29040539 width=135) + Filter Operator [FIL_333] (rows=17130654 width=212) predicate:(_col4 > 0) - Select Operator [SEL_340] (rows=87121617 width=135) + Select Operator [SEL_332] (rows=51391963 width=212) Output:["_col0","_col4"] - Group By Operator [GBY_339] (rows=87121617 width=135) + Group By Operator [GBY_331] (rows=51391963 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_58] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_57] (rows=174243235 width=135) + Group By Operator [GBY_57] (rows=51391963 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_276] (rows=174243235 width=135) - Conds:RS_53._col1=RS_314._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_276] (rows=51391963 width=395) + Conds:RS_53._col1=RS_312._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_314] + SHUFFLE [RS_312] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_308] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_275] (rows=158402938 width=135) - Conds:RS_338._col0=RS_292._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_275] (rows=51391963 width=119) + Conds:RS_330._col0=RS_292._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_292] PartitionCols:_col0 - Select Operator [SEL_285] (rows=36524 width=1119) + Select Operator [SEL_285] (rows=652 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_282] (rows=36524 width=1119) + Filter Operator [FIL_282] (rows=652 width=8) predicate:((d_year = 2001) and (d_year) IN (2001, 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_65] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_338] + SHUFFLE [RS_330] PartitionCols:_col0 - Select Operator [SEL_337] (rows=144002668 width=135) + Select Operator [SEL_329] (rows=143930993 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_336] (rows=144002668 width=135) + Filter Operator [FIL_328] (rows=143930993 width=119) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_51_date_dim_d_date_sk_min) AND DynamicValue(RS_51_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_51_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_41] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] + TableScan [TS_41] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_335] - Group By Operator [GBY_334] (rows=1 width=12) + BROADCAST [RS_327] + Group By Operator [GBY_326] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_301] Group By Operator [GBY_297] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_293] (rows=36524 width=1119) + Select Operator [SEL_293] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_285] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_353] + SHUFFLE [RS_343] PartitionCols:_col0 - Select Operator [SEL_352] (rows=348477374 width=88) + Select Operator [SEL_342] (rows=187573258 width=392) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_351] (rows=348477374 width=88) + Group By Operator [GBY_341] (rows=187573258 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_79] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_78] (rows=696954748 width=88) + Group By Operator [GBY_78] (rows=187573258 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_278] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_278] (rows=187573258 width=381) Conds:RS_74._col1=RS_309._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized SHUFFLE [RS_309] @@ -312,69 +299,58 @@ Stage-0 <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_74] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_277] (rows=633595212 width=88) - Conds:RS_350._col0=RS_286._col0(Inner),Output:["_col1","_col2","_col4"] + Merge Join Operator [MERGEJOIN_277] (rows=187573258 width=105) + Conds:RS_340._col0=RS_286._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_286] PartitionCols:_col0 - Select Operator [SEL_283] (rows=36524 width=1119) + Select Operator [SEL_283] (rows=652 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_280] (rows=36524 width=1119) + Filter Operator [FIL_280] (rows=652 width=8) predicate:((d_year = 2002) and (d_year) IN (2001, 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_65] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_350] + SHUFFLE [RS_340] PartitionCols:_col0 - Select Operator [SEL_349] (rows=575995635 width=88) + Select Operator [SEL_339] (rows=525327388 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_348] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_75_customer_c_customer_sk_min) AND DynamicValue(RS_75_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_75_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_62] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] + Filter Operator [FIL_338] (rows=525327388 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_62] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_net_paid"] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_345] - Group By Operator [GBY_344] (rows=1 width=12) + BROADCAST [RS_337] + Group By Operator [GBY_336] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_298] Group By Operator [GBY_294] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_287] (rows=36524 width=1119) + Select Operator [SEL_287] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_283] - <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_347] - Group By Operator [GBY_346] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 24 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_317] - Group By Operator [GBY_315] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_310] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_308] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_321] + SHUFFLE [RS_315] PartitionCols:_col0 - Select Operator [SEL_320] (rows=87121617 width=135) + Select Operator [SEL_314] (rows=51391963 width=212) Output:["_col0","_col1"] - Group By Operator [GBY_319] (rows=87121617 width=135) + Group By Operator [GBY_313] (rows=51391963 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_16] (rows=174243235 width=135) + Group By Operator [GBY_16] (rows=51391963 width=396) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["max(_col2)"],keys:_col6, _col7, _col8, _col4 - Merge Join Operator [MERGEJOIN_272] (rows=174243235 width=135) - Conds:RS_12._col1=RS_311._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_272] (rows=51391963 width=395) + Conds:RS_12._col1=RS_310._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_311] + SHUFFLE [RS_310] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_308] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_271] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_271] (rows=51391963 width=119) Conds:RS_306._col0=RS_288._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_288] @@ -383,12 +359,12 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] PartitionCols:_col0 - Select Operator [SEL_305] (rows=144002668 width=135) + Select Operator [SEL_305] (rows=143930993 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_304] (rows=144002668 width=135) + Filter Operator [FIL_304] (rows=143930993 width=119) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] + TableScan [TS_0] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_net_paid"] <-Reducer 21 [BROADCAST_EDGE] vectorized BROADCAST [RS_303] Group By Operator [GBY_302] (rows=1 width=12) @@ -397,7 +373,7 @@ Stage-0 SHUFFLE [RS_299] Group By Operator [GBY_295] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_289] (rows=36524 width=1119) + Select Operator [SEL_289] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_283] diff --git a/ql/src/test/results/clientpositive/perf/tez/query75.q.out b/ql/src/test/results/clientpositive/perf/tez/query75.q.out index 2f7c8ff787..8d01a31e5c 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query75.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query75.q.out @@ -188,91 +188,91 @@ Stage-0 Stage-1 Reducer 10 vectorized File Output Operator [FS_638] - Select Operator [SEL_637] (rows=100 width=111) + Select Operator [SEL_637] (rows=100 width=160) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Limit [LIM_636] (rows=100 width=111) + Limit [LIM_636] (rows=100 width=152) Number of rows:100 - Select Operator [SEL_635] (rows=70276244 width=111) + Select Operator [SEL_635] (rows=3422897230256 width=151) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_175] - Select Operator [SEL_174] (rows=70276244 width=111) + Select Operator [SEL_174] (rows=3422897230256 width=151) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_173] (rows=70276244 width=111) + Filter Operator [FIL_173] (rows=3422897230256 width=255) predicate:((CAST( _col10 AS decimal(17,2)) / CAST( _col4 AS decimal(17,2))) < 0.9) - Merge Join Operator [MERGEJOIN_518] (rows=210828734 width=111) + Merge Join Operator [MERGEJOIN_518] (rows=10268691690770 width=255) Conds:RS_631._col0, _col1, _col2, _col3=RS_634._col0, _col1, _col2, _col3(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col10","_col11"] <-Reducer 27 [SIMPLE_EDGE] vectorized SHUFFLE [RS_634] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_633] (rows=191662482 width=111) + Group By Operator [GBY_633] (rows=84235776 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 - Group By Operator [GBY_632] (rows=383324964 width=111) + Group By Operator [GBY_632] (rows=549581438 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 26 [SIMPLE_EDGE] <-Reducer 25 [CONTAINS] vectorized Reduce Output Operator [RS_670] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_669] (rows=766649929 width=111) + Group By Operator [GBY_669] (rows=549581438 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_668] (rows=574982367 width=103) + Group By Operator [GBY_668] (rows=461495441 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 24 [SIMPLE_EDGE] <-Reducer 23 [CONTAINS] Reduce Output Operator [RS_542] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_541] (rows=1149964734 width=103) + Group By Operator [GBY_541] (rows=461495441 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_539] (rows=383314495 width=135) + Select Operator [SEL_539] (rows=152879623 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_538] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_538] (rows=152879623 width=246) Conds:RS_103._col1, _col2=RS_625._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] <-Map 44 [SIMPLE_EDGE] vectorized SHUFFLE [RS_625] PartitionCols:_col0, _col1 - Select Operator [SEL_623] (rows=28798881 width=106) + Select Operator [SEL_623] (rows=28798881 width=121) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_622] (rows=28798881 width=106) + Filter Operator [FIL_622] (rows=28798881 width=121) predicate:cr_item_sk is not null - TableScan [TS_9] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] + TableScan [TS_9] (rows=28798881 width=121) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_103] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_510] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_510] (rows=96821196 width=138) Conds:RS_100._col1=RS_599._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_599] PartitionCols:_col0 - Select Operator [SEL_592] (rows=231000 width=1436) + Select Operator [SEL_592] (rows=45745 width=109) Output:["_col0","_col1","_col2","_col3","_col5"] - Filter Operator [FIL_591] (rows=231000 width=1436) + Filter Operator [FIL_591] (rows=45745 width=109) predicate:((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] + TableScan [TS_6] (rows=462000 width=109) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_100] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_509] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_509] (rows=101592102 width=122) Conds:RS_667._col0=RS_571._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_571] PartitionCols:_col0 - Select Operator [SEL_562] (rows=36524 width=1119) + Select Operator [SEL_562] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_558] (rows=36524 width=1119) + Filter Operator [FIL_558] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 49 [SIMPLE_EDGE] vectorized SHUFFLE [RS_667] PartitionCols:_col0 - Select Operator [SEL_666] (rows=287989836 width=135) + Select Operator [SEL_666] (rows=286549727 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_665] (rows=287989836 width=135) + Filter Operator [FIL_665] (rows=286549727 width=127) predicate:((cs_item_sk BETWEEN DynamicValue(RS_101_item_i_item_sk_min) AND DynamicValue(RS_101_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_101_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_98_date_dim_d_date_sk_min) AND DynamicValue(RS_98_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_98_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_85] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] + TableScan [TS_85] (rows=287989836 width=127) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] <-Reducer 28 [BROADCAST_EDGE] vectorized BROADCAST [RS_662] Group By Operator [GBY_661] (rows=1 width=12) @@ -281,7 +281,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_586] Group By Operator [GBY_580] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_572] (rows=36524 width=1119) + Select Operator [SEL_572] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_562] <-Reducer 41 [BROADCAST_EDGE] vectorized @@ -292,31 +292,31 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_614] Group By Operator [GBY_608] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_600] (rows=231000 width=1436) + Select Operator [SEL_600] (rows=45745 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_592] <-Reducer 31 [CONTAINS] Reduce Output Operator [RS_551] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_550] (rows=1149964734 width=103) + Group By Operator [GBY_550] (rows=461495441 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_548] (rows=766650239 width=88) + Select Operator [SEL_548] (rows=308615818 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_547] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_547] (rows=308615818 width=237) Conds:RS_125._col1, _col2=RS_649._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] <-Map 46 [SIMPLE_EDGE] vectorized SHUFFLE [RS_649] PartitionCols:_col0, _col1 - Select Operator [SEL_647] (rows=57591150 width=77) + Select Operator [SEL_647] (rows=57591150 width=119) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_646] (rows=57591150 width=77) + Filter Operator [FIL_646] (rows=57591150 width=119) predicate:sr_item_sk is not null - TableScan [TS_31] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] + TableScan [TS_31] (rows=57591150 width=119) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] <-Reducer 30 [SIMPLE_EDGE] SHUFFLE [RS_125] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_513] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_513] (rows=187186493 width=124) Conds:RS_122._col1=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_601] @@ -325,25 +325,25 @@ Stage-0 <-Reducer 29 [SIMPLE_EDGE] SHUFFLE [RS_122] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_512] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_512] (rows=196410188 width=109) Conds:RS_677._col0=RS_573._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_573] PartitionCols:_col0 - Select Operator [SEL_563] (rows=36524 width=1119) + Select Operator [SEL_563] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_559] (rows=36524 width=1119) + Filter Operator [FIL_559] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 50 [SIMPLE_EDGE] vectorized SHUFFLE [RS_677] PartitionCols:_col0 - Select Operator [SEL_676] (rows=575995635 width=88) + Select Operator [SEL_676] (rows=550076554 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_675] (rows=575995635 width=88) + Filter Operator [FIL_675] (rows=550076554 width=122) predicate:((ss_item_sk BETWEEN DynamicValue(RS_123_item_i_item_sk_min) AND DynamicValue(RS_123_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_123_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_120_date_dim_d_date_sk_min) AND DynamicValue(RS_120_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_120_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_107] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] + TableScan [TS_107] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] <-Reducer 32 [BROADCAST_EDGE] vectorized BROADCAST [RS_672] Group By Operator [GBY_671] (rows=1 width=12) @@ -352,7 +352,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_587] Group By Operator [GBY_581] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_574] (rows=36524 width=1119) + Select Operator [SEL_574] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_563] <-Reducer 42 [BROADCAST_EDGE] vectorized @@ -363,31 +363,31 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_615] Group By Operator [GBY_609] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_602] (rows=231000 width=1436) + Select Operator [SEL_602] (rows=45745 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_592] <-Reducer 35 [CONTAINS] Reduce Output Operator [RS_556] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_555] (rows=766649929 width=111) + Group By Operator [GBY_555] (rows=549581438 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_553] (rows=191667562 width=135) + Select Operator [SEL_553] (rows=88085997 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_552] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_552] (rows=88085997 width=247) Conds:RS_154._col1, _col2=RS_660._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] <-Map 48 [SIMPLE_EDGE] vectorized SHUFFLE [RS_660] PartitionCols:_col0, _col1 - Select Operator [SEL_658] (rows=14398467 width=92) + Select Operator [SEL_658] (rows=14398467 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_657] (rows=14398467 width=92) + Filter Operator [FIL_657] (rows=14398467 width=118) predicate:wr_item_sk is not null - TableScan [TS_60] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] + TableScan [TS_60] (rows=14398467 width=118) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] <-Reducer 34 [SIMPLE_EDGE] SHUFFLE [RS_154] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_516] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_516] (rows=48990732 width=139) Conds:RS_151._col1=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_603] @@ -396,25 +396,25 @@ Stage-0 <-Reducer 33 [SIMPLE_EDGE] SHUFFLE [RS_151] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_515] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_515] (rows=51404771 width=123) Conds:RS_684._col0=RS_575._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_575] PartitionCols:_col0 - Select Operator [SEL_564] (rows=36524 width=1119) + Select Operator [SEL_564] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_560] (rows=36524 width=1119) + Filter Operator [FIL_560] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 51 [SIMPLE_EDGE] vectorized SHUFFLE [RS_684] PartitionCols:_col0 - Select Operator [SEL_683] (rows=144002668 width=135) + Select Operator [SEL_683] (rows=143966864 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_682] (rows=144002668 width=135) + Filter Operator [FIL_682] (rows=143966864 width=127) predicate:((ws_item_sk BETWEEN DynamicValue(RS_152_item_i_item_sk_min) AND DynamicValue(RS_152_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_152_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_149_date_dim_d_date_sk_min) AND DynamicValue(RS_149_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_149_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_136] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] + TableScan [TS_136] (rows=144002668 width=127) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] <-Reducer 36 [BROADCAST_EDGE] vectorized BROADCAST [RS_679] Group By Operator [GBY_678] (rows=1 width=12) @@ -423,7 +423,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_588] Group By Operator [GBY_582] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_576] (rows=36524 width=1119) + Select Operator [SEL_576] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_564] <-Reducer 43 [BROADCAST_EDGE] vectorized @@ -434,25 +434,25 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_616] Group By Operator [GBY_610] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_604] (rows=231000 width=1436) + Select Operator [SEL_604] (rows=45745 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_592] <-Reducer 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_631] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_630] (rows=191662482 width=111) + Group By Operator [GBY_630] (rows=84235776 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 - Group By Operator [GBY_629] (rows=383324964 width=111) + Group By Operator [GBY_629] (rows=549581438 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 7 [SIMPLE_EDGE] <-Reducer 19 [CONTAINS] Reduce Output Operator [RS_537] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_536] (rows=766649929 width=111) + Group By Operator [GBY_536] (rows=549581438 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_534] (rows=191667562 width=135) + Select Operator [SEL_534] (rows=88085997 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_533] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_533] (rows=88085997 width=247) Conds:RS_69._col1, _col2=RS_659._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] <-Map 48 [SIMPLE_EDGE] vectorized SHUFFLE [RS_659] @@ -461,7 +461,7 @@ Stage-0 <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_507] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_507] (rows=48990732 width=139) Conds:RS_66._col1=RS_597._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_597] @@ -470,25 +470,25 @@ Stage-0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_506] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_506] (rows=51404771 width=123) Conds:RS_656._col0=RS_569._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_569] PartitionCols:_col0 - Select Operator [SEL_561] (rows=36524 width=1119) + Select Operator [SEL_561] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_557] (rows=36524 width=1119) + Filter Operator [FIL_557] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 47 [SIMPLE_EDGE] vectorized SHUFFLE [RS_656] PartitionCols:_col0 - Select Operator [SEL_655] (rows=144002668 width=135) + Select Operator [SEL_655] (rows=143966864 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_654] (rows=144002668 width=135) + Filter Operator [FIL_654] (rows=143966864 width=127) predicate:((ws_item_sk BETWEEN DynamicValue(RS_67_item_i_item_sk_min) AND DynamicValue(RS_67_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_67_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_64_date_dim_d_date_sk_min) AND DynamicValue(RS_64_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_64_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_51] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] + TableScan [TS_51] (rows=144002668 width=127) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] <-Reducer 20 [BROADCAST_EDGE] vectorized BROADCAST [RS_651] Group By Operator [GBY_650] (rows=1 width=12) @@ -497,7 +497,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_585] Group By Operator [GBY_579] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_570] (rows=36524 width=1119) + Select Operator [SEL_570] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_561] <-Reducer 40 [BROADCAST_EDGE] vectorized @@ -508,25 +508,25 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_613] Group By Operator [GBY_607] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_598] (rows=231000 width=1436) + Select Operator [SEL_598] (rows=45745 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_592] <-Reducer 6 [CONTAINS] vectorized Reduce Output Operator [RS_628] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_627] (rows=766649929 width=111) + Group By Operator [GBY_627] (rows=549581438 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_626] (rows=574982367 width=103) + Group By Operator [GBY_626] (rows=461495441 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 5 [SIMPLE_EDGE] <-Reducer 15 [CONTAINS] Reduce Output Operator [RS_532] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_531] (rows=1149964734 width=103) + Group By Operator [GBY_531] (rows=461495441 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_529] (rows=766650239 width=88) + Select Operator [SEL_529] (rows=308615818 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_528] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_528] (rows=308615818 width=237) Conds:RS_40._col1, _col2=RS_648._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] <-Map 46 [SIMPLE_EDGE] vectorized SHUFFLE [RS_648] @@ -535,7 +535,7 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_504] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_504] (rows=187186493 width=124) Conds:RS_37._col1=RS_595._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_595] @@ -544,7 +544,7 @@ Stage-0 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_503] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_503] (rows=196410188 width=109) Conds:RS_645._col0=RS_567._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_567] @@ -553,12 +553,12 @@ Stage-0 <-Map 45 [SIMPLE_EDGE] vectorized SHUFFLE [RS_645] PartitionCols:_col0 - Select Operator [SEL_644] (rows=575995635 width=88) + Select Operator [SEL_644] (rows=550076554 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_643] (rows=575995635 width=88) + Filter Operator [FIL_643] (rows=550076554 width=122) predicate:((ss_item_sk BETWEEN DynamicValue(RS_38_item_i_item_sk_min) AND DynamicValue(RS_38_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_38_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_22] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] + TableScan [TS_22] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_640] Group By Operator [GBY_639] (rows=1 width=12) @@ -567,7 +567,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_584] Group By Operator [GBY_578] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_568] (rows=36524 width=1119) + Select Operator [SEL_568] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_561] <-Reducer 39 [BROADCAST_EDGE] vectorized @@ -578,17 +578,17 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_612] Group By Operator [GBY_606] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_596] (rows=231000 width=1436) + Select Operator [SEL_596] (rows=45745 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_592] <-Reducer 4 [CONTAINS] Reduce Output Operator [RS_523] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_522] (rows=1149964734 width=103) + Group By Operator [GBY_522] (rows=461495441 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Select Operator [SEL_520] (rows=383314495 width=135) + Select Operator [SEL_520] (rows=152879623 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_519] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_519] (rows=152879623 width=246) Conds:RS_18._col1, _col2=RS_624._col0, _col1(Left Outer),Output:["_col3","_col4","_col8","_col9","_col10","_col12","_col15","_col16"] <-Map 44 [SIMPLE_EDGE] vectorized SHUFFLE [RS_624] @@ -597,7 +597,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_501] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_501] (rows=96821196 width=138) Conds:RS_15._col1=RS_593._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col8","_col9","_col10","_col12"] <-Map 37 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_593] @@ -606,7 +606,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_500] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_500] (rows=101592102 width=122) Conds:RS_621._col0=RS_565._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_565] @@ -615,12 +615,12 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_621] PartitionCols:_col0 - Select Operator [SEL_620] (rows=287989836 width=135) + Select Operator [SEL_620] (rows=286549727 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_619] (rows=287989836 width=135) + Filter Operator [FIL_619] (rows=286549727 width=127) predicate:((cs_item_sk BETWEEN DynamicValue(RS_16_item_i_item_sk_min) AND DynamicValue(RS_16_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_16_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] + TableScan [TS_0] (rows=287989836 width=127) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] <-Reducer 12 [BROADCAST_EDGE] vectorized BROADCAST [RS_590] Group By Operator [GBY_589] (rows=1 width=12) @@ -629,7 +629,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_583] Group By Operator [GBY_577] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_566] (rows=36524 width=1119) + Select Operator [SEL_566] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_561] <-Reducer 38 [BROADCAST_EDGE] vectorized @@ -640,7 +640,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_611] Group By Operator [GBY_605] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_594] (rows=231000 width=1436) + Select Operator [SEL_594] (rows=45745 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_592] diff --git a/ql/src/test/results/clientpositive/perf/tez/query76.q.out b/ql/src/test/results/clientpositive/perf/tez/query76.q.out index c1d7b97579..bdf8712abe 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query76.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query76.q.out @@ -47,222 +47,147 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 14 <- Reducer 16 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Map 17 <- Reducer 10 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE) -Map 20 <- Reducer 13 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE) -Reducer 10 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Map 1 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 12 <- Map 21 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 13 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) -Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 10 <- Map 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) Reducer 5 <- Union 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) -Reducer 9 <- Map 18 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 7 <- Map 1 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 8 <- Map 14 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 9 <- Map 1 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_199] - Limit [LIM_198] (rows=100 width=108) + File Output Operator [FS_183] + Limit [LIM_182] (rows=100 width=408) Number of rows:100 - Select Operator [SEL_197] (rows=304916424 width=108) + Select Operator [SEL_181] (rows=5600 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_196] - Group By Operator [GBY_195] (rows=304916424 width=108) + SHUFFLE [RS_180] + Group By Operator [GBY_179] (rows=5600 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Union 4 [SIMPLE_EDGE] - <-Reducer 12 [CONTAINS] + <-Reducer 10 [CONTAINS] Reduce Output Operator [RS_167] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_166] (rows=609832848 width=108) + Group By Operator [GBY_166] (rows=224000 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["count()","sum(_col5)"],keys:_col0, _col1, _col2, _col3, _col4 - Top N Key Operator [TNK_165] (rows=609832848 width=108) + Top N Key Operator [TNK_165] (rows=26219002 width=388) keys:_col0, _col1, _col2, _col3, _col4,sort order:+++++,top n:100 - Select Operator [SEL_163] (rows=174233858 width=135) + Select Operator [SEL_163] (rows=1433911 width=399) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_162] (rows=174233858 width=135) - Conds:RS_45._col0=RS_217._col0(Inner),Output:["_col3","_col5","_col7","_col8"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_217] + Merge Join Operator [MERGEJOIN_162] (rows=1433911 width=209) + Conds:RS_45._col0=RS_195._col0(Inner),Output:["_col3","_col5","_col7","_col8"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_195] PartitionCols:_col0 - Select Operator [SEL_216] (rows=73049 width=1119) + Select Operator [SEL_194] (rows=73049 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_215] (rows=73049 width=1119) + Filter Operator [FIL_193] (rows=73049 width=12) predicate:d_date_sk is not null - TableScan [TS_39] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Reducer 11 [SIMPLE_EDGE] + TableScan [TS_39] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_148] (rows=158394413 width=135) - Conds:RS_225._col2=RS_174._col0(Inner),Output:["_col0","_col3","_col5"] + Merge Join Operator [MERGEJOIN_148] (rows=1433911 width=205) + Conds:RS_192._col2=RS_172._col0(Inner),Output:["_col0","_col3","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_174] + SHUFFLE [RS_172] PartitionCols:_col0 - Select Operator [SEL_169] (rows=462000 width=1436) + Select Operator [SEL_169] (rows=462000 width=94) Output:["_col0","_col1"] - Filter Operator [FIL_168] (rows=462000 width=1436) + Filter Operator [FIL_168] (rows=462000 width=94) predicate:i_item_sk is not null - TableScan [TS_0] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_category"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_225] + TableScan [TS_0] (rows=462000 width=94) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_category"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_192] PartitionCols:_col2 - Select Operator [SEL_224] (rows=143994918 width=135) + Select Operator [SEL_191] (rows=1433911 width=119) Output:["_col0","_col2","_col3"] - Filter Operator [FIL_223] (rows=143994918 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_43_item_i_item_sk_min) AND DynamicValue(RS_43_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_43_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_46_date_dim_d_date_sk_min) AND DynamicValue(RS_46_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_46_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is null) - TableScan [TS_33] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_warehouse_sk","cs_item_sk","cs_ext_sales_price"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_214] - Group By Operator [GBY_213] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_181] - Group By Operator [GBY_178] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_175] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_169] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_222] - Group By Operator [GBY_221] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_220] - Group By Operator [GBY_219] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_218] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_216] + Filter Operator [FIL_190] (rows=1433911 width=123) + predicate:(cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is null) + TableScan [TS_33] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_warehouse_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 3 [CONTAINS] Reduce Output Operator [RS_155] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_154] (rows=609832848 width=108) + Group By Operator [GBY_154] (rows=224000 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["count()","sum(_col5)"],keys:_col0, _col1, _col2, _col3, _col4 - Top N Key Operator [TNK_153] (rows=609832848 width=108) + Top N Key Operator [TNK_153] (rows=26219002 width=388) keys:_col0, _col1, _col2, _col3, _col4,sort order:+++++,top n:100 - Select Operator [SEL_151] (rows=348477373 width=88) + Select Operator [SEL_151] (rows=24749363 width=387) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_150] (rows=348477373 width=88) - Conds:RS_12._col2=RS_186._col0(Inner),Output:["_col1","_col5","_col7","_col8"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_186] + Merge Join Operator [MERGEJOIN_150] (rows=24749363 width=204) + Conds:RS_12._col2=RS_178._col0(Inner),Output:["_col1","_col5","_col7","_col8"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_178] PartitionCols:_col0 - Select Operator [SEL_185] (rows=73049 width=1119) + Select Operator [SEL_177] (rows=73049 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_184] (rows=73049 width=1119) + Filter Operator [FIL_176] (rows=73049 width=12) predicate:d_date_sk is not null - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_144] (rows=316797605 width=88) - Conds:RS_170._col0=RS_194._col1(Inner),Output:["_col1","_col2","_col5"] + Merge Join Operator [MERGEJOIN_144] (rows=24749363 width=200) + Conds:RS_170._col0=RS_175._col1(Inner),Output:["_col1","_col2","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_170] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_169] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_194] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_175] PartitionCols:_col1 - Select Operator [SEL_193] (rows=287997817 width=88) + Select Operator [SEL_174] (rows=24749363 width=114) Output:["_col0","_col1","_col3"] - Filter Operator [FIL_192] (rows=287997817 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_9_item_i_item_sk_min) AND DynamicValue(RS_9_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_9_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is null and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_191] - Group By Operator [GBY_190] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_189] - Group By Operator [GBY_188] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_187] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_185] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_183] - Group By Operator [GBY_182] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_179] - Group By Operator [GBY_176] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_171] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_169] - <-Reducer 9 [CONTAINS] + Filter Operator [FIL_173] (rows=24749363 width=118) + predicate:(ss_addr_sk is null and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_3] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] + <-Reducer 8 [CONTAINS] Reduce Output Operator [RS_161] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_160] (rows=609832848 width=108) + Group By Operator [GBY_160] (rows=224000 width=408) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["count()","sum(_col5)"],keys:_col0, _col1, _col2, _col3, _col4 - Top N Key Operator [TNK_159] (rows=609832848 width=108) + Top N Key Operator [TNK_159] (rows=26219002 width=388) keys:_col0, _col1, _col2, _col3, _col4,sort order:+++++,top n:100 - Select Operator [SEL_157] (rows=87121617 width=135) + Select Operator [SEL_157] (rows=35728 width=394) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_156] (rows=87121617 width=135) - Conds:RS_28._col0=RS_204._col0(Inner),Output:["_col3","_col5","_col7","_col8"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_204] + Merge Join Operator [MERGEJOIN_156] (rows=35728 width=209) + Conds:RS_28._col0=RS_189._col0(Inner),Output:["_col3","_col5","_col7","_col8"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_189] PartitionCols:_col0 - Select Operator [SEL_203] (rows=73049 width=1119) + Select Operator [SEL_188] (rows=73049 width=12) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_202] (rows=73049 width=1119) + Filter Operator [FIL_187] (rows=73049 width=12) predicate:d_date_sk is not null - TableScan [TS_22] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Reducer 8 [SIMPLE_EDGE] + TableScan [TS_22] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_146] (rows=79201469 width=135) - Conds:RS_212._col1=RS_172._col0(Inner),Output:["_col0","_col3","_col5"] + Merge Join Operator [MERGEJOIN_146] (rows=35728 width=205) + Conds:RS_186._col1=RS_171._col0(Inner),Output:["_col0","_col3","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_172] + SHUFFLE [RS_171] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_169] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_212] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_186] PartitionCols:_col1 - Select Operator [SEL_211] (rows=72001334 width=135) + Select Operator [SEL_185] (rows=35728 width=119) Output:["_col0","_col1","_col3"] - Filter Operator [FIL_210] (rows=72001334 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_26_item_i_item_sk_min) AND DynamicValue(RS_26_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_26_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_29_date_dim_d_date_sk_min) AND DynamicValue(RS_29_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_29_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null and ws_web_page_sk is null) - TableScan [TS_16] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_ext_sales_price"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_201] - Group By Operator [GBY_200] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_180] - Group By Operator [GBY_177] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_173] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_169] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_209] - Group By Operator [GBY_208] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_207] - Group By Operator [GBY_206] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_205] (rows=73049 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_203] + Filter Operator [FIL_184] (rows=35728 width=123) + predicate:(ws_item_sk is not null and ws_sold_date_sk is not null and ws_web_page_sk is null) + TableScan [TS_16] (rows=144002668 width=123) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_ext_sales_price"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query77.q.out b/ql/src/test/results/clientpositive/perf/tez/query77.q.out index 617a47346f..96257e7da5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query77.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query77.q.out @@ -214,31 +214,29 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE) -Map 31 <- Reducer 17 (BROADCAST_EDGE) -Map 33 <- Reducer 24 (BROADCAST_EDGE), Reducer 35 (BROADCAST_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE) +Map 30 <- Reducer 17 (BROADCAST_EDGE) +Map 32 <- Reducer 24 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Map 30 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 11 <- Map 29 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) Reducer 12 <- Map 28 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) Reducer 13 <- Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 31 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 14 <- Map 30 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) Reducer 15 <- Reducer 14 (SIMPLE_EDGE) Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 19 (CUSTOM_SIMPLE_EDGE), Union 6 (CONTAINS) Reducer 17 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 32 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 18 <- Map 31 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 20 <- Map 33 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 21 <- Map 34 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 20 <- Map 32 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 21 <- Map 33 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) Reducer 22 <- Reducer 21 (SIMPLE_EDGE) Reducer 23 <- Reducer 22 (ONE_TO_ONE_EDGE), Reducer 27 (ONE_TO_ONE_EDGE), Union 6 (CONTAINS) Reducer 24 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 36 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 26 <- Map 34 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) +Reducer 25 <- Map 34 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 26 <- Map 33 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) Reducer 27 <- Reducer 26 (SIMPLE_EDGE) -Reducer 29 <- Map 28 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 28 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 35 <- Map 34 (CUSTOM_SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 13 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE), Union 6 (CONTAINS) Reducer 7 <- Union 6 (SIMPLE_EDGE) @@ -249,282 +247,271 @@ Stage-0 limit:100 Stage-1 Reducer 8 vectorized - File Output Operator [FS_372] - Limit [LIM_371] (rows=100 width=163) + File Output Operator [FS_367] + Limit [LIM_366] (rows=23 width=439) Number of rows:100 - Select Operator [SEL_370] (rows=956329968 width=163) + Select Operator [SEL_365] (rows=23 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_369] - Select Operator [SEL_368] (rows=956329968 width=163) + SHUFFLE [RS_364] + Select Operator [SEL_363] (rows=23 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_367] (rows=956329968 width=163) + Group By Operator [GBY_362] (rows=23 width=447) Output:["_col0","_col1","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 6 [SIMPLE_EDGE] <-Reducer 16 [CONTAINS] Reduce Output Operator [RS_322] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_321] (rows=1912659936 width=163) + Group By Operator [GBY_321] (rows=52 width=447) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_320] (rows=637553312 width=163) + Top N Key Operator [TNK_320] (rows=35 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_318] (rows=158394413 width=360) + Select Operator [SEL_318] (rows=2 width=439) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_317] (rows=158394413 width=360) + Merge Join Operator [MERGEJOIN_317] (rows=2 width=452) Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_379] - Group By Operator [GBY_378] (rows=158394413 width=135) + PARTITION_ONLY_SHUFFLE [RS_374] + Group By Operator [GBY_373] (rows=2 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col0 - Group By Operator [GBY_54] (rows=316788826 width=135) + Group By Operator [GBY_54] (rows=56 width=227) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col1 - Merge Join Operator [MERGEJOIN_302] (rows=316788826 width=135) - Conds:RS_377._col0=RS_334._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_302] (rows=31836679 width=222) + Conds:RS_372._col0=RS_334._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_334] PartitionCols:_col0 - Select Operator [SEL_330] (rows=8116 width=1119) + Select Operator [SEL_330] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_329] (rows=8116 width=1119) + Filter Operator [FIL_329] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Map 31 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_377] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_372] PartitionCols:_col0 - Select Operator [SEL_376] (rows=287989836 width=135) + Select Operator [SEL_371] (rows=286549727 width=231) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_375] (rows=287989836 width=135) + Filter Operator [FIL_370] (rows=286549727 width=231) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_51_date_dim_d_date_sk_min) AND DynamicValue(RS_51_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_51_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_44] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_call_center_sk","cs_ext_sales_price","cs_net_profit"] + TableScan [TS_44] (rows=287989836 width=231) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_call_center_sk","cs_ext_sales_price","cs_net_profit"] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_374] - Group By Operator [GBY_373] (rows=1 width=12) + BROADCAST [RS_369] + Group By Operator [GBY_368] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_344] Group By Operator [GBY_341] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_335] (rows=8116 width=1119) + Select Operator [SEL_335] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_330] <-Reducer 19 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_384] - Group By Operator [GBY_383] (rows=1 width=224) + PARTITION_ONLY_SHUFFLE [RS_379] + Group By Operator [GBY_378] (rows=1 width=224) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_69] Group By Operator [GBY_68] (rows=1 width=224) Output:["_col0","_col1"],aggregations:["sum(_col1)","sum(_col2)"] - Merge Join Operator [MERGEJOIN_303] (rows=31678769 width=106) - Conds:RS_382._col0=RS_336._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_303] (rows=3199657 width=183) + Conds:RS_377._col0=RS_336._col0(Inner),Output:["_col1","_col2"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_336] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_330] - <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_382] + <-Map 31 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_377] PartitionCols:_col0 - Select Operator [SEL_381] (rows=28798881 width=106) + Select Operator [SEL_376] (rows=28798881 width=223) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_380] (rows=28798881 width=106) + Filter Operator [FIL_375] (rows=28798881 width=223) predicate:cr_returned_date_sk is not null - TableScan [TS_58] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_return_amount","cr_net_loss"] + TableScan [TS_58] (rows=28798881 width=223) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_returned_date_sk","cr_return_amount","cr_net_loss"] <-Reducer 23 [CONTAINS] Reduce Output Operator [RS_328] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_327] (rows=1912659936 width=163) + Group By Operator [GBY_327] (rows=52 width=447) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_326] (rows=637553312 width=163) + Top N Key Operator [TNK_326] (rows=35 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_324] (rows=95833780 width=135) + Select Operator [SEL_324] (rows=23 width=435) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_323] (rows=95833780 width=135) - Conds:RS_400._col0=RS_405._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] + Merge Join Operator [MERGEJOIN_323] (rows=23 width=452) + Conds:RS_390._col0=RS_395._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] <-Reducer 22 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_400] + FORWARD [RS_390] PartitionCols:_col0 - Group By Operator [GBY_399] (rows=87121617 width=135) + Group By Operator [GBY_389] (rows=23 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_94] PartitionCols:_col0 - Group By Operator [GBY_93] (rows=174243235 width=135) + Group By Operator [GBY_93] (rows=345 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 - Merge Join Operator [MERGEJOIN_305] (rows=174243235 width=135) - Conds:RS_89._col1=RS_389._col0(Inner),Output:["_col2","_col3","_col6"] - <-Map 34 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_389] + Merge Join Operator [MERGEJOIN_305] (rows=15991254 width=227) + Conds:RS_89._col1=RS_387._col0(Inner),Output:["_col2","_col3","_col6"] + <-Map 33 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_387] PartitionCols:_col0 - Select Operator [SEL_388] (rows=4602 width=585) + Select Operator [SEL_386] (rows=4602 width=4) Output:["_col0"] - Filter Operator [FIL_387] (rows=4602 width=585) + Filter Operator [FIL_385] (rows=4602 width=4) predicate:wp_web_page_sk is not null - TableScan [TS_83] (rows=4602 width=585) - default@web_page,web_page,Tbl:COMPLETE,Col:NONE,Output:["wp_web_page_sk"] + TableScan [TS_83] (rows=4602 width=4) + default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk"] <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_89] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=158402938 width=135) - Conds:RS_398._col0=RS_337._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_304] (rows=15991254 width=227) + Conds:RS_384._col0=RS_337._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_337] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_330] - <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_398] + <-Map 32 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_384] PartitionCols:_col0 - Select Operator [SEL_397] (rows=144002668 width=135) + Select Operator [SEL_383] (rows=143931136 width=231) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_396] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_87_date_dim_d_date_sk_min) AND DynamicValue(RS_87_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_87_date_dim_d_date_sk_bloom_filter))) and (ws_web_page_sk BETWEEN DynamicValue(RS_90_web_page_wp_web_page_sk_min) AND DynamicValue(RS_90_web_page_wp_web_page_sk_max) and in_bloom_filter(ws_web_page_sk, DynamicValue(RS_90_web_page_wp_web_page_sk_bloom_filter))) and ws_sold_date_sk is not null and ws_web_page_sk is not null) - TableScan [TS_77] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_web_page_sk","ws_ext_sales_price","ws_net_profit"] + Filter Operator [FIL_382] (rows=143931136 width=231) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_87_date_dim_d_date_sk_min) AND DynamicValue(RS_87_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_87_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null and ws_web_page_sk is not null) + TableScan [TS_77] (rows=144002668 width=231) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_web_page_sk","ws_ext_sales_price","ws_net_profit"] <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_386] - Group By Operator [GBY_385] (rows=1 width=12) + BROADCAST [RS_381] + Group By Operator [GBY_380] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_345] Group By Operator [GBY_342] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_338] (rows=8116 width=1119) + Select Operator [SEL_338] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_330] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_395] - Group By Operator [GBY_394] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_393] - Group By Operator [GBY_392] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_390] (rows=4602 width=585) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_388] <-Reducer 27 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_405] + FORWARD [RS_395] PartitionCols:_col0 - Group By Operator [GBY_404] (rows=8711072 width=92) + Group By Operator [GBY_394] (rows=23 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_114] PartitionCols:_col0 - Group By Operator [GBY_113] (rows=17422145 width=92) + Group By Operator [GBY_113] (rows=23 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 - Merge Join Operator [MERGEJOIN_307] (rows=17422145 width=92) - Conds:RS_109._col1=RS_391._col0(Inner),Output:["_col2","_col3","_col6"] - <-Map 34 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_391] + Merge Join Operator [MERGEJOIN_307] (rows=1458758 width=137) + Conds:RS_109._col1=RS_388._col0(Inner),Output:["_col2","_col3","_col6"] + <-Map 33 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_388] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_388] + Please refer to the previous Select Operator [SEL_386] <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_306] (rows=15838314 width=92) - Conds:RS_403._col0=RS_339._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_306] (rows=1458758 width=135) + Conds:RS_393._col0=RS_339._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_339] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_330] - <-Map 36 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_403] + <-Map 34 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_393] PartitionCols:_col0 - Select Operator [SEL_402] (rows=14398467 width=92) + Select Operator [SEL_392] (rows=13129719 width=221) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_401] (rows=14398467 width=92) + Filter Operator [FIL_391] (rows=13129719 width=221) predicate:(wr_returned_date_sk is not null and wr_web_page_sk is not null) - TableScan [TS_97] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_web_page_sk","wr_return_amt","wr_net_loss"] + TableScan [TS_97] (rows=14398467 width=221) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_returned_date_sk","wr_web_page_sk","wr_return_amt","wr_net_loss"] <-Reducer 5 [CONTAINS] Reduce Output Operator [RS_316] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_315] (rows=1912659936 width=163) + Group By Operator [GBY_315] (rows=52 width=447) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_314] (rows=637553312 width=163) + Top N Key Operator [TNK_314] (rows=35 width=435) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_312] (rows=383325119 width=88) + Select Operator [SEL_312] (rows=10 width=437) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_311] (rows=383325119 width=88) - Conds:RS_361._col0=RS_366._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] + Merge Join Operator [MERGEJOIN_311] (rows=10 width=452) + Conds:RS_356._col0=RS_361._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"] <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_366] + FORWARD [RS_361] PartitionCols:_col0 - Group By Operator [GBY_365] (rows=34842647 width=77) + Group By Operator [GBY_360] (rows=10 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 - Group By Operator [GBY_36] (rows=69685294 width=77) + Group By Operator [GBY_36] (rows=40 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 - Merge Join Operator [MERGEJOIN_301] (rows=69685294 width=77) - Conds:RS_32._col1=RS_352._col0(Inner),Output:["_col2","_col3","_col6"] + Merge Join Operator [MERGEJOIN_301] (rows=5959021 width=157) + Conds:RS_32._col1=RS_354._col0(Inner),Output:["_col2","_col3","_col6"] <-Map 28 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_352] + SHUFFLE [RS_354] PartitionCols:_col0 - Select Operator [SEL_349] (rows=1704 width=1910) + Select Operator [SEL_352] (rows=1704 width=4) Output:["_col0"] - Filter Operator [FIL_348] (rows=1704 width=1910) + Filter Operator [FIL_351] (rows=1704 width=4) predicate:s_store_sk is not null - TableScan [TS_6] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"] + TableScan [TS_6] (rows=1704 width=4) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_300] (rows=63350266 width=77) - Conds:RS_364._col0=RS_333._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_300] (rows=5959021 width=156) + Conds:RS_359._col0=RS_333._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_333] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_330] - <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_364] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_359] PartitionCols:_col0 - Select Operator [SEL_363] (rows=57591150 width=77) + Select Operator [SEL_358] (rows=53634860 width=223) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_362] (rows=57591150 width=77) + Filter Operator [FIL_357] (rows=53634860 width=223) predicate:(sr_returned_date_sk is not null and sr_store_sk is not null) - TableScan [TS_20] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_store_sk","sr_return_amt","sr_net_loss"] + TableScan [TS_20] (rows=57591150 width=223) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_store_sk","sr_return_amt","sr_net_loss"] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_361] + FORWARD [RS_356] PartitionCols:_col0 - Group By Operator [GBY_360] (rows=348477374 width=88) + Group By Operator [GBY_355] (rows=10 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=320 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6 - Merge Join Operator [MERGEJOIN_299] (rows=696954748 width=88) - Conds:RS_12._col1=RS_350._col0(Inner),Output:["_col2","_col3","_col6"] + Merge Join Operator [MERGEJOIN_299] (rows=58365993 width=137) + Conds:RS_12._col1=RS_353._col0(Inner),Output:["_col2","_col3","_col6"] <-Map 28 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_350] + SHUFFLE [RS_353] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_349] + Please refer to the previous Select Operator [SEL_352] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_298] (rows=633595212 width=88) - Conds:RS_359._col0=RS_331._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_298] (rows=58365993 width=135) + Conds:RS_350._col0=RS_331._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_331] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_330] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_359] + SHUFFLE [RS_350] PartitionCols:_col0 - Select Operator [SEL_358] (rows=575995635 width=88) + Select Operator [SEL_349] (rows=525329897 width=221) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_357] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_13_store_s_store_sk_min) AND DynamicValue(RS_13_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_13_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_ext_sales_price","ss_net_profit"] + Filter Operator [FIL_348] (rows=525329897 width=221) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=221) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_ext_sales_price","ss_net_profit"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_347] Group By Operator [GBY_346] (rows=1 width=12) @@ -533,18 +520,7 @@ Stage-0 SHUFFLE [RS_343] Group By Operator [GBY_340] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_332] (rows=8116 width=1119) + Select Operator [SEL_332] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_330] - <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_356] - Group By Operator [GBY_355] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_354] - Group By Operator [GBY_353] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_351] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_349] diff --git a/ql/src/test/results/clientpositive/perf/tez/query78.q.out b/ql/src/test/results/clientpositive/perf/tez/query78.q.out index b1102603c7..7ffac9f99d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query78.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query78.q.out @@ -115,146 +115,95 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 14 <- Reducer 7 (BROADCAST_EDGE) Map 17 <- Reducer 10 (BROADCAST_EDGE) -Map 20 <- Reducer 13 (BROADCAST_EDGE) +Map 20 <- Reducer 13 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 23 <- Reducer 16 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) Reducer 10 <- Map 1 (CUSTOM_SIMPLE_EDGE) Reducer 11 <- Map 1 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) Reducer 12 <- Reducer 11 (SIMPLE_EDGE) Reducer 13 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 14 <- Map 1 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE) +Reducer 16 <- Map 1 (CUSTOM_SIMPLE_EDGE) Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) Reducer 21 <- Map 20 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) +Reducer 24 <- Map 23 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 3 (ONE_TO_ONE_EDGE), Reducer 9 (ONE_TO_ONE_EDGE) -Reducer 5 <- Reducer 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Reducer 12 (ONE_TO_ONE_EDGE), Reducer 3 (ONE_TO_ONE_EDGE) +Reducer 5 <- Reducer 15 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Map 1 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 7 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_238] - Limit [LIM_237] (rows=100 width=88) + File Output Operator [FS_250] + Limit [LIM_249] (rows=12 width=484) Number of rows:100 - Select Operator [SEL_236] (rows=23425424 width=88) + Select Operator [SEL_248] (rows=12 width=484) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_73] - Select Operator [SEL_72] (rows=23425424 width=88) + Select Operator [SEL_72] (rows=12 width=720) Output:["_col0","_col1","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] - Filter Operator [FIL_71] (rows=23425424 width=88) + Filter Operator [FIL_71] (rows=12 width=704) predicate:(COALESCE(_col11,0) > 0) - Merge Join Operator [MERGEJOIN_191] (rows=70276272 width=88) - Conds:RS_68._col1=RS_235._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col11","_col12","_col13"] - <-Reducer 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_235] - PartitionCols:_col0 - Select Operator [SEL_234] (rows=43558464 width=135) - Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_233] (rows=43558464 width=135) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1 - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_65] - PartitionCols:_col0, _col1 - Group By Operator [GBY_64] (rows=87116928 width=135) - Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col3, _col4 - Merge Join Operator [MERGEJOIN_189] (rows=87116928 width=135) - Conds:RS_198._col0=RS_61._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_198] - PartitionCols:_col0 - Select Operator [SEL_193] (rows=36524 width=1119) - Output:["_col0"] - Filter Operator [FIL_192] (rows=36524 width=1119) - predicate:((d_year = 2000) and d_date_sk is not null) - TableScan [TS_0] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_61] - PartitionCols:_col0 - Select Operator [SEL_59] (rows=79197206 width=135) - Output:["_col0","_col1","_col2","_col4","_col5","_col6"] - Filter Operator [FIL_58] (rows=79197206 width=135) - predicate:_col8 is null - Merge Join Operator [MERGEJOIN_188] (rows=158394413 width=135) - Conds:RS_230._col2, _col3=RS_232._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_230] - PartitionCols:_col2, _col3 - Select Operator [SEL_229] (rows=143994918 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_228] (rows=143994918 width=135) - predicate:((cs_item_sk = cs_item_sk) and (cs_sold_date_sk BETWEEN DynamicValue(RS_60_date_dim_d_date_sk_min) AND DynamicValue(RS_60_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_60_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_50] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_order_number","cs_quantity","cs_wholesale_cost","cs_sales_price"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_227] - Group By Operator [GBY_226] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_205] - Group By Operator [GBY_202] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_199] (rows=36524 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_193] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_232] - PartitionCols:_col0, _col1 - Select Operator [SEL_231] (rows=28798881 width=106) - Output:["_col0","_col1"] - TableScan [TS_53] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number"] + Merge Join Operator [MERGEJOIN_191] (rows=36 width=704) + Conds:RS_68._col1=RS_247._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col11","_col12","_col13"] <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_68] + PARTITION_ONLY_SHUFFLE [RS_68] PartitionCols:_col1 - Filter Operator [FIL_45] (rows=63887519 width=88) + Filter Operator [FIL_45] (rows=1 width=472) predicate:(COALESCE(_col7,0) > 0) - Merge Join Operator [MERGEJOIN_190] (rows=191662559 width=88) - Conds:RS_215._col1, _col0=RS_225._col1, _col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9"] + Merge Join Operator [MERGEJOIN_190] (rows=1 width=472) + Conds:RS_215._col1, _col0=RS_235._col1, _col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9"] <-Reducer 3 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_215] + PARTITION_ONLY_SHUFFLE [RS_215] PartitionCols:_col1, _col0 - Select Operator [SEL_214] (rows=174238687 width=88) + Select Operator [SEL_214] (rows=1 width=240) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_213] (rows=174238687 width=88) + Group By Operator [GBY_213] (rows=1 width=240) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1 - Group By Operator [GBY_17] (rows=348477374 width=88) + Group By Operator [GBY_17] (rows=1 width=240) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col4, _col3 - Merge Join Operator [MERGEJOIN_185] (rows=348477374 width=88) + Merge Join Operator [MERGEJOIN_185] (rows=1 width=236) Conds:RS_194._col0=RS_14._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_193] - <-Reducer 15 [SIMPLE_EDGE] + Select Operator [SEL_193] (rows=652 width=8) + Output:["_col0"] + Filter Operator [FIL_192] (rows=652 width=8) + predicate:((d_year = 2000) and d_date_sk is not null) + TableScan [TS_0] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_14] PartitionCols:_col0 - Select Operator [SEL_12] (rows=316797606 width=88) + Select Operator [SEL_12] (rows=1 width=244) Output:["_col0","_col1","_col2","_col4","_col5","_col6"] - Filter Operator [FIL_11] (rows=316797606 width=88) + Filter Operator [FIL_11] (rows=1 width=244) predicate:_col8 is null - Merge Join Operator [MERGEJOIN_184] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_184] (rows=563130026 width=233) Conds:RS_210._col1, _col3=RS_212._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"] - <-Map 14 [SIMPLE_EDGE] vectorized + <-Map 17 [SIMPLE_EDGE] vectorized SHUFFLE [RS_210] PartitionCols:_col1, _col3 - Select Operator [SEL_209] (rows=575995635 width=88) + Select Operator [SEL_209] (rows=550076554 width=233) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_208] (rows=575995635 width=88) + Filter Operator [FIL_208] (rows=550076554 width=233) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_ticket_number","ss_quantity","ss_wholesale_cost","ss_sales_price"] - <-Reducer 7 [BROADCAST_EDGE] vectorized + TableScan [TS_3] (rows=575995635 width=233) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_ticket_number","ss_quantity","ss_wholesale_cost","ss_sales_price"] + <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_207] Group By Operator [GBY_206] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] @@ -262,68 +211,155 @@ Stage-0 SHUFFLE [RS_203] Group By Operator [GBY_200] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_195] (rows=36524 width=1119) + Select Operator [SEL_195] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_193] - <-Map 16 [SIMPLE_EDGE] vectorized + <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_212] PartitionCols:_col0, _col1 - Select Operator [SEL_211] (rows=57591150 width=77) + Select Operator [SEL_211] (rows=57591150 width=8) Output:["_col0","_col1"] - TableScan [TS_6] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"] - <-Reducer 9 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_225] + TableScan [TS_6] (rows=57591150 width=8) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] + <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_235] PartitionCols:_col1, _col0 - Select Operator [SEL_224] (rows=43560808 width=135) + Select Operator [SEL_234] (rows=1008883 width=239) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_223] (rows=43560808 width=135) + Group By Operator [GBY_233] (rows=1008883 width=239) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1 - <-Reducer 8 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col0, _col1 - Group By Operator [GBY_38] (rows=87121617 width=135) + Group By Operator [GBY_38] (rows=1008883 width=239) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col4, _col3 - Merge Join Operator [MERGEJOIN_187] (rows=87121617 width=135) + Merge Join Operator [MERGEJOIN_187] (rows=1008883 width=235) Conds:RS_196._col0=RS_35._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_196] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_193] - <-Reducer 18 [SIMPLE_EDGE] + <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0 - Select Operator [SEL_33] (rows=79201469 width=135) + Select Operator [SEL_33] (rows=2825529 width=243) Output:["_col0","_col1","_col2","_col4","_col5","_col6"] - Filter Operator [FIL_32] (rows=79201469 width=135) + Filter Operator [FIL_32] (rows=2825529 width=243) predicate:_col8 is null - Merge Join Operator [MERGEJOIN_186] (rows=158402938 width=135) - Conds:RS_220._col1, _col3=RS_222._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_220] + Merge Join Operator [MERGEJOIN_186] (rows=143966864 width=243) + Conds:RS_230._col1, _col3=RS_232._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_230] PartitionCols:_col1, _col3 - Select Operator [SEL_219] (rows=144002668 width=135) + Select Operator [SEL_229] (rows=143966864 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_218] (rows=144002668 width=135) - predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_34_date_dim_d_date_sk_min) AND DynamicValue(RS_34_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_34_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) - TableScan [TS_24] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_order_number","ws_quantity","ws_wholesale_cost","ws_sales_price"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_217] - Group By Operator [GBY_216] (rows=1 width=12) + Filter Operator [FIL_228] (rows=143966864 width=243) + predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_42_store_sales_ss_customer_sk_min) AND DynamicValue(RS_42_store_sales_ss_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_42_store_sales_ss_customer_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_42_store_sales_ss_item_sk_min) AND DynamicValue(RS_42_store_sales_ss_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_42_store_sales_ss_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_34_date_dim_d_date_sk_min) AND DynamicValue(RS_34_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_34_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null) + TableScan [TS_24] (rows=144002668 width=243) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_order_number","ws_quantity","ws_wholesale_cost","ws_sales_price"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_223] + Group By Operator [GBY_222] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_204] Group By Operator [GBY_201] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_197] (rows=36524 width=1119) + Select Operator [SEL_197] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_193] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_222] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_225] + Group By Operator [GBY_224] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_220] + Group By Operator [GBY_218] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_216] (rows=1 width=8) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_214] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_227] + Group By Operator [GBY_226] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_221] + Group By Operator [GBY_219] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_217] (rows=1 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_214] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_232] PartitionCols:_col0, _col1 - Select Operator [SEL_221] (rows=14398467 width=92) + Select Operator [SEL_231] (rows=14398467 width=8) Output:["_col0","_col1"] - TableScan [TS_27] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number"] + TableScan [TS_27] (rows=14398467 width=8) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_order_number"] + <-Reducer 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_247] + PartitionCols:_col0 + Select Operator [SEL_246] (rows=18503137 width=235) + Output:["_col0","_col1","_col2","_col3"] + Group By Operator [GBY_245] (rows=18503137 width=239) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1 + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_65] + PartitionCols:_col0, _col1 + Group By Operator [GBY_64] (rows=18503137 width=239) + Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col3, _col4 + Merge Join Operator [MERGEJOIN_189] (rows=18503137 width=232) + Conds:RS_198._col0=RS_61._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_198] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_193] + <-Reducer 24 [SIMPLE_EDGE] + SHUFFLE [RS_61] + PartitionCols:_col0 + Select Operator [SEL_59] (rows=52189774 width=241) + Output:["_col0","_col1","_col2","_col4","_col5","_col6"] + Filter Operator [FIL_58] (rows=52189774 width=241) + predicate:_col8 is null + Merge Join Operator [MERGEJOIN_188] (rows=143274863 width=241) + Conds:RS_242._col2, _col3=RS_244._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_242] + PartitionCols:_col2, _col3 + Select Operator [SEL_241] (rows=143274863 width=242) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Filter Operator [FIL_240] (rows=143274863 width=242) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_68_store_sales_ss_customer_sk_min) AND DynamicValue(RS_68_store_sales_ss_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_68_store_sales_ss_customer_sk_bloom_filter))) and (cs_item_sk = cs_item_sk) and (cs_sold_date_sk BETWEEN DynamicValue(RS_60_date_dim_d_date_sk_min) AND DynamicValue(RS_60_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_60_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) + TableScan [TS_50] (rows=287989836 width=242) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_order_number","cs_quantity","cs_wholesale_cost","cs_sales_price"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_237] + Group By Operator [GBY_236] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_205] + Group By Operator [GBY_202] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_199] (rows=652 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_193] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_239] + Group By Operator [GBY_238] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_169] + Group By Operator [GBY_168] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_167] (rows=1 width=8) + Output:["_col0"] + Please refer to the previous Filter Operator [FIL_45] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_244] + PartitionCols:_col0, _col1 + Select Operator [SEL_243] (rows=28798881 width=8) + Output:["_col0","_col1"] + TableScan [TS_53] (rows=28798881 width=8) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query79.q.out b/ql/src/test/results/clientpositive/perf/tez/query79.q.out index 7b9d48f123..42bfbbef20 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query79.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query79.q.out @@ -45,145 +45,133 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 5 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 4 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Map 4 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Map 10 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) -Reducer 7 <- Map 12 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Map 14 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 6 <- Map 11 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 13 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_141] - Limit [LIM_140] (rows=100 width=88) + File Output Operator [FS_136] + Limit [LIM_135] (rows=100 width=776) Number of rows:100 - Select Operator [SEL_139] (rows=421657640 width=88) + Select Operator [SEL_134] (rows=14510208 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_33] - Select Operator [SEL_32] (rows=421657640 width=88) + Select Operator [SEL_32] (rows=14510208 width=776) Output:["_col0","_col1","_col3","_col4","_col5","_col6"] - Merge Join Operator [MERGEJOIN_100] (rows=421657640 width=88) - Conds:RS_103._col0=RS_138._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_100] (rows=14510208 width=501) + Conds:RS_103._col0=RS_133._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_103] + SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_102] (rows=80000000 width=860) + Select Operator [SEL_102] (rows=80000000 width=184) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_101] (rows=80000000 width=860) + Filter Operator [FIL_101] (rows=80000000 width=184) predicate:c_customer_sk is not null - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name"] - <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_138] + TableScan [TS_0] (rows=80000000 width=184) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name"] + <-Reducer 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_133] PartitionCols:_col1 - Select Operator [SEL_137] (rows=383325119 width=88) + Select Operator [SEL_132] (rows=14510208 width=321) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_136] (rows=383325119 width=88) + Group By Operator [GBY_131] (rows=14510208 width=321) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 8 [SIMPLE_EDGE] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_25] (rows=766650239 width=88) + Group By Operator [GBY_25] (rows=14510208 width=321) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col3, _col5, _col13 - Merge Join Operator [MERGEJOIN_99] (rows=766650239 width=88) - Conds:RS_21._col2=RS_125._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col13"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] + Merge Join Operator [MERGEJOIN_99] (rows=14510208 width=97) + Conds:RS_21._col2=RS_122._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col13"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] PartitionCols:_col0 - Select Operator [SEL_124] (rows=6000 width=107) + Select Operator [SEL_121] (rows=3055 width=12) Output:["_col0"] - Filter Operator [FIL_123] (rows=6000 width=107) + Filter Operator [FIL_120] (rows=3055 width=12) predicate:(((hd_dep_count = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) - TableScan [TS_12] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] - <-Reducer 7 [SIMPLE_EDGE] + TableScan [TS_12] (rows=7200 width=12) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_98] (rows=696954748 width=88) - Conds:RS_18._col4=RS_117._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col13"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] + Merge Join Operator [MERGEJOIN_98] (rows=34197543 width=184) + Conds:RS_18._col4=RS_114._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col13"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_116] (rows=189 width=1910) + Select Operator [SEL_113] (rows=568 width=100) Output:["_col0","_col2"] - Filter Operator [FIL_115] (rows=189 width=1910) + Filter Operator [FIL_112] (rows=568 width=100) predicate:(s_number_employees BETWEEN 200 AND 295 and s_store_sk is not null) - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_number_employees","s_city"] - <-Reducer 6 [SIMPLE_EDGE] + TableScan [TS_9] (rows=1704 width=100) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_number_employees","s_city"] + <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_97] (rows=633595212 width=88) - Conds:RS_135._col0=RS_109._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_109] + Merge Join Operator [MERGEJOIN_97] (rows=102592623 width=193) + Conds:RS_130._col0=RS_106._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_108] (rows=36524 width=1119) + Select Operator [SEL_105] (rows=391 width=12) Output:["_col0"] - Filter Operator [FIL_107] (rows=36524 width=1119) + Filter Operator [FIL_104] (rows=391 width=12) predicate:((d_dow = 1) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dow"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] + TableScan [TS_6] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dow"] + <-Map 4 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_130] PartitionCols:_col0 - Select Operator [SEL_134] (rows=575995635 width=88) + Select Operator [SEL_129] (rows=479121995 width=237) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_133] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_29_customer_c_customer_sk_min) AND DynamicValue(RS_29_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_29_customer_c_customer_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_22_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_22_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_22_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_114] - Group By Operator [GBY_113] (rows=1 width=12) + Filter Operator [FIL_128] (rows=479121995 width=237) + predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_22_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_22_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_22_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_3] (rows=575995635 width=237) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_111] + Group By Operator [GBY_110] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] - Group By Operator [GBY_111] (rows=1 width=12) + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_109] + Group By Operator [GBY_108] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_110] (rows=36524 width=1119) + Select Operator [SEL_107] (rows=391 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_108] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_122] - Group By Operator [GBY_121] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_105] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_119] + Group By Operator [GBY_118] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] - Group By Operator [GBY_119] (rows=1 width=12) + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_117] + Group By Operator [GBY_116] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_118] (rows=189 width=1910) + Select Operator [SEL_115] (rows=568 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_116] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_130] - Group By Operator [GBY_129] (rows=1 width=12) + Please refer to the previous Select Operator [SEL_113] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_127] + Group By Operator [GBY_126] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_128] - Group By Operator [GBY_127] (rows=1 width=12) + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] + Group By Operator [GBY_124] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_126] (rows=6000 width=107) + Select Operator [SEL_123] (rows=3055 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_124] - <-Reducer 4 [BROADCAST_EDGE] vectorized - BROADCAST [RS_132] - Group By Operator [GBY_131] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_104] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] + Please refer to the previous Select Operator [SEL_121] diff --git a/ql/src/test/results/clientpositive/perf/tez/query8.q.out b/ql/src/test/results/clientpositive/perf/tez/query8.q.out index ee20e61ff4..c295c2bc25 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query8.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query8.q.out @@ -235,131 +235,131 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_151] - Limit [LIM_150] (rows=100 width=88) + Limit [LIM_150] (rows=1 width=200) Number of rows:100 - Select Operator [SEL_149] (rows=348477374 width=88) + Select Operator [SEL_149] (rows=1 width=200) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_148] - Group By Operator [GBY_147] (rows=348477374 width=88) + Group By Operator [GBY_147] (rows=1 width=200) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col0 - Group By Operator [GBY_56] (rows=696954748 width=88) + Group By Operator [GBY_56] (rows=1 width=200) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col8 - Top N Key Operator [TNK_84] (rows=696954748 width=88) + Top N Key Operator [TNK_84] (rows=1 width=200) keys:_col8,sort order:+,top n:100 - Merge Join Operator [MERGEJOIN_118] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_118] (rows=1 width=200) Conds:RS_52._col1=RS_53._col1(Inner),Output:["_col2","_col8"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_117] (rows=1874 width=1911) + Merge Join Operator [MERGEJOIN_117] (rows=1 width=92) Conds:RS_138.substr(_col0, 1, 2)=RS_141.substr(_col2, 1, 2)(Inner),Output:["_col1","_col2"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_141] PartitionCols:substr(_col2, 1, 2) - Select Operator [SEL_140] (rows=1704 width=1910) + Select Operator [SEL_140] (rows=1704 width=181) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_139] (rows=1704 width=1910) + Filter Operator [FIL_139] (rows=1704 width=181) predicate:(s_store_sk is not null and substr(s_zip, 1, 2) is not null) - TableScan [TS_42] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_zip"] + TableScan [TS_42] (rows=1704 width=181) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_zip"] <-Reducer 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_138] PartitionCols:substr(_col0, 1, 2) - Select Operator [SEL_137] (rows=1 width=1014) + Select Operator [SEL_137] (rows=1 width=184) Output:["_col0"] - Filter Operator [FIL_136] (rows=1 width=1014) + Filter Operator [FIL_136] (rows=1 width=192) predicate:(_col1 = 2L) - Group By Operator [GBY_135] (rows=6833333 width=1014) + Group By Operator [GBY_135] (rows=3098 width=192) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Union 10 [SIMPLE_EDGE] <-Reducer 17 [CONTAINS] vectorized Reduce Output Operator [RS_172] PartitionCols:_col0 - Group By Operator [GBY_171] (rows=13666666 width=1014) + Group By Operator [GBY_171] (rows=3098 width=192) Output:["_col0","_col1"],aggregations:["count(_col1)"],keys:_col0 - Group By Operator [GBY_170] (rows=3666666 width=1014) + Group By Operator [GBY_170] (rows=1126 width=192) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_169] PartitionCols:_col0 - Group By Operator [GBY_168] (rows=7333333 width=1014) + Group By Operator [GBY_168] (rows=1126 width=192) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Select Operator [SEL_167] (rows=7333333 width=1014) + Select Operator [SEL_167] (rows=2253 width=97) Output:["_col0"] - Filter Operator [FIL_166] (rows=7333333 width=1014) + Filter Operator [FIL_166] (rows=2253 width=97) predicate:(_col1 > 10L) - Group By Operator [GBY_165] (rows=22000000 width=1014) + Group By Operator [GBY_165] (rows=6761 width=97) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Group By Operator [GBY_24] (rows=44000000 width=1014) + Group By Operator [GBY_24] (rows=67610 width=97) Output:["_col0","_col1"],aggregations:["count()"],keys:_col1 - Merge Join Operator [MERGEJOIN_116] (rows=44000000 width=1014) + Merge Join Operator [MERGEJOIN_116] (rows=26666667 width=89) Conds:RS_161._col0=RS_164._col0(Inner),Output:["_col1"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_161] PartitionCols:_col0 - Select Operator [SEL_160] (rows=40000000 width=1014) + Select Operator [SEL_160] (rows=40000000 width=93) Output:["_col0","_col1"] - Filter Operator [FIL_159] (rows=40000000 width=1014) + Filter Operator [FIL_159] (rows=40000000 width=93) predicate:(ca_address_sk is not null and substr(substr(ca_zip, 1, 5), 1, 2) is not null) - TableScan [TS_14] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_zip"] + TableScan [TS_14] (rows=40000000 width=93) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_zip"] <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_164] PartitionCols:_col0 - Select Operator [SEL_163] (rows=40000000 width=860) + Select Operator [SEL_163] (rows=26666667 width=89) Output:["_col0"] - Filter Operator [FIL_162] (rows=40000000 width=860) + Filter Operator [FIL_162] (rows=26666667 width=89) predicate:((c_preferred_cust_flag = 'Y') and c_current_addr_sk is not null) - TableScan [TS_17] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_current_addr_sk","c_preferred_cust_flag"] + TableScan [TS_17] (rows=80000000 width=89) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_current_addr_sk","c_preferred_cust_flag"] <-Reducer 9 [CONTAINS] vectorized Reduce Output Operator [RS_158] PartitionCols:_col0 - Group By Operator [GBY_157] (rows=13666666 width=1014) + Group By Operator [GBY_157] (rows=3098 width=192) Output:["_col0","_col1"],aggregations:["count(_col1)"],keys:_col0 - Group By Operator [GBY_156] (rows=10000000 width=1014) + Group By Operator [GBY_156] (rows=5071 width=192) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_155] PartitionCols:_col0 - Group By Operator [GBY_154] (rows=20000000 width=1014) + Group By Operator [GBY_154] (rows=70994 width=192) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Select Operator [SEL_153] (rows=20000000 width=1014) + Select Operator [SEL_153] (rows=20000000 width=89) Output:["_col0"] - Filter Operator [FIL_152] (rows=20000000 width=1014) + Filter Operator [FIL_152] (rows=20000000 width=89) predicate:((substr(ca_zip, 1, 5)) IN ('89436', '30868', '65085', '22977', '83927', '77557', '58429', '40697', '80614', '10502', '32779', '91137', '61265', '98294', '17921', '18427', '21203', '59362', '87291', '84093', '21505', '17184', '10866', '67898', '25797', '28055', '18377', '80332', '74535', '21757', '29742', '90885', '29898', '17819', '40811', '25990', '47513', '89531', '91068', '10391', '18846', '99223', '82637', '41368', '83658', '86199', '81625', '26696', '89338', '88425', '32200', '81427', '19053', '77471', '36610', '99823', '43276', '41249', '48584', '83550', '82276', '18842', '78890', '14090', '38123', '40936', '34425', '19850', '43286', '80072', '79188', '54191', '11395', '50497', '84861', '90733', '21068', '57666', '37119', '25004', '57835', '70067', '62878', '95806', '19303', '18840', '19124', '29785', '16737', '16022', '49613', '89977', '68310', '60069', '98360', '48649', '39050', '41793', '25002', '27413', '39736', '47208', '16515', '94808', '57648', '15009', '80015', '42961', '63982', '21744', '71853', '81087', '67468', '34175', '64008', '20261', '11201', '51799', '48043', '45645', '61163', '48375', '36447', '57042', '21218', '41100', '89951', '22745', '35851', '83326', '61125', '78298', '80752', '49858', '52940', '96976', '63792', '11376', '53582', '18717', '90226', '50530', '94203', '99447', '27670', '96577', '57856', '56372', '16165', '23427', '54561', '28806', '44439', '22926', '30123', '61451', '92397', '56979', '92309', '70873', '13355', '21801', '46346', '37562', '56458', '28286', '47306', '99555', '69399', '26234', '47546', '49661', '88601', '35943', '39936', '25632', '24611', '44166', '56648', '30379', '59785', '11110', '14329', '93815', '52226', '71381', '13842', '25612', '63294', '14664', '21077', '82626', '18799', '60915', '81020', '56447', '76619', '11433', '13414', '42548', '92713', '70467', '30884', '47484', '16072', '38936', '13036', '88376', '45539', '35901', '19506', '65690', '73957', '71850', '49231', '14276', '20005', '18384', '76615', '11635', '38177', '55607', '41369', '95447', '58581', '58149', '91946', '33790', '76232', '75692', '95464', '22246', '51061', '56692', '53121', '77209', '15482', '10688', '14868', '45907', '73520', '72666', '25734', '17959', '24677', '66446', '94627', '53535', '15560', '41967', '69297', '11929', '59403', '33283', '52232', '57350', '43933', '40921', '36635', '10827', '71286', '19736', '80619', '25251', '95042', '15526', '36496', '55854', '49124', '81980', '35375', '49157', '63512', '28944', '14946', '36503', '54010', '18767', '23969', '43905', '66979', '33113', '21286', '58471', '59080', '13395', '79144', '70373', '67031', '38360', '26705', '50906', '52406', '26066', '73146', '15884', '31897', '30045', '61068', '45550', '92454', '13376', '14354', '19770', '22928', '97790', '50723', '46081', '30202', '14410', '20223', '88500', '67298', '13261', '14172', '81410', '93578', '83583', '46047', '94167', '82564', '21156', '15799', '86709', '37931', '74703', '83103', '23054', '70470', '72008', '49247', '91911', '69998', '20961', '70070', '63197', '54853', '88191', '91830', '49521', '19454', '81450', '89091', '62378', '25683', '61869', '51744', '36580', '85778', '36871', '48121', '28810', '83712', '45486', '67393', '26935', '42393', '20132', '55349', '86057', '21309', '80218', '10094', '11357', '48819', '39734', '40758', '30432', '21204', '29467', '30214', '61024', '55307', '74621', '11622', '68908', '33032', '52868', '99194', '99900', '84936', '69036', '99149', '45013', '32895', '59004', '32322', '14933', '32936', '33562', '72550', '27385', '58049', '58200', '16808', '21360', '32961', '18586', '79307', '15492') and substr(substr(ca_zip, 1, 5), 1, 2) is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_zip"] + TableScan [TS_6] (rows=40000000 width=89) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_zip"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_115] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_115] (rows=37399754 width=42) Conds:RS_146._col0=RS_129._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_129] PartitionCols:_col0 - Select Operator [SEL_128] (rows=18262 width=1119) + Select Operator [SEL_128] (rows=130 width=12) Output:["_col0"] - Filter Operator [FIL_127] (rows=18262 width=1119) + Filter Operator [FIL_127] (rows=130 width=12) predicate:((d_qoy = 1) and (d_year = 2002) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_qoy"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_146] PartitionCols:_col0 - Select Operator [SEL_145] (rows=575995635 width=88) + Select Operator [SEL_145] (rows=525329897 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_144] (rows=575995635 width=88) + Filter Operator [FIL_144] (rows=525329897 width=114) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_53_store_s_store_sk_min) AND DynamicValue(RS_53_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_53_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"] <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_143] Group By Operator [GBY_142] (rows=1 width=12) @@ -368,7 +368,7 @@ Stage-0 SHUFFLE [RS_92] Group By Operator [GBY_91] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_90] (rows=1874 width=1911) + Select Operator [SEL_90] (rows=1 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_117] <-Reducer 7 [BROADCAST_EDGE] vectorized @@ -379,7 +379,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_132] Group By Operator [GBY_131] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_130] (rows=18262 width=1119) + Select Operator [SEL_130] (rows=130 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_128] diff --git a/ql/src/test/results/clientpositive/perf/tez/query80.q.out b/ql/src/test/results/clientpositive/perf/tez/query80.q.out index e02f45f165..770800dea3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query80.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query80.q.out @@ -191,22 +191,22 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 13 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 31 (BROADCAST_EDGE), Reducer 35 (BROADCAST_EDGE) -Map 36 <- Reducer 19 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE), Reducer 40 (BROADCAST_EDGE) -Map 41 <- Reducer 25 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE), Reducer 33 (BROADCAST_EDGE), Reducer 45 (BROADCAST_EDGE) +Map 1 <- Reducer 13 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 31 (BROADCAST_EDGE) +Map 35 <- Reducer 19 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE), Reducer 32 (BROADCAST_EDGE) +Map 39 <- Reducer 25 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE), Reducer 33 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 12 (SIMPLE_EDGE), Reducer 37 (SIMPLE_EDGE) +Reducer 14 <- Map 12 (SIMPLE_EDGE), Reducer 36 (SIMPLE_EDGE) Reducer 15 <- Map 26 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) Reducer 16 <- Map 30 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 17 <- Map 39 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) +Reducer 17 <- Map 38 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) Reducer 18 <- Reducer 17 (SIMPLE_EDGE), Union 8 (CONTAINS) Reducer 19 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) -Reducer 20 <- Map 12 (SIMPLE_EDGE), Reducer 42 (SIMPLE_EDGE) +Reducer 20 <- Map 12 (SIMPLE_EDGE), Reducer 40 (SIMPLE_EDGE) Reducer 21 <- Map 26 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) Reducer 22 <- Map 30 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 23 <- Map 44 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 23 <- Map 42 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) Reducer 24 <- Reducer 23 (SIMPLE_EDGE), Union 8 (CONTAINS) Reducer 25 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 27 <- Map 26 (CUSTOM_SIMPLE_EDGE) @@ -216,12 +216,9 @@ Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 31 <- Map 30 (CUSTOM_SIMPLE_EDGE) Reducer 32 <- Map 30 (CUSTOM_SIMPLE_EDGE) Reducer 33 <- Map 30 (CUSTOM_SIMPLE_EDGE) -Reducer 35 <- Map 34 (CUSTOM_SIMPLE_EDGE) -Reducer 37 <- Map 36 (SIMPLE_EDGE), Map 38 (SIMPLE_EDGE) +Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 37 (SIMPLE_EDGE) Reducer 4 <- Map 26 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 40 <- Map 39 (CUSTOM_SIMPLE_EDGE) -Reducer 42 <- Map 41 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE) -Reducer 45 <- Map 44 (CUSTOM_SIMPLE_EDGE) +Reducer 40 <- Map 39 (SIMPLE_EDGE), Map 41 (SIMPLE_EDGE) Reducer 5 <- Map 30 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Map 34 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE), Union 8 (CONTAINS) @@ -232,189 +229,178 @@ Stage-0 limit:100 Stage-1 Reducer 10 vectorized - File Output Operator [FS_465] - Limit [LIM_464] (rows=100 width=108) + File Output Operator [FS_460] + Limit [LIM_459] (rows=100 width=619) Number of rows:100 - Select Operator [SEL_463] (rows=1217531358 width=108) + Select Operator [SEL_458] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_462] - Select Operator [SEL_461] (rows=1217531358 width=108) + SHUFFLE [RS_457] + Select Operator [SEL_456] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_460] (rows=1217531358 width=108) + Group By Operator [GBY_455] (rows=38846 width=627) Output:["_col0","_col1","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 8 [SIMPLE_EDGE] <-Reducer 18 [CONTAINS] vectorized - Reduce Output Operator [RS_490] + Reduce Output Operator [RS_480] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_489] (rows=2435062716 width=108) + Group By Operator [GBY_479] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_488] (rows=811687572 width=108) + Top N Key Operator [TNK_478] (rows=39721 width=618) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_487] (rows=231905279 width=135) + Select Operator [SEL_477] (rows=38846 width=619) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_486] (rows=231905279 width=135) + Group By Operator [GBY_476] (rows=38846 width=436) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_75] PartitionCols:_col0 - Group By Operator [GBY_74] (rows=463810558 width=135) + Group By Operator [GBY_74] (rows=271922 width=436) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)"],keys:_col0 - Select Operator [SEL_72] (rows=463810558 width=135) + Select Operator [SEL_72] (rows=5253195 width=293) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_369] (rows=463810558 width=135) - Conds:RS_69._col1=RS_474._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] - <-Map 39 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_474] + Merge Join Operator [MERGEJOIN_369] (rows=5253195 width=293) + Conds:RS_69._col1=RS_475._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_475] PartitionCols:_col0 - Select Operator [SEL_473] (rows=46000 width=460) + Select Operator [SEL_474] (rows=46000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_472] (rows=46000 width=460) + Filter Operator [FIL_473] (rows=46000 width=104) predicate:cp_catalog_page_sk is not null - TableScan [TS_54] (rows=46000 width=460) - default@catalog_page,catalog_page,Tbl:COMPLETE,Col:NONE,Output:["cp_catalog_page_sk","cp_catalog_page_id"] + TableScan [TS_54] (rows=46000 width=104) + default@catalog_page,catalog_page,Tbl:COMPLETE,Col:COMPLETE,Output:["cp_catalog_page_sk","cp_catalog_page_id"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_368] (rows=421645953 width=135) + Merge Join Operator [MERGEJOIN_368] (rows=5253195 width=196) Conds:RS_66._col3=RS_429._col0(Inner),Output:["_col1","_col5","_col6","_col9","_col10"] <-Map 30 [SIMPLE_EDGE] vectorized SHUFFLE [RS_429] PartitionCols:_col0 - Select Operator [SEL_426] (rows=1150 width=1179) + Select Operator [SEL_426] (rows=1150 width=89) Output:["_col0"] - Filter Operator [FIL_425] (rows=1150 width=1179) + Filter Operator [FIL_425] (rows=1150 width=89) predicate:((p_channel_tv = 'N') and p_promo_sk is not null) - TableScan [TS_12] (rows=2300 width=1179) - default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_tv"] + TableScan [TS_12] (rows=2300 width=89) + default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk","p_channel_tv"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_367] (rows=383314495 width=135) + Merge Join Operator [MERGEJOIN_367] (rows=10506389 width=215) Conds:RS_63._col2=RS_413._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col9","_col10"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_413] PartitionCols:_col0 - Select Operator [SEL_410] (rows=154000 width=1436) + Select Operator [SEL_410] (rows=154000 width=115) Output:["_col0"] - Filter Operator [FIL_409] (rows=154000 width=1436) + Filter Operator [FIL_409] (rows=154000 width=115) predicate:((i_current_price > 50) and i_item_sk is not null) - TableScan [TS_9] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price"] + TableScan [TS_9] (rows=462000 width=115) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price"] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_366] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_366] (rows=31519166 width=230) Conds:RS_60._col0=RS_397._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_397] PartitionCols:_col0 - Select Operator [SEL_394] (rows=8116 width=1119) + Select Operator [SEL_394] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_393] (rows=8116 width=1119) + Filter Operator [FIL_393] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Reducer 37 [SIMPLE_EDGE] + TableScan [TS_6] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Reducer 36 [SIMPLE_EDGE] SHUFFLE [RS_60] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_365] (rows=316788826 width=135) - Conds:RS_482._col2, _col4=RS_485._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"] - <-Map 36 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_482] + Merge Join Operator [MERGEJOIN_365] (rows=283691906 width=381) + Conds:RS_469._col2, _col4=RS_472._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"] + <-Map 35 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_469] PartitionCols:_col2, _col4 - Select Operator [SEL_481] (rows=287989836 width=135) + Select Operator [SEL_468] (rows=283691906 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_480] (rows=287989836 width=135) - predicate:((cs_catalog_page_sk BETWEEN DynamicValue(RS_70_catalog_page_cp_catalog_page_sk_min) AND DynamicValue(RS_70_catalog_page_cp_catalog_page_sk_max) and in_bloom_filter(cs_catalog_page_sk, DynamicValue(RS_70_catalog_page_cp_catalog_page_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_64_item_i_item_sk_min) AND DynamicValue(RS_64_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_64_item_i_item_sk_bloom_filter))) and (cs_promo_sk BETWEEN DynamicValue(RS_67_promotion_p_promo_sk_min) AND DynamicValue(RS_67_promotion_p_promo_sk_max) and in_bloom_filter(cs_promo_sk, DynamicValue(RS_67_promotion_p_promo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_61_date_dim_d_date_sk_min) AND DynamicValue(RS_61_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_61_date_dim_d_date_sk_bloom_filter))) and cs_catalog_page_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_39] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_catalog_page_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_ext_sales_price","cs_net_profit"] + Filter Operator [FIL_467] (rows=283691906 width=243) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_64_item_i_item_sk_min) AND DynamicValue(RS_64_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_64_item_i_item_sk_bloom_filter))) and (cs_promo_sk BETWEEN DynamicValue(RS_67_promotion_p_promo_sk_min) AND DynamicValue(RS_67_promotion_p_promo_sk_max) and in_bloom_filter(cs_promo_sk, DynamicValue(RS_67_promotion_p_promo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_61_date_dim_d_date_sk_min) AND DynamicValue(RS_61_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_61_date_dim_d_date_sk_bloom_filter))) and cs_catalog_page_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_39] (rows=287989836 width=243) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_catalog_page_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_ext_sales_price","cs_net_profit"] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_467] - Group By Operator [GBY_466] (rows=1 width=12) + BROADCAST [RS_462] + Group By Operator [GBY_461] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_405] Group By Operator [GBY_402] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_398] (rows=8116 width=1119) + Select Operator [SEL_398] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_394] <-Reducer 28 [BROADCAST_EDGE] vectorized - BROADCAST [RS_469] - Group By Operator [GBY_468] (rows=1 width=12) + BROADCAST [RS_464] + Group By Operator [GBY_463] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_421] Group By Operator [GBY_418] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_414] (rows=154000 width=1436) + Select Operator [SEL_414] (rows=154000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_410] <-Reducer 32 [BROADCAST_EDGE] vectorized - BROADCAST [RS_471] - Group By Operator [GBY_470] (rows=1 width=12) + BROADCAST [RS_466] + Group By Operator [GBY_465] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_437] Group By Operator [GBY_434] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_430] (rows=1150 width=1179) + Select Operator [SEL_430] (rows=1150 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_426] - <-Reducer 40 [BROADCAST_EDGE] vectorized - BROADCAST [RS_479] - Group By Operator [GBY_478] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_477] - Group By Operator [GBY_476] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_475] (rows=46000 width=460) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_473] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_485] + <-Map 37 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_472] PartitionCols:_col0, _col1 - Select Operator [SEL_484] (rows=28798881 width=106) + Select Operator [SEL_471] (rows=28798881 width=227) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_483] (rows=28798881 width=106) + Filter Operator [FIL_470] (rows=28798881 width=227) predicate:cr_item_sk is not null - TableScan [TS_42] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_return_amount","cr_net_loss"] + TableScan [TS_42] (rows=28798881 width=227) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_return_amount","cr_net_loss"] <-Reducer 24 [CONTAINS] vectorized - Reduce Output Operator [RS_515] + Reduce Output Operator [RS_500] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_514] (rows=2435062716 width=108) + Group By Operator [GBY_499] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_513] (rows=811687572 width=108) + Top N Key Operator [TNK_498] (rows=39721 width=618) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_512] (rows=115958879 width=135) + Select Operator [SEL_497] (rows=53 width=615) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_511] (rows=115958879 width=135) + Group By Operator [GBY_496] (rows=53 width=436) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0 <-Reducer 23 [SIMPLE_EDGE] SHUFFLE [RS_115] PartitionCols:_col0 - Group By Operator [GBY_114] (rows=231917759 width=135) + Group By Operator [GBY_114] (rows=212 width=436) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)"],keys:_col0 - Select Operator [SEL_112] (rows=231917759 width=135) + Select Operator [SEL_112] (rows=2664536 width=322) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_374] (rows=231917759 width=135) - Conds:RS_109._col2=RS_499._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] - <-Map 44 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_499] + Merge Join Operator [MERGEJOIN_374] (rows=2664536 width=322) + Conds:RS_109._col2=RS_495._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] + <-Map 42 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_495] PartitionCols:_col0 - Select Operator [SEL_498] (rows=84 width=1850) + Select Operator [SEL_494] (rows=84 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_497] (rows=84 width=1850) + Filter Operator [FIL_493] (rows=84 width=104) predicate:web_site_sk is not null - TableScan [TS_94] (rows=84 width=1850) - default@web_site,web_site,Tbl:COMPLETE,Col:NONE,Output:["web_site_sk","web_site_id"] + TableScan [TS_94] (rows=84 width=104) + default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_site_id"] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_373] (rows=210834322 width=135) + Merge Join Operator [MERGEJOIN_373] (rows=2664536 width=226) Conds:RS_106._col3=RS_431._col0(Inner),Output:["_col2","_col5","_col6","_col9","_col10"] <-Map 30 [SIMPLE_EDGE] vectorized SHUFFLE [RS_431] @@ -423,7 +409,7 @@ Stage-0 <-Reducer 21 [SIMPLE_EDGE] SHUFFLE [RS_106] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_372] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_372] (rows=5329072 width=309) Conds:RS_103._col1=RS_415._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col9","_col10"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_415] @@ -432,112 +418,101 @@ Stage-0 <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_103] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_371] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_371] (rows=15987214 width=411) Conds:RS_100._col0=RS_399._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_399] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_394] - <-Reducer 42 [SIMPLE_EDGE] + <-Reducer 40 [SIMPLE_EDGE] SHUFFLE [RS_100] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_370] (rows=158402938 width=135) - Conds:RS_507._col1, _col4=RS_510._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"] - <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_507] + Merge Join Operator [MERGEJOIN_370] (rows=143894769 width=458) + Conds:RS_489._col1, _col4=RS_492._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"] + <-Map 39 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_489] PartitionCols:_col1, _col4 - Select Operator [SEL_506] (rows=144002668 width=135) + Select Operator [SEL_488] (rows=143894769 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_505] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_promo_sk BETWEEN DynamicValue(RS_107_promotion_p_promo_sk_min) AND DynamicValue(RS_107_promotion_p_promo_sk_max) and in_bloom_filter(ws_promo_sk, DynamicValue(RS_107_promotion_p_promo_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_101_date_dim_d_date_sk_min) AND DynamicValue(RS_101_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_101_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_110_web_site_web_site_sk_min) AND DynamicValue(RS_110_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_110_web_site_web_site_sk_bloom_filter))) and ws_item_sk is not null and ws_promo_sk is not null and ws_sold_date_sk is not null and ws_web_site_sk is not null) - TableScan [TS_79] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_site_sk","ws_promo_sk","ws_order_number","ws_ext_sales_price","ws_net_profit"] + Filter Operator [FIL_487] (rows=143894769 width=243) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_promo_sk BETWEEN DynamicValue(RS_107_promotion_p_promo_sk_min) AND DynamicValue(RS_107_promotion_p_promo_sk_max) and in_bloom_filter(ws_promo_sk, DynamicValue(RS_107_promotion_p_promo_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_101_date_dim_d_date_sk_min) AND DynamicValue(RS_101_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_101_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_promo_sk is not null and ws_sold_date_sk is not null and ws_web_site_sk is not null) + TableScan [TS_79] (rows=144002668 width=243) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_site_sk","ws_promo_sk","ws_order_number","ws_ext_sales_price","ws_net_profit"] <-Reducer 25 [BROADCAST_EDGE] vectorized - BROADCAST [RS_492] - Group By Operator [GBY_491] (rows=1 width=12) + BROADCAST [RS_482] + Group By Operator [GBY_481] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_406] Group By Operator [GBY_403] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_400] (rows=8116 width=1119) + Select Operator [SEL_400] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_394] <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_494] - Group By Operator [GBY_493] (rows=1 width=12) + BROADCAST [RS_484] + Group By Operator [GBY_483] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_422] Group By Operator [GBY_419] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_416] (rows=154000 width=1436) + Select Operator [SEL_416] (rows=154000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_410] <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_496] - Group By Operator [GBY_495] (rows=1 width=12) + BROADCAST [RS_486] + Group By Operator [GBY_485] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_438] Group By Operator [GBY_435] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_432] (rows=1150 width=1179) + Select Operator [SEL_432] (rows=1150 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_426] - <-Reducer 45 [BROADCAST_EDGE] vectorized - BROADCAST [RS_504] - Group By Operator [GBY_503] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 44 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_502] - Group By Operator [GBY_501] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_500] (rows=84 width=1850) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_498] - <-Map 43 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_510] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_492] PartitionCols:_col0, _col1 - Select Operator [SEL_509] (rows=14398467 width=92) + Select Operator [SEL_491] (rows=14398467 width=221) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_508] (rows=14398467 width=92) + Filter Operator [FIL_490] (rows=14398467 width=221) predicate:wr_item_sk is not null - TableScan [TS_82] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number","wr_return_amt","wr_net_loss"] + TableScan [TS_82] (rows=14398467 width=221) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_order_number","wr_return_amt","wr_net_loss"] <-Reducer 7 [CONTAINS] vectorized - Reduce Output Operator [RS_459] + Reduce Output Operator [RS_454] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_458] (rows=2435062716 width=108) + Group By Operator [GBY_453] (rows=59581 width=627) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L - Top N Key Operator [TNK_457] (rows=811687572 width=108) + Top N Key Operator [TNK_452] (rows=39721 width=618) keys:_col0, _col1, 0L,sort order:+++,top n:100 - Select Operator [SEL_456] (rows=463823414 width=88) + Select Operator [SEL_451] (rows=822 width=617) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_455] (rows=463823414 width=88) + Group By Operator [GBY_450] (rows=822 width=436) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_36] PartitionCols:_col0 - Group By Operator [GBY_35] (rows=927646829 width=88) + Group By Operator [GBY_35] (rows=9042 width=436) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)"],keys:_col0 - Select Operator [SEL_33] (rows=927646829 width=88) + Select Operator [SEL_33] (rows=9510435 width=276) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_364] (rows=927646829 width=88) - Conds:RS_30._col2=RS_443._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] + Merge Join Operator [MERGEJOIN_364] (rows=9510435 width=276) + Conds:RS_30._col2=RS_449._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"] <-Map 34 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_443] + SHUFFLE [RS_449] PartitionCols:_col0 - Select Operator [SEL_442] (rows=1704 width=1910) + Select Operator [SEL_448] (rows=1704 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_441] (rows=1704 width=1910) + Filter Operator [FIL_447] (rows=1704 width=104) predicate:s_store_sk is not null - TableScan [TS_15] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id"] + TableScan [TS_15] (rows=1704 width=104) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_363] (rows=843315281 width=88) + Merge Join Operator [MERGEJOIN_363] (rows=9510435 width=176) Conds:RS_27._col3=RS_427._col0(Inner),Output:["_col2","_col5","_col6","_col9","_col10"] <-Map 30 [SIMPLE_EDGE] vectorized SHUFFLE [RS_427] @@ -546,7 +521,7 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_362] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_362] (rows=19020869 width=200) Conds:RS_24._col1=RS_411._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col9","_col10"] <-Map 26 [SIMPLE_EDGE] vectorized SHUFFLE [RS_411] @@ -555,7 +530,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_361] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_361] (rows=57062604 width=360) Conds:RS_21._col0=RS_395._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"] <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_395] @@ -564,17 +539,17 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_360] (rows=633595212 width=88) - Conds:RS_451._col1, _col4=RS_454._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"] + Merge Join Operator [MERGEJOIN_360] (rows=513598586 width=452) + Conds:RS_443._col1, _col4=RS_446._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_451] + SHUFFLE [RS_443] PartitionCols:_col1, _col4 - Select Operator [SEL_450] (rows=575995635 width=88) + Select Operator [SEL_442] (rows=501693263 width=233) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_449] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_28_promotion_p_promo_sk_min) AND DynamicValue(RS_28_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_28_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_31_store_s_store_sk_min) AND DynamicValue(RS_31_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_31_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_ext_sales_price","ss_net_profit"] + Filter Operator [FIL_441] (rows=501693263 width=233) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_28_promotion_p_promo_sk_min) AND DynamicValue(RS_28_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_28_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=233) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_ext_sales_price","ss_net_profit"] <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_408] Group By Operator [GBY_407] (rows=1 width=12) @@ -583,7 +558,7 @@ Stage-0 SHUFFLE [RS_404] Group By Operator [GBY_401] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_396] (rows=8116 width=1119) + Select Operator [SEL_396] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_394] <-Reducer 27 [BROADCAST_EDGE] vectorized @@ -594,7 +569,7 @@ Stage-0 SHUFFLE [RS_420] Group By Operator [GBY_417] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_412] (rows=154000 width=1436) + Select Operator [SEL_412] (rows=154000 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_410] <-Reducer 31 [BROADCAST_EDGE] vectorized @@ -605,27 +580,16 @@ Stage-0 SHUFFLE [RS_436] Group By Operator [GBY_433] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_428] (rows=1150 width=1179) + Select Operator [SEL_428] (rows=1150 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_426] - <-Reducer 35 [BROADCAST_EDGE] vectorized - BROADCAST [RS_448] - Group By Operator [GBY_447] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_446] - Group By Operator [GBY_445] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_444] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_442] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_454] + SHUFFLE [RS_446] PartitionCols:_col0, _col1 - Select Operator [SEL_453] (rows=57591150 width=77) + Select Operator [SEL_445] (rows=57591150 width=224) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_452] (rows=57591150 width=77) + Filter Operator [FIL_444] (rows=57591150 width=224) predicate:sr_item_sk is not null - TableScan [TS_3] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number","sr_return_amt","sr_net_loss"] + TableScan [TS_3] (rows=57591150 width=224) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number","sr_return_amt","sr_net_loss"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query81.q.out b/ql/src/test/results/clientpositive/perf/tez/query81.q.out index 3dd59754dd..96b0d38d75 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query81.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query81.q.out @@ -78,90 +78,90 @@ Stage-0 Stage-1 Reducer 4 vectorized File Output Operator [FS_210] - Select Operator [SEL_209] (rows=100 width=860) + Select Operator [SEL_209] (rows=100 width=1506) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] - Limit [LIM_208] (rows=100 width=860) + Limit [LIM_208] (rows=100 width=1420) Number of rows:100 - Select Operator [SEL_207] (rows=96800003 width=860) + Select Operator [SEL_207] (rows=1577696 width=1418) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_63] - Select Operator [SEL_62] (rows=96800003 width=860) + Select Operator [SEL_62] (rows=1577696 width=1418) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] - Merge Join Operator [MERGEJOIN_178] (rows=96800003 width=860) + Merge Join Operator [MERGEJOIN_178] (rows=1577696 width=1418) Conds:RS_59._col0=RS_60._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17","_col20"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_60] PartitionCols:_col0 - Select Operator [SEL_55] (rows=8066666 width=1014) + Select Operator [SEL_55] (rows=1609248 width=227) Output:["_col0","_col2"] - Filter Operator [FIL_54] (rows=8066666 width=1014) + Filter Operator [FIL_54] (rows=1609248 width=227) predicate:(_col2 > _col3) - Merge Join Operator [MERGEJOIN_177] (rows=24200000 width=1014) + Merge Join Operator [MERGEJOIN_177] (rows=4827746 width=227) Conds:RS_201._col1=RS_206._col1(Inner),Output:["_col0","_col2","_col3"] <-Reducer 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_206] PartitionCols:_col1 - Select Operator [SEL_205] (rows=11000000 width=1014) + Select Operator [SEL_205] (rows=12 width=198) Output:["_col0","_col1"] - Group By Operator [GBY_204] (rows=11000000 width=1014) + Group By Operator [GBY_204] (rows=12 width=206) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col0 - Select Operator [SEL_203] (rows=22000000 width=1014) + Select Operator [SEL_203] (rows=5266632 width=201) Output:["_col0","_col2"] - Group By Operator [GBY_202] (rows=22000000 width=1014) + Group By Operator [GBY_202] (rows=5266632 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0 - Group By Operator [GBY_42] (rows=44000000 width=1014) + Group By Operator [GBY_42] (rows=8749496 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_176] (rows=44000000 width=1014) + Merge Join Operator [MERGEJOIN_176] (rows=8749496 width=194) Conds:RS_38._col2=RS_198._col0(Inner),Output:["_col1","_col3","_col7"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_198] PartitionCols:_col0 - Select Operator [SEL_196] (rows=40000000 width=1014) + Select Operator [SEL_196] (rows=40000000 width=90) Output:["_col0","_col1"] - Filter Operator [FIL_195] (rows=40000000 width=1014) + Filter Operator [FIL_195] (rows=40000000 width=90) predicate:(ca_address_sk is not null and ca_state is not null) - TableScan [TS_12] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + TableScan [TS_12] (rows=40000000 width=90) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_175] (rows=31678769 width=106) + Merge Join Operator [MERGEJOIN_175] (rows=8749496 width=112) Conds:RS_190._col0=RS_194._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_194] PartitionCols:_col0 - Select Operator [SEL_192] (rows=36524 width=1119) + Select Operator [SEL_192] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_191] (rows=36524 width=1119) + Filter Operator [FIL_191] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_9] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_190] PartitionCols:_col0 - Select Operator [SEL_188] (rows=28798881 width=106) + Select Operator [SEL_188] (rows=28221532 width=121) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_186] (rows=28798881 width=106) + Filter Operator [FIL_186] (rows=28221532 width=121) predicate:(cr_returned_date_sk is not null and cr_returning_addr_sk is not null) - TableScan [TS_6] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_returning_addr_sk","cr_return_amt_inc_tax"] + TableScan [TS_6] (rows=28798881 width=121) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_returning_addr_sk","cr_return_amt_inc_tax"] <-Reducer 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_201] PartitionCols:_col1 - Select Operator [SEL_200] (rows=22000000 width=1014) + Select Operator [SEL_200] (rows=4827746 width=201) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_199] (rows=22000000 width=1014) + Group By Operator [GBY_199] (rows=4827746 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0, _col1 - Group By Operator [GBY_22] (rows=44000000 width=1014) + Group By Operator [GBY_22] (rows=8574602 width=201) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1 - Merge Join Operator [MERGEJOIN_174] (rows=44000000 width=1014) + Merge Join Operator [MERGEJOIN_174] (rows=8574602 width=194) Conds:RS_18._col2=RS_197._col0(Inner),Output:["_col1","_col3","_col7"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_197] @@ -170,7 +170,7 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_173] (rows=31678769 width=106) + Merge Join Operator [MERGEJOIN_173] (rows=8574602 width=112) Conds:RS_189._col0=RS_193._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_193] @@ -179,32 +179,32 @@ Stage-0 <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_189] PartitionCols:_col0 - Select Operator [SEL_187] (rows=28798881 width=106) + Select Operator [SEL_187] (rows=27657410 width=121) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_185] (rows=28798881 width=106) + Filter Operator [FIL_185] (rows=27657410 width=121) predicate:(cr_returned_date_sk is not null and cr_returning_addr_sk is not null and cr_returning_customer_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_172] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_172] (rows=1568628 width=1310) Conds:RS_181._col2=RS_184._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_181] PartitionCols:_col2 - Select Operator [SEL_180] (rows=80000000 width=860) + Select Operator [SEL_180] (rows=80000000 width=375) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_179] (rows=80000000 width=860) + Filter Operator [FIL_179] (rows=80000000 width=375) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name"] + TableScan [TS_0] (rows=80000000 width=375) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_184] PartitionCols:_col0 - Select Operator [SEL_183] (rows=20000000 width=1014) + Select Operator [SEL_183] (rows=784314 width=1027) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col8","_col9","_col10","_col11"] - Filter Operator [FIL_182] (rows=20000000 width=1014) + Filter Operator [FIL_182] (rows=784314 width=1027) predicate:((ca_state = 'IL') and ca_address_sk is not null) - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_street_type","ca_suite_number","ca_city","ca_county","ca_state","ca_zip","ca_country","ca_gmt_offset","ca_location_type"] + TableScan [TS_3] (rows=40000000 width=1027) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_street_number","ca_street_name","ca_street_type","ca_suite_number","ca_city","ca_county","ca_state","ca_zip","ca_country","ca_gmt_offset","ca_location_type"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query82.q.out b/ql/src/test/results/clientpositive/perf/tez/query82.q.out index de5a68141e..916e45509f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query82.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query82.q.out @@ -47,64 +47,64 @@ Stage-0 Stage-1 Reducer 4 vectorized File Output Operator [FS_97] - Limit [LIM_96] (rows=100 width=88) + Limit [LIM_96] (rows=100 width=396) Number of rows:100 - Select Operator [SEL_95] (rows=633595212 width=88) + Select Operator [SEL_95] (rows=26286282 width=396) Output:["_col0","_col1","_col2"] <-Reducer 3 [SIMPLE_EDGE] vectorized SHUFFLE [RS_94] - Group By Operator [GBY_93] (rows=633595212 width=88) + Group By Operator [GBY_93] (rows=26286282 width=396) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_21] (rows=1267190424 width=88) + Group By Operator [GBY_21] (rows=237894414 width=395) Output:["_col0","_col1","_col2"],keys:_col2, _col3, _col4 - Top N Key Operator [TNK_43] (rows=1267190424 width=88) + Top N Key Operator [TNK_43] (rows=237894414 width=396) keys:_col2, _col3, _col4,sort order:+++,top n:100 - Merge Join Operator [MERGEJOIN_73] (rows=1267190424 width=88) + Merge Join Operator [MERGEJOIN_73] (rows=237894414 width=396) Conds:RS_92._col0=RS_76._col0(Inner),RS_76._col0=RS_18._col1(Inner),Output:["_col2","_col3","_col4"] <-Map 5 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_76] PartitionCols:_col0 - Select Operator [SEL_75] (rows=51333 width=1436) + Select Operator [SEL_75] (rows=297 width=404) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_74] (rows=51333 width=1436) + Filter Operator [FIL_74] (rows=297 width=404) predicate:((i_manufact_id) IN (437, 129, 727, 663) and i_current_price BETWEEN 30 AND 60 and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_manufact_id"] + TableScan [TS_3] (rows=462000 width=403) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_manufact_id"] <-Reducer 8 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_72] (rows=4593600 width=15) + Merge Join Operator [MERGEJOIN_72] (rows=463969 width=4) Conds:RS_84._col0=RS_87._col0(Inner),Output:["_col1"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=8116 width=1119) + Select Operator [SEL_86] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_85] (rows=8116 width=1119) + Filter Operator [FIL_85] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2002-05-30 00:00:00' AND TIMESTAMP'2002-07-29 00:00:00' and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_9] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_84] PartitionCols:_col0 - Select Operator [SEL_83] (rows=4176000 width=15) + Select Operator [SEL_83] (rows=4176000 width=11) Output:["_col0","_col1"] - Filter Operator [FIL_82] (rows=4176000 width=15) + Filter Operator [FIL_82] (rows=4176000 width=11) predicate:(inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) - TableScan [TS_6] (rows=37584000 width=15) - default@inventory,inventory,Tbl:COMPLETE,Col:NONE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] + TableScan [TS_6] (rows=37584000 width=11) + default@inventory,inventory,Tbl:COMPLETE,Col:COMPLETE,Output:["inv_date_sk","inv_item_sk","inv_quantity_on_hand"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_92] PartitionCols:_col0 - Select Operator [SEL_91] (rows=575995635 width=88) + Select Operator [SEL_91] (rows=575995635 width=4) Output:["_col0"] - Filter Operator [FIL_90] (rows=575995635 width=88) + Filter Operator [FIL_90] (rows=575995635 width=4) predicate:((ss_item_sk BETWEEN DynamicValue(RS_17_item_i_item_sk_min) AND DynamicValue(RS_17_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_17_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_18_inventory_inv_item_sk_min) AND DynamicValue(RS_18_inventory_inv_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_18_inventory_inv_item_sk_bloom_filter))) and ss_item_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk"] + TableScan [TS_0] (rows=575995635 width=4) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk"] <-Reducer 6 [BROADCAST_EDGE] vectorized BROADCAST [RS_81] Group By Operator [GBY_80] (rows=1 width=12) @@ -113,18 +113,18 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_79] Group By Operator [GBY_78] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_77] (rows=51333 width=1436) + Select Operator [SEL_77] (rows=297 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_75] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_89] Group By Operator [GBY_88] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4593600)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_51] Group By Operator [GBY_50] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4593600)"] - Select Operator [SEL_49] (rows=4593600 width=15) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_49] (rows=463969 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_72] diff --git a/ql/src/test/results/clientpositive/perf/tez/query83.q.out b/ql/src/test/results/clientpositive/perf/tez/query83.q.out index c33b37c87b..9684c16b25 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query83.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query83.q.out @@ -154,108 +154,108 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_395] - Limit [LIM_394] (rows=100 width=77) + Limit [LIM_394] (rows=100 width=260) Number of rows:100 - Select Operator [SEL_393] (rows=76653825 width=77) + Select Operator [SEL_393] (rows=130021 width=260) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_125] - Select Operator [SEL_124] (rows=76653825 width=77) + Select Operator [SEL_124] (rows=130021 width=260) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_360] (rows=76653825 width=77) + Merge Join Operator [MERGEJOIN_360] (rows=130021 width=124) Conds:RS_382._col0=RS_387._col0(Inner),RS_382._col0=RS_392._col0(Inner),Output:["_col0","_col1","_col3","_col5"] <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_387] PartitionCols:_col0 - Group By Operator [GBY_386] (rows=34842647 width=77) + Group By Operator [GBY_386] (rows=141711 width=108) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_77] PartitionCols:_col0 - Group By Operator [GBY_76] (rows=69685294 width=77) + Group By Operator [GBY_76] (rows=1558821 width=108) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_358] (rows=69685294 width=77) + Merge Join Operator [MERGEJOIN_358] (rows=25343167 width=103) Conds:RS_72._col0=RS_73._col0(Inner),Output:["_col2","_col4"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_73] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_350] (rows=80353 width=1119) + Merge Join Operator [MERGEJOIN_350] (rows=5070 width=4) Conds:RS_371._col1=RS_380._col0(Inner),Output:["_col0"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_371] PartitionCols:_col1 - Select Operator [SEL_370] (rows=73049 width=1119) + Select Operator [SEL_370] (rows=73049 width=98) Output:["_col0","_col1"] - Filter Operator [FIL_369] (rows=73049 width=1119) + Filter Operator [FIL_369] (rows=73049 width=98) predicate:(d_date is not null and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_6] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_380] PartitionCols:_col0 - Group By Operator [GBY_379] (rows=40176 width=1119) + Group By Operator [GBY_379] (rows=5070 width=94) Output:["_col0"],keys:KEY._col0 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col0 - Group By Operator [GBY_21] (rows=80353 width=1119) + Group By Operator [GBY_21] (rows=5070 width=94) Output:["_col0"],keys:_col0 - Merge Join Operator [MERGEJOIN_349] (rows=80353 width=1119) + Merge Join Operator [MERGEJOIN_349] (rows=10141 width=94) Conds:RS_374._col1=RS_378._col0(Left Semi),Output:["_col0"] <-Map 16 [SIMPLE_EDGE] vectorized SHUFFLE [RS_374] PartitionCols:_col1 - Select Operator [SEL_373] (rows=73049 width=1119) + Select Operator [SEL_373] (rows=73049 width=98) Output:["_col0","_col1"] - Filter Operator [FIL_372] (rows=73049 width=1119) + Filter Operator [FIL_372] (rows=73049 width=98) predicate:(d_date is not null and d_week_seq is not null) - TableScan [TS_9] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] + TableScan [TS_9] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] <-Map 19 [SIMPLE_EDGE] vectorized SHUFFLE [RS_378] PartitionCols:_col0 - Group By Operator [GBY_377] (rows=73049 width=1119) + Group By Operator [GBY_377] (rows=1826 width=4) Output:["_col0"],keys:_col0 - Select Operator [SEL_376] (rows=73049 width=1119) + Select Operator [SEL_376] (rows=3652 width=4) Output:["_col0"] - Filter Operator [FIL_375] (rows=73049 width=1119) + Filter Operator [FIL_375] (rows=3652 width=98) predicate:((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') and d_week_seq is not null) - TableScan [TS_12] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] + TableScan [TS_12] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date","d_week_seq"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_72] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_351] (rows=63350266 width=77) + Merge Join Operator [MERGEJOIN_351] (rows=55578005 width=107) Conds:RS_385._col1=RS_367._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_367] PartitionCols:_col0 - Select Operator [SEL_365] (rows=462000 width=1436) + Select Operator [SEL_365] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_364] (rows=462000 width=1436) + Filter Operator [FIL_364] (rows=462000 width=104) predicate:(i_item_id is not null and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + TableScan [TS_3] (rows=462000 width=104) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_385] PartitionCols:_col1 - Select Operator [SEL_384] (rows=57591150 width=77) + Select Operator [SEL_384] (rows=55578005 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_383] (rows=57591150 width=77) + Filter Operator [FIL_383] (rows=55578005 width=11) predicate:(sr_item_sk is not null and sr_returned_date_sk is not null) - TableScan [TS_40] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_return_quantity"] + TableScan [TS_40] (rows=57591150 width=11) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_return_quantity"] <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_392] PartitionCols:_col0 - Group By Operator [GBY_391] (rows=8711072 width=92) + Group By Operator [GBY_391] (rows=130021 width=108) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_117] PartitionCols:_col0 - Group By Operator [GBY_116] (rows=17422145 width=92) + Group By Operator [GBY_116] (rows=390063 width=108) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_359] (rows=17422145 width=92) + Merge Join Operator [MERGEJOIN_359] (rows=5752600 width=103) Conds:RS_112._col0=RS_113._col0(Inner),Output:["_col2","_col4"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_113] @@ -264,7 +264,7 @@ Stage-0 <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_112] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_354] (rows=15838314 width=92) + Merge Join Operator [MERGEJOIN_354] (rows=13749816 width=107) Conds:RS_390._col1=RS_368._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_368] @@ -273,23 +273,23 @@ Stage-0 <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_390] PartitionCols:_col1 - Select Operator [SEL_389] (rows=14398467 width=92) + Select Operator [SEL_389] (rows=13749816 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_388] (rows=14398467 width=92) + Filter Operator [FIL_388] (rows=13749816 width=11) predicate:(wr_item_sk is not null and wr_returned_date_sk is not null) - TableScan [TS_80] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_item_sk","wr_return_quantity"] + TableScan [TS_80] (rows=14398467 width=11) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_returned_date_sk","wr_item_sk","wr_return_quantity"] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_382] PartitionCols:_col0 - Group By Operator [GBY_381] (rows=17423323 width=106) + Group By Operator [GBY_381] (rows=134905 width=108) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col0 - Group By Operator [GBY_36] (rows=34846646 width=106) + Group By Operator [GBY_36] (rows=809430 width=108) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_357] (rows=34846646 width=106) + Merge Join Operator [MERGEJOIN_357] (rows=12501392 width=103) Conds:RS_32._col0=RS_33._col0(Inner),Output:["_col2","_col4"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_33] @@ -298,7 +298,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_348] (rows=31678769 width=106) + Merge Join Operator [MERGEJOIN_348] (rows=28798881 width=107) Conds:RS_363._col1=RS_366._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_366] @@ -307,10 +307,10 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_363] PartitionCols:_col1 - Select Operator [SEL_362] (rows=28798881 width=106) + Select Operator [SEL_362] (rows=28798881 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_361] (rows=28798881 width=106) + Filter Operator [FIL_361] (rows=28798881 width=11) predicate:(cr_item_sk is not null and cr_returned_date_sk is not null) - TableScan [TS_0] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_item_sk","cr_return_quantity"] + TableScan [TS_0] (rows=28798881 width=11) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_returned_date_sk","cr_item_sk","cr_return_quantity"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query84.q.out b/ql/src/test/results/clientpositive/perf/tez/query84.q.out index a2396ffe95..c14b3175a5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query84.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query84.q.out @@ -53,43 +53,43 @@ Stage-0 Stage-1 Reducer 3 vectorized File Output Operator [FS_137] - Limit [LIM_136] (rows=100 width=860) + Limit [LIM_136] (rows=100 width=384) Number of rows:100 - Select Operator [SEL_135] (rows=212960011 width=860) + Select Operator [SEL_135] (rows=255285 width=384) Output:["_col0","_col1"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_34] - Select Operator [SEL_33] (rows=212960011 width=860) + Select Operator [SEL_33] (rows=255285 width=384) Output:["_col1","_col2"] - Merge Join Operator [MERGEJOIN_116] (rows=212960011 width=860) + Merge Join Operator [MERGEJOIN_116] (rows=255285 width=280) Conds:RS_119._col0=RS_122._col0(Inner),RS_122._col0=RS_31._col1(Inner),Output:["_col2","_col6","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_119] PartitionCols:_col0 - Select Operator [SEL_118] (rows=57591150 width=77) + Select Operator [SEL_118] (rows=55577698 width=3) Output:["_col0"] - Filter Operator [FIL_117] (rows=57591150 width=77) + Filter Operator [FIL_117] (rows=55577698 width=3) predicate:sr_cdemo_sk is not null - TableScan [TS_0] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_cdemo_sk"] + TableScan [TS_0] (rows=57591150 width=3) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_cdemo_sk"] <-Map 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_122] PartitionCols:_col0 - Select Operator [SEL_121] (rows=1861800 width=385) + Select Operator [SEL_121] (rows=1861800 width=4) Output:["_col0"] - Filter Operator [FIL_120] (rows=1861800 width=385) + Filter Operator [FIL_120] (rows=1861800 width=4) predicate:cd_demo_sk is not null - TableScan [TS_3] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk"] + TableScan [TS_3] (rows=1861800 width=4) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_115] (rows=96800003 width=860) + Merge Join Operator [MERGEJOIN_115] (rows=8315 width=280) Conds:RS_25._col2=RS_26._col0(Inner),Output:["_col0","_col1","_col4","_col5"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_114] (rows=7920 width=107) + Merge Join Operator [MERGEJOIN_114] (rows=721 width=4) Conds:RS_131._col1=RS_134._col0(Inner),Output:["_col0"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_134] @@ -99,37 +99,37 @@ Stage-0 Filter Operator [FIL_132] (rows=2 width=12) predicate:((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287) and ib_income_band_sk is not null) TableScan [TS_15] (rows=20 width=12) - default@income_band,income_band,Tbl:COMPLETE,Col:NONE,Output:["ib_income_band_sk","ib_lower_bound","ib_upper_bound"] + default@income_band,income_band,Tbl:COMPLETE,Col:COMPLETE,Output:["ib_income_band_sk","ib_lower_bound","ib_upper_bound"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_131] PartitionCols:_col1 - Select Operator [SEL_130] (rows=7200 width=107) + Select Operator [SEL_130] (rows=7200 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_129] (rows=7200 width=107) + Filter Operator [FIL_129] (rows=7200 width=8) predicate:(hd_demo_sk is not null and hd_income_band_sk is not null) - TableScan [TS_12] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_income_band_sk"] + TableScan [TS_12] (rows=7200 width=8) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_income_band_sk"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_113] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_113] (rows=83148 width=280) Conds:RS_125._col3=RS_128._col0(Inner),Output:["_col0","_col1","_col2","_col4","_col5"] <-Map 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_125] PartitionCols:_col3 - Select Operator [SEL_124] (rows=80000000 width=860) + Select Operator [SEL_124] (rows=74500295 width=291) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_123] (rows=80000000 width=860) + Filter Operator [FIL_123] (rows=74500295 width=291) predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null) - TableScan [TS_6] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_id","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk","c_first_name","c_last_name"] + TableScan [TS_6] (rows=80000000 width=291) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_id","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk","c_first_name","c_last_name"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_128] PartitionCols:_col0 - Select Operator [SEL_127] (rows=20000000 width=1014) + Select Operator [SEL_127] (rows=44643 width=96) Output:["_col0"] - Filter Operator [FIL_126] (rows=20000000 width=1014) + Filter Operator [FIL_126] (rows=44643 width=97) predicate:((ca_city = 'Hopewell') and ca_address_sk is not null) - TableScan [TS_9] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_city"] + TableScan [TS_9] (rows=40000000 width=97) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_city"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query85.q.out b/ql/src/test/results/clientpositive/perf/tez/query85.q.out index bd6f45f051..2d2c36fde2 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query85.q.out @@ -167,17 +167,16 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Map 16 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Map 18 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 8 <- Map 17 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 @@ -185,125 +184,125 @@ Stage-0 limit:-1 Stage-1 Reducer 10 vectorized - File Output Operator [FS_244] - Limit [LIM_243] (rows=100 width=1014) + File Output Operator [FS_239] + Limit [LIM_238] (rows=72 width=832) Number of rows:100 - Select Operator [SEL_242] (rows=4436665 width=1014) + Select Operator [SEL_237] (rows=72 width=832) Output:["_col0","_col1","_col2","_col3"] <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_241] - Select Operator [SEL_240] (rows=4436665 width=1014) + SHUFFLE [RS_236] + Select Operator [SEL_235] (rows=72 width=832) Output:["_col4","_col5","_col6","_col7"] - Group By Operator [GBY_239] (rows=4436665 width=1014) + Group By Operator [GBY_234] (rows=72 width=353) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_48] (rows=8873331 width=1014) + Group By Operator [GBY_48] (rows=72 width=353) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col4)","count(_col4)","sum(_col16)","count(_col16)","sum(_col15)","count(_col15)"],keys:_col28 - Merge Join Operator [MERGEJOIN_206] (rows=8873331 width=1014) - Conds:RS_44._col13=RS_238._col0(Inner),Output:["_col4","_col15","_col16","_col28"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_238] + Merge Join Operator [MERGEJOIN_206] (rows=3270 width=259) + Conds:RS_44._col13=RS_233._col0(Inner),Output:["_col4","_col15","_col16","_col28"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_233] PartitionCols:_col0 - Select Operator [SEL_237] (rows=72 width=200) + Select Operator [SEL_232] (rows=72 width=101) Output:["_col0","_col1"] - Filter Operator [FIL_236] (rows=72 width=200) + Filter Operator [FIL_231] (rows=72 width=101) predicate:r_reason_sk is not null - TableScan [TS_21] (rows=72 width=200) - default@reason,reason,Tbl:COMPLETE,Col:NONE,Output:["r_reason_sk","r_reason_desc"] + TableScan [TS_21] (rows=72 width=101) + default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk","r_reason_desc"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col13 - Merge Join Operator [MERGEJOIN_205] (rows=8066665 width=1014) - Conds:RS_41._col2=RS_217._col0(Inner),Output:["_col4","_col13","_col15","_col16"] + Merge Join Operator [MERGEJOIN_205] (rows=3270 width=165) + Conds:RS_41._col2=RS_230._col0(Inner),Output:["_col4","_col13","_col15","_col16"] <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_217] + SHUFFLE [RS_230] PartitionCols:_col0 - Select Operator [SEL_216] (rows=4602 width=585) + Select Operator [SEL_229] (rows=4602 width=4) Output:["_col0"] - Filter Operator [FIL_215] (rows=4602 width=585) + Filter Operator [FIL_228] (rows=4602 width=4) predicate:wp_web_page_sk is not null - TableScan [TS_18] (rows=4602 width=585) - default@web_page,web_page,Tbl:COMPLETE,Col:NONE,Output:["wp_web_page_sk"] + TableScan [TS_18] (rows=4602 width=4) + default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col2 - Filter Operator [FIL_40] (rows=7333332 width=1014) + Filter Operator [FIL_40] (rows=3270 width=367) predicate:((((_col24 = 'KY') or (_col24 = 'GA') or (_col24 = 'NM')) and _col6 BETWEEN 100 AND 200) or (((_col24 = 'MT') or (_col24 = 'OR') or (_col24 = 'IN')) and _col6 BETWEEN 150 AND 300) or (((_col24 = 'WI') or (_col24 = 'MO') or (_col24 = 'WV')) and _col6 BETWEEN 50 AND 250)) - Merge Join Operator [MERGEJOIN_204] (rows=22000000 width=1014) - Conds:RS_37._col11=RS_235._col0(Inner),Output:["_col2","_col4","_col6","_col13","_col15","_col16","_col24"] + Merge Join Operator [MERGEJOIN_204] (rows=9818 width=367) + Conds:RS_37._col11=RS_227._col0(Inner),Output:["_col2","_col4","_col6","_col13","_col15","_col16","_col24"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_235] + SHUFFLE [RS_227] PartitionCols:_col0 - Select Operator [SEL_234] (rows=20000000 width=1014) + Select Operator [SEL_226] (rows=20000000 width=187) Output:["_col0","_col1"] - Filter Operator [FIL_233] (rows=20000000 width=1014) + Filter Operator [FIL_225] (rows=20000000 width=187) predicate:((ca_country = 'United States') and ca_address_sk is not null) - TableScan [TS_15] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state","ca_country"] + TableScan [TS_15] (rows=40000000 width=187) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col11 - Merge Join Operator [MERGEJOIN_203] (rows=5856506 width=135) - Conds:RS_34._col12, _col18, _col19=RS_231._col0, _col1, _col2(Inner),Output:["_col2","_col4","_col6","_col11","_col13","_col15","_col16"] + Merge Join Operator [MERGEJOIN_203] (rows=19635 width=318) + Conds:RS_34._col12, _col18, _col19=RS_223._col0, _col1, _col2(Inner),Output:["_col2","_col4","_col6","_col11","_col13","_col15","_col16"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_231] + SHUFFLE [RS_223] PartitionCols:_col0, _col1, _col2 - Select Operator [SEL_230] (rows=1861800 width=385) + Select Operator [SEL_222] (rows=265971 width=183) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_229] (rows=1861800 width=385) + Filter Operator [FIL_221] (rows=265971 width=183) predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) - TableScan [TS_12] (rows=1861800 width=385) - default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + TableScan [TS_12] (rows=1861800 width=183) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col12, _col18, _col19 - Filter Operator [FIL_33] (rows=5324097 width=135) + Filter Operator [FIL_33] (rows=19635 width=612) predicate:(((_col18 = 'D') and (_col19 = 'Primary') and _col5 BETWEEN 50 AND 100) or ((_col18 = 'M') and (_col19 = '4 yr Degree') and _col5 BETWEEN 100 AND 150) or ((_col18 = 'U') and (_col19 = 'Advanced Degree') and _col5 BETWEEN 150 AND 200)) - Merge Join Operator [MERGEJOIN_202] (rows=63889183 width=135) - Conds:RS_30._col10=RS_232._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col11","_col12","_col13","_col15","_col16","_col18","_col19"] + Merge Join Operator [MERGEJOIN_202] (rows=3711392 width=612) + Conds:RS_30._col10=RS_224._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col11","_col12","_col13","_col15","_col16","_col18","_col19"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_232] + SHUFFLE [RS_224] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_230] + Please refer to the previous Select Operator [SEL_222] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col10 - Merge Join Operator [MERGEJOIN_201] (rows=58081075 width=135) - Conds:RS_27._col1, _col3=RS_228._col0, _col5(Inner),Output:["_col2","_col4","_col5","_col6","_col10","_col11","_col12","_col13","_col15","_col16"] + Merge Join Operator [MERGEJOIN_201] (rows=25617525 width=466) + Conds:RS_27._col1, _col3=RS_220._col0, _col5(Inner),Output:["_col2","_col4","_col5","_col6","_col10","_col11","_col12","_col13","_col15","_col16"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_228] + SHUFFLE [RS_220] PartitionCols:_col0, _col5 - Select Operator [SEL_227] (rows=14398467 width=92) + Select Operator [SEL_219] (rows=11975292 width=237) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_226] (rows=14398467 width=92) + Filter Operator [FIL_218] (rows=11975292 width=237) predicate:(wr_item_sk is not null and wr_order_number is not null and wr_reason_sk is not null and wr_refunded_addr_sk is not null and wr_refunded_cdemo_sk is not null and wr_returning_cdemo_sk is not null) - TableScan [TS_6] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_refunded_cdemo_sk","wr_refunded_addr_sk","wr_returning_cdemo_sk","wr_reason_sk","wr_order_number","wr_fee","wr_refunded_cash"] + TableScan [TS_6] (rows=14398467 width=237) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_refunded_cdemo_sk","wr_refunded_addr_sk","wr_returning_cdemo_sk","wr_reason_sk","wr_order_number","wr_fee","wr_refunded_cash"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col1, _col3 - Merge Join Operator [MERGEJOIN_200] (rows=52800977 width=135) - Conds:RS_225._col0=RS_209._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] + Merge Join Operator [MERGEJOIN_200] (rows=17130671 width=239) + Conds:RS_217._col0=RS_209._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_209] PartitionCols:_col0 - Select Operator [SEL_208] (rows=36524 width=1119) + Select Operator [SEL_208] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_207] (rows=36524 width=1119) + Filter Operator [FIL_207] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_225] + SHUFFLE [RS_217] PartitionCols:_col0 - Select Operator [SEL_224] (rows=48000888 width=135) + Select Operator [SEL_216] (rows=47977044 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_223] (rows=48000888 width=135) - predicate:((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and (ws_sold_date_sk BETWEEN DynamicValue(RS_25_date_dim_d_date_sk_min) AND DynamicValue(RS_25_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_25_date_dim_d_date_sk_bloom_filter))) and (ws_web_page_sk BETWEEN DynamicValue(RS_42_web_page_wp_web_page_sk_min) AND DynamicValue(RS_42_web_page_wp_web_page_sk_max) and in_bloom_filter(ws_web_page_sk, DynamicValue(RS_42_web_page_wp_web_page_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"] + Filter Operator [FIL_215] (rows=47977044 width=243) + predicate:((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and (ws_sold_date_sk BETWEEN DynamicValue(RS_25_date_dim_d_date_sk_min) AND DynamicValue(RS_25_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_25_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) + TableScan [TS_0] (rows=144002668 width=243) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_page_sk","ws_order_number","ws_quantity","ws_sales_price","ws_net_profit"] <-Reducer 12 [BROADCAST_EDGE] vectorized BROADCAST [RS_214] Group By Operator [GBY_213] (rows=1 width=12) @@ -312,18 +311,7 @@ Stage-0 SHUFFLE [RS_212] Group By Operator [GBY_211] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_210] (rows=36524 width=1119) + Select Operator [SEL_210] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_208] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_222] - Group By Operator [GBY_221] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_220] - Group By Operator [GBY_219] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_218] (rows=4602 width=585) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_216] diff --git a/ql/src/test/results/clientpositive/perf/tez/query86.q.out b/ql/src/test/results/clientpositive/perf/tez/query86.q.out index 8140b72795..c757d74299 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query86.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query86.q.out @@ -51,8 +51,7 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 8 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) @@ -65,78 +64,67 @@ Stage-0 limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_89] - Limit [LIM_88] (rows=100 width=135) + File Output Operator [FS_84] + Limit [LIM_83] (rows=100 width=490) Number of rows:100 - Select Operator [SEL_87] (rows=261364852 width=135) + Select Operator [SEL_82] (rows=3060 width=490) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_86] - Select Operator [SEL_85] (rows=261364852 width=135) + SHUFFLE [RS_81] + Select Operator [SEL_80] (rows=3060 width=490) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - PTF Operator [PTF_84] (rows=261364852 width=135) + PTF Operator [PTF_79] (rows=3060 width=302) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 DESC NULLS LAST","partition by:":"(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END"}] - Select Operator [SEL_83] (rows=261364852 width=135) + Select Operator [SEL_78] (rows=3060 width=302) Output:["_col0","_col1","_col2","_col3"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_82] + SHUFFLE [RS_77] PartitionCols:(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END - Select Operator [SEL_81] (rows=261364852 width=135) + Select Operator [SEL_76] (rows=3060 width=302) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_80] (rows=261364852 width=135) + Group By Operator [GBY_75] (rows=3060 width=302) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_17] (rows=522729705 width=135) + Group By Operator [GBY_17] (rows=58140 width=302) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col0, _col1, 0L - Select Operator [SEL_15] (rows=174243235 width=135) + Select Operator [SEL_15] (rows=15995224 width=293) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_60] (rows=174243235 width=135) - Conds:RS_12._col1=RS_71._col0(Inner),Output:["_col2","_col6","_col7"] + Merge Join Operator [MERGEJOIN_60] (rows=15995224 width=293) + Conds:RS_12._col1=RS_74._col0(Inner),Output:["_col2","_col6","_col7"] <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_71] + SHUFFLE [RS_74] PartitionCols:_col0 - Select Operator [SEL_70] (rows=462000 width=1436) + Select Operator [SEL_73] (rows=462000 width=186) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_69] (rows=462000 width=1436) + Filter Operator [FIL_72] (rows=462000 width=186) predicate:i_item_sk is not null - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_class","i_category"] + TableScan [TS_6] (rows=462000 width=186) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_class","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_59] (rows=158402938 width=135) - Conds:RS_79._col0=RS_63._col0(Inner),Output:["_col1","_col2"] + Merge Join Operator [MERGEJOIN_59] (rows=15995224 width=115) + Conds:RS_71._col0=RS_63._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_63] PartitionCols:_col0 - Select Operator [SEL_62] (rows=8116 width=1119) + Select Operator [SEL_62] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_61] (rows=8116 width=1119) + Filter Operator [FIL_61] (rows=8116 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_79] + SHUFFLE [RS_71] PartitionCols:_col0 - Select Operator [SEL_78] (rows=144002668 width=135) + Select Operator [SEL_70] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_77] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_10_d1_d_date_sk_min) AND DynamicValue(RS_10_d1_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_d1_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_net_paid"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_76] - Group By Operator [GBY_75] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_74] - Group By Operator [GBY_73] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_72] (rows=462000 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_70] + Filter Operator [FIL_69] (rows=143966864 width=119) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_10_d1_d_date_sk_min) AND DynamicValue(RS_10_d1_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_10_d1_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_0] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_net_paid"] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_68] Group By Operator [GBY_67] (rows=1 width=12) @@ -145,7 +133,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_66] Group By Operator [GBY_65] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_64] (rows=8116 width=1119) + Select Operator [SEL_64] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_62] diff --git a/ql/src/test/results/clientpositive/perf/tez/query87.q.out b/ql/src/test/results/clientpositive/perf/tez/query87.q.out index 1b9256d53e..fd9bca2130 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query87.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query87.q.out @@ -43,21 +43,19 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE) -Map 23 <- Reducer 15 (BROADCAST_EDGE), Reducer 22 (BROADCAST_EDGE) -Map 24 <- Reducer 19 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE) +Map 21 <- Reducer 15 (BROADCAST_EDGE) +Map 22 <- Reducer 19 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 10 (SIMPLE_EDGE), Map 23 (SIMPLE_EDGE) +Reducer 12 <- Map 10 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) Reducer 13 <- Map 20 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 15 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 10 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) +Reducer 16 <- Map 10 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) Reducer 17 <- Map 20 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) Reducer 18 <- Reducer 17 (SIMPLE_EDGE), Union 7 (CONTAINS) Reducer 19 <- Map 10 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 20 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 20 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) @@ -69,214 +67,203 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_280] - Group By Operator [GBY_279] (rows=1 width=24) + File Output Operator [FS_272] + Group By Operator [GBY_271] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_278] - Group By Operator [GBY_277] (rows=1 width=24) + PARTITION_ONLY_SHUFFLE [RS_270] + Group By Operator [GBY_269] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_276] (rows=4537552 width=129) - Filter Operator [FIL_275] (rows=4537552 width=129) + Select Operator [SEL_268] (rows=5166409 width=16) + Filter Operator [FIL_267] (rows=5166409 width=16) predicate:(((_col3 * 2) = _col4) and (_col3 > 0L)) - Select Operator [SEL_274] (rows=27225312 width=129) + Select Operator [SEL_266] (rows=30998455 width=16) Output:["_col3","_col4"] - Group By Operator [GBY_273] (rows=27225312 width=129) + Group By Operator [GBY_265] (rows=30998455 width=290) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 7 [SIMPLE_EDGE] <-Reducer 18 [CONTAINS] vectorized - Reduce Output Operator [RS_306] + Reduce Output Operator [RS_296] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_305] (rows=54450625 width=129) + Group By Operator [GBY_295] (rows=30998455 width=290) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","sum(_col4)"],keys:_col0, _col1, _col2 - Select Operator [SEL_304] (rows=54450625 width=129) + Select Operator [SEL_294] (rows=30998455 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Select Operator [SEL_303] (rows=43560808 width=135) + Select Operator [SEL_293] (rows=15991238 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_302] (rows=43560808 width=135) + Group By Operator [GBY_292] (rows=15991238 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_301] (rows=87121617 width=135) + Select Operator [SEL_291] (rows=15991238 width=274) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_300] (rows=87121617 width=135) + Group By Operator [GBY_290] (rows=15991238 width=274) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_80] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_79] (rows=174243235 width=135) + Group By Operator [GBY_79] (rows=15991238 width=274) Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_192] (rows=174243235 width=135) - Conds:RS_75._col1=RS_248._col0(Inner),Output:["_col3","_col6","_col7"] + Merge Join Operator [MERGEJOIN_192] (rows=15991238 width=274) + Conds:RS_75._col1=RS_249._col0(Inner),Output:["_col3","_col6","_col7"] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_248] + SHUFFLE [RS_249] PartitionCols:_col0 - Select Operator [SEL_243] (rows=80000000 width=860) + Select Operator [SEL_246] (rows=80000000 width=184) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_242] (rows=80000000 width=860) + Filter Operator [FIL_245] (rows=80000000 width=184) predicate:c_customer_sk is not null - TableScan [TS_6] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name"] + TableScan [TS_6] (rows=80000000 width=184) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_75] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_191] (rows=158402938 width=135) - Conds:RS_299._col0=RS_232._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_191] (rows=15991238 width=97) + Conds:RS_289._col0=RS_232._col0(Inner),Output:["_col1","_col3"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_232] PartitionCols:_col0 - Select Operator [SEL_227] (rows=8116 width=1119) + Select Operator [SEL_227] (rows=8116 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_226] (rows=8116 width=1119) + Filter Operator [FIL_226] (rows=8116 width=102) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_month_seq"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_299] + TableScan [TS_3] (rows=73049 width=102) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_month_seq"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_289] PartitionCols:_col0 - Select Operator [SEL_298] (rows=144002668 width=135) + Select Operator [SEL_288] (rows=143930993 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_297] (rows=144002668 width=135) + Filter Operator [FIL_287] (rows=143930993 width=7) predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_73_date_dim_d_date_sk_min) AND DynamicValue(RS_73_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_73_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_63] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + TableScan [TS_63] (rows=144002668 width=7) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_296] - Group By Operator [GBY_295] (rows=1 width=12) + BROADCAST [RS_286] + Group By Operator [GBY_285] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_239] Group By Operator [GBY_236] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_233] (rows=8116 width=1119) + Select Operator [SEL_233] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_227] <-Reducer 6 [CONTAINS] vectorized - Reduce Output Operator [RS_272] + Reduce Output Operator [RS_264] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_271] (rows=54450625 width=129) + Group By Operator [GBY_263] (rows=30998455 width=290) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","sum(_col4)"],keys:_col0, _col1, _col2 - Select Operator [SEL_270] (rows=54450625 width=129) + Select Operator [SEL_262] (rows=30998455 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Select Operator [SEL_269] (rows=10889817 width=103) + Select Operator [SEL_261] (rows=15007217 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_268] (rows=10889817 width=103) + Group By Operator [GBY_260] (rows=15007217 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_267] (rows=21779634 width=103) + Select Operator [SEL_259] (rows=15007217 width=290) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_266] (rows=21779634 width=103) + Filter Operator [FIL_258] (rows=15007217 width=290) predicate:(((_col3 * 2) = _col4) and (_col3 > 0L)) - Group By Operator [GBY_265] (rows=130677808 width=103) + Group By Operator [GBY_257] (rows=90043306 width=290) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 5 [SIMPLE_EDGE] <-Reducer 14 [CONTAINS] vectorized - Reduce Output Operator [RS_294] + Reduce Output Operator [RS_284] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_293] (rows=261355616 width=103) + Group By Operator [GBY_283] (rows=90043306 width=290) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","sum(_col4)"],keys:_col0, _col1, _col2 - Select Operator [SEL_292] (rows=261355616 width=103) + Select Operator [SEL_282] (rows=90043306 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Select Operator [SEL_291] (rows=87116929 width=135) + Select Operator [SEL_281] (rows=31677591 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_290] (rows=87116929 width=135) + Group By Operator [GBY_280] (rows=31677591 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_289] (rows=174233858 width=135) + Select Operator [SEL_279] (rows=31677591 width=274) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_288] (rows=174233858 width=135) + Group By Operator [GBY_278] (rows=31677591 width=274) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_41] (rows=348467716 width=135) + Group By Operator [GBY_41] (rows=31677591 width=274) Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_190] (rows=348467716 width=135) - Conds:RS_37._col1=RS_246._col0(Inner),Output:["_col3","_col6","_col7"] + Merge Join Operator [MERGEJOIN_190] (rows=31677591 width=274) + Conds:RS_37._col1=RS_248._col0(Inner),Output:["_col3","_col6","_col7"] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_246] + SHUFFLE [RS_248] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_243] + Please refer to the previous Select Operator [SEL_246] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_189] (rows=316788826 width=135) - Conds:RS_287._col0=RS_230._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_189] (rows=31677591 width=97) + Conds:RS_277._col0=RS_230._col0(Inner),Output:["_col1","_col3"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_230] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_227] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_287] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_277] PartitionCols:_col0 - Select Operator [SEL_286] (rows=287989836 width=135) + Select Operator [SEL_276] (rows=285117831 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_285] (rows=287989836 width=135) - predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_38_customer_c_customer_sk_min) AND DynamicValue(RS_38_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_38_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_25] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] + Filter Operator [FIL_275] (rows=285117831 width=7) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_25] (rows=287989836 width=7) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_282] - Group By Operator [GBY_281] (rows=1 width=12) + BROADCAST [RS_274] + Group By Operator [GBY_273] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_238] Group By Operator [GBY_235] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_231] (rows=8116 width=1119) + Select Operator [SEL_231] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_227] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_284] - Group By Operator [GBY_283] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_252] - Group By Operator [GBY_250] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_247] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_243] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_264] + Reduce Output Operator [RS_256] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_263] (rows=261355616 width=103) + Group By Operator [GBY_255] (rows=90043306 width=290) Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","sum(_col4)"],keys:_col0, _col1, _col2 - Select Operator [SEL_262] (rows=261355616 width=103) + Select Operator [SEL_254] (rows=90043306 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Select Operator [SEL_261] (rows=174238687 width=88) + Select Operator [SEL_253] (rows=58365715 width=290) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_260] (rows=174238687 width=88) + Group By Operator [GBY_252] (rows=58365715 width=282) Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_259] (rows=348477374 width=88) + Select Operator [SEL_251] (rows=58365715 width=274) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_258] (rows=348477374 width=88) + Group By Operator [GBY_250] (rows=58365715 width=274) Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=58365715 width=274) Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_188] (rows=696954748 width=88) - Conds:RS_12._col1=RS_244._col0(Inner),Output:["_col3","_col6","_col7"] + Merge Join Operator [MERGEJOIN_188] (rows=58365715 width=274) + Conds:RS_12._col1=RS_247._col0(Inner),Output:["_col3","_col6","_col7"] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_244] + SHUFFLE [RS_247] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_243] + Please refer to the previous Select Operator [SEL_246] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_187] (rows=633595212 width=88) - Conds:RS_257._col0=RS_228._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_187] (rows=58365715 width=96) + Conds:RS_244._col0=RS_228._col0(Inner),Output:["_col1","_col3"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_228] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_227] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_257] + SHUFFLE [RS_244] PartitionCols:_col0 - Select Operator [SEL_256] (rows=575995635 width=88) + Select Operator [SEL_243] (rows=525327388 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_255] (rows=575995635 width=88) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_13_customer_c_customer_sk_min) AND DynamicValue(RS_13_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_13_customer_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] + Filter Operator [FIL_242] (rows=525327388 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_0] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_241] Group By Operator [GBY_240] (rows=1 width=12) @@ -285,18 +272,7 @@ Stage-0 SHUFFLE [RS_237] Group By Operator [GBY_234] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_229] (rows=8116 width=1119) + Select Operator [SEL_229] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_227] - <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_254] - Group By Operator [GBY_253] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] - <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_251] - Group By Operator [GBY_249] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] - Select Operator [SEL_245] (rows=80000000 width=860) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_243] diff --git a/ql/src/test/results/clientpositive/perf/tez/query88.q.out b/ql/src/test/results/clientpositive/perf/tez/query88.q.out index 59944e07ad..1b0947346e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query88.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query88.q.out @@ -258,9 +258,9 @@ Stage-0 Stage-1 Reducer 6 File Output Operator [FS_218] - Select Operator [SEL_217] (rows=1 width=65) + Select Operator [SEL_217] (rows=1 width=64) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_587] (rows=1 width=65) + Merge Join Operator [MERGEJOIN_587] (rows=1 width=64) Conds:(Inner),(Inner),(Inner),(Inner),(Inner),(Inner),(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_725] @@ -270,54 +270,54 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_49] Group By Operator [GBY_48] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_568] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_568] (rows=1806751 width=8) Conds:RS_44._col2=RS_678._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_678] PartitionCols:_col0 - Select Operator [SEL_675] (rows=852 width=1910) + Select Operator [SEL_675] (rows=155 width=91) Output:["_col0"] - Filter Operator [FIL_674] (rows=852 width=1910) + Filter Operator [FIL_674] (rows=155 width=92) predicate:((s_store_name = 'ese') and s_store_sk is not null) - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name"] + TableScan [TS_9] (rows=1704 width=92) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_567] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_567] (rows=2460956 width=0) Conds:RS_41._col1=RS_642._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_642] PartitionCols:_col0 - Select Operator [SEL_639] (rows=3600 width=107) + Select Operator [SEL_639] (rows=1091 width=12) Output:["_col0"] - Filter Operator [FIL_638] (rows=3600 width=107) + Filter Operator [FIL_638] (rows=1091 width=12) predicate:((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) - TableScan [TS_6] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] + TableScan [TS_6] (rows=7200 width=12) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_566] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_566] (rows=16240953 width=0) Conds:RS_723._col0=RS_606._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_606] PartitionCols:_col0 - Select Operator [SEL_597] (rows=14400 width=471) + Select Operator [SEL_597] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_589] (rows=14400 width=471) + Filter Operator [FIL_589] (rows=1515 width=12) predicate:((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) - TableScan [TS_3] (rows=86400 width=471) - default@time_dim,time_dim,Tbl:COMPLETE,Col:NONE,Output:["t_time_sk","t_hour","t_minute"] + TableScan [TS_3] (rows=86400 width=12) + default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute"] <-Map 62 [SIMPLE_EDGE] vectorized SHUFFLE [RS_723] PartitionCols:_col0 - Select Operator [SEL_722] (rows=575995635 width=88) + Select Operator [SEL_722] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_721] (rows=575995635 width=88) + Filter Operator [FIL_721] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_42_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_42_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_42_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_39_time_dim_t_time_sk_min) AND DynamicValue(RS_39_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_39_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_45_store_s_store_sk_min) AND DynamicValue(RS_45_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_45_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_26] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_26] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_716] Group By Operator [GBY_715] (rows=1 width=12) @@ -326,7 +326,7 @@ Stage-0 SHUFFLE [RS_629] Group By Operator [GBY_621] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_607] (rows=14400 width=471) + Select Operator [SEL_607] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_597] <-Reducer 46 [BROADCAST_EDGE] vectorized @@ -337,7 +337,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_665] Group By Operator [GBY_657] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_643] (rows=3600 width=107) + Select Operator [SEL_643] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 55 [BROADCAST_EDGE] vectorized @@ -348,7 +348,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_701] Group By Operator [GBY_693] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_679] (rows=852 width=1910) + Select Operator [SEL_679] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 17 [CUSTOM_SIMPLE_EDGE] vectorized @@ -359,7 +359,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_75] Group By Operator [GBY_74] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_571] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_571] (rows=1806751 width=8) Conds:RS_70._col2=RS_680._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_680] @@ -368,7 +368,7 @@ Stage-0 <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_70] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_570] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_570] (rows=2460956 width=0) Conds:RS_67._col1=RS_644._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_644] @@ -377,25 +377,25 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_569] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_569] (rows=16240953 width=0) Conds:RS_734._col0=RS_608._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_608] PartitionCols:_col0 - Select Operator [SEL_598] (rows=14400 width=471) + Select Operator [SEL_598] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_590] (rows=14400 width=471) + Filter Operator [FIL_590] (rows=1515 width=12) predicate:((t_hour = 11) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 63 [SIMPLE_EDGE] vectorized SHUFFLE [RS_734] PartitionCols:_col0 - Select Operator [SEL_733] (rows=575995635 width=88) + Select Operator [SEL_733] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_732] (rows=575995635 width=88) + Filter Operator [FIL_732] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_68_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_68_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_68_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_65_time_dim_t_time_sk_min) AND DynamicValue(RS_65_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_65_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_71_store_s_store_sk_min) AND DynamicValue(RS_71_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_71_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_52] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_52] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 18 [BROADCAST_EDGE] vectorized BROADCAST [RS_727] Group By Operator [GBY_726] (rows=1 width=12) @@ -404,7 +404,7 @@ Stage-0 SHUFFLE [RS_630] Group By Operator [GBY_622] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_609] (rows=14400 width=471) + Select Operator [SEL_609] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_598] <-Reducer 47 [BROADCAST_EDGE] vectorized @@ -415,7 +415,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_666] Group By Operator [GBY_658] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_645] (rows=3600 width=107) + Select Operator [SEL_645] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 56 [BROADCAST_EDGE] vectorized @@ -426,7 +426,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_702] Group By Operator [GBY_694] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_681] (rows=852 width=1910) + Select Operator [SEL_681] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 22 [CUSTOM_SIMPLE_EDGE] vectorized @@ -437,7 +437,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_101] Group By Operator [GBY_100] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_574] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_574] (rows=1806751 width=8) Conds:RS_96._col2=RS_682._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_682] @@ -446,7 +446,7 @@ Stage-0 <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_96] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_573] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_573] (rows=2460956 width=0) Conds:RS_93._col1=RS_646._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_646] @@ -455,25 +455,25 @@ Stage-0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_572] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_572] (rows=16240953 width=0) Conds:RS_745._col0=RS_610._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_610] PartitionCols:_col0 - Select Operator [SEL_599] (rows=14400 width=471) + Select Operator [SEL_599] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_591] (rows=14400 width=471) + Filter Operator [FIL_591] (rows=1515 width=12) predicate:((t_hour = 11) and (t_minute < 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 64 [SIMPLE_EDGE] vectorized SHUFFLE [RS_745] PartitionCols:_col0 - Select Operator [SEL_744] (rows=575995635 width=88) + Select Operator [SEL_744] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_743] (rows=575995635 width=88) + Filter Operator [FIL_743] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_94_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_94_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_94_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_91_time_dim_t_time_sk_min) AND DynamicValue(RS_91_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_91_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_97_store_s_store_sk_min) AND DynamicValue(RS_97_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_97_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_78] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_78] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 23 [BROADCAST_EDGE] vectorized BROADCAST [RS_738] Group By Operator [GBY_737] (rows=1 width=12) @@ -482,7 +482,7 @@ Stage-0 SHUFFLE [RS_631] Group By Operator [GBY_623] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_611] (rows=14400 width=471) + Select Operator [SEL_611] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_599] <-Reducer 48 [BROADCAST_EDGE] vectorized @@ -493,7 +493,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_667] Group By Operator [GBY_659] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_647] (rows=3600 width=107) + Select Operator [SEL_647] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 57 [BROADCAST_EDGE] vectorized @@ -504,7 +504,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_703] Group By Operator [GBY_695] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_683] (rows=852 width=1910) + Select Operator [SEL_683] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized @@ -515,7 +515,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_127] Group By Operator [GBY_126] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_577] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_577] (rows=1806751 width=8) Conds:RS_122._col2=RS_684._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_684] @@ -524,7 +524,7 @@ Stage-0 <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_122] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_576] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_576] (rows=2460956 width=0) Conds:RS_119._col1=RS_648._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_648] @@ -533,25 +533,25 @@ Stage-0 <-Reducer 24 [SIMPLE_EDGE] SHUFFLE [RS_119] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_575] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_575] (rows=16240953 width=0) Conds:RS_756._col0=RS_612._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_612] PartitionCols:_col0 - Select Operator [SEL_600] (rows=14400 width=471) + Select Operator [SEL_600] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_592] (rows=14400 width=471) + Filter Operator [FIL_592] (rows=1515 width=12) predicate:((t_hour = 10) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 65 [SIMPLE_EDGE] vectorized SHUFFLE [RS_756] PartitionCols:_col0 - Select Operator [SEL_755] (rows=575995635 width=88) + Select Operator [SEL_755] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_754] (rows=575995635 width=88) + Filter Operator [FIL_754] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_120_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_120_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_120_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_117_time_dim_t_time_sk_min) AND DynamicValue(RS_117_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_117_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_123_store_s_store_sk_min) AND DynamicValue(RS_123_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_123_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_104] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_104] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 28 [BROADCAST_EDGE] vectorized BROADCAST [RS_749] Group By Operator [GBY_748] (rows=1 width=12) @@ -560,7 +560,7 @@ Stage-0 SHUFFLE [RS_632] Group By Operator [GBY_624] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_613] (rows=14400 width=471) + Select Operator [SEL_613] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_600] <-Reducer 49 [BROADCAST_EDGE] vectorized @@ -571,7 +571,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_668] Group By Operator [GBY_660] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_649] (rows=3600 width=107) + Select Operator [SEL_649] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 58 [BROADCAST_EDGE] vectorized @@ -582,7 +582,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_704] Group By Operator [GBY_696] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_685] (rows=852 width=1910) + Select Operator [SEL_685] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized @@ -593,7 +593,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_153] Group By Operator [GBY_152] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_580] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_580] (rows=1806751 width=8) Conds:RS_148._col2=RS_686._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_686] @@ -602,7 +602,7 @@ Stage-0 <-Reducer 30 [SIMPLE_EDGE] SHUFFLE [RS_148] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_579] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_579] (rows=2460956 width=0) Conds:RS_145._col1=RS_650._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_650] @@ -611,25 +611,25 @@ Stage-0 <-Reducer 29 [SIMPLE_EDGE] SHUFFLE [RS_145] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_578] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_578] (rows=16240953 width=0) Conds:RS_767._col0=RS_614._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_614] PartitionCols:_col0 - Select Operator [SEL_601] (rows=14400 width=471) + Select Operator [SEL_601] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_593] (rows=14400 width=471) + Filter Operator [FIL_593] (rows=1515 width=12) predicate:((t_hour = 10) and (t_minute < 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 66 [SIMPLE_EDGE] vectorized SHUFFLE [RS_767] PartitionCols:_col0 - Select Operator [SEL_766] (rows=575995635 width=88) + Select Operator [SEL_766] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_765] (rows=575995635 width=88) + Filter Operator [FIL_765] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_146_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_146_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_146_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_143_time_dim_t_time_sk_min) AND DynamicValue(RS_143_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_143_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_149_store_s_store_sk_min) AND DynamicValue(RS_149_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_149_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_130] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_130] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 33 [BROADCAST_EDGE] vectorized BROADCAST [RS_760] Group By Operator [GBY_759] (rows=1 width=12) @@ -638,7 +638,7 @@ Stage-0 SHUFFLE [RS_633] Group By Operator [GBY_625] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_615] (rows=14400 width=471) + Select Operator [SEL_615] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_601] <-Reducer 50 [BROADCAST_EDGE] vectorized @@ -649,7 +649,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_669] Group By Operator [GBY_661] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_651] (rows=3600 width=107) + Select Operator [SEL_651] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 59 [BROADCAST_EDGE] vectorized @@ -660,7 +660,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_705] Group By Operator [GBY_697] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_687] (rows=852 width=1910) + Select Operator [SEL_687] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 37 [CUSTOM_SIMPLE_EDGE] vectorized @@ -671,7 +671,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_179] Group By Operator [GBY_178] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_583] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_583] (rows=1806751 width=8) Conds:RS_174._col2=RS_688._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_688] @@ -680,7 +680,7 @@ Stage-0 <-Reducer 35 [SIMPLE_EDGE] SHUFFLE [RS_174] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_582] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_582] (rows=2460956 width=0) Conds:RS_171._col1=RS_652._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_652] @@ -689,25 +689,25 @@ Stage-0 <-Reducer 34 [SIMPLE_EDGE] SHUFFLE [RS_171] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_581] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_581] (rows=16240953 width=0) Conds:RS_778._col0=RS_616._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_616] PartitionCols:_col0 - Select Operator [SEL_602] (rows=14400 width=471) + Select Operator [SEL_602] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_594] (rows=14400 width=471) + Filter Operator [FIL_594] (rows=1515 width=12) predicate:((t_hour = 9) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 67 [SIMPLE_EDGE] vectorized SHUFFLE [RS_778] PartitionCols:_col0 - Select Operator [SEL_777] (rows=575995635 width=88) + Select Operator [SEL_777] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_776] (rows=575995635 width=88) + Filter Operator [FIL_776] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_172_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_172_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_172_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_169_time_dim_t_time_sk_min) AND DynamicValue(RS_169_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_169_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_175_store_s_store_sk_min) AND DynamicValue(RS_175_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_175_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_156] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_156] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 38 [BROADCAST_EDGE] vectorized BROADCAST [RS_771] Group By Operator [GBY_770] (rows=1 width=12) @@ -716,7 +716,7 @@ Stage-0 SHUFFLE [RS_634] Group By Operator [GBY_626] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_617] (rows=14400 width=471) + Select Operator [SEL_617] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_602] <-Reducer 51 [BROADCAST_EDGE] vectorized @@ -727,7 +727,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_670] Group By Operator [GBY_662] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_653] (rows=3600 width=107) + Select Operator [SEL_653] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 60 [BROADCAST_EDGE] vectorized @@ -738,7 +738,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_706] Group By Operator [GBY_698] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_689] (rows=852 width=1910) + Select Operator [SEL_689] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 42 [CUSTOM_SIMPLE_EDGE] vectorized @@ -749,7 +749,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_205] Group By Operator [GBY_204] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_586] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_586] (rows=1806751 width=8) Conds:RS_200._col2=RS_690._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_690] @@ -758,7 +758,7 @@ Stage-0 <-Reducer 40 [SIMPLE_EDGE] SHUFFLE [RS_200] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_585] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_585] (rows=2460956 width=0) Conds:RS_197._col1=RS_654._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_654] @@ -767,25 +767,25 @@ Stage-0 <-Reducer 39 [SIMPLE_EDGE] SHUFFLE [RS_197] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_584] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_584] (rows=16240953 width=0) Conds:RS_789._col0=RS_618._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_618] PartitionCols:_col0 - Select Operator [SEL_603] (rows=14400 width=471) + Select Operator [SEL_603] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_595] (rows=14400 width=471) + Filter Operator [FIL_595] (rows=1515 width=12) predicate:((t_hour = 9) and (t_minute < 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 68 [SIMPLE_EDGE] vectorized SHUFFLE [RS_789] PartitionCols:_col0 - Select Operator [SEL_788] (rows=575995635 width=88) + Select Operator [SEL_788] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_787] (rows=575995635 width=88) + Filter Operator [FIL_787] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_198_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_198_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_198_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_195_time_dim_t_time_sk_min) AND DynamicValue(RS_195_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_195_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_201_store_s_store_sk_min) AND DynamicValue(RS_201_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_201_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_182] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_182] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 43 [BROADCAST_EDGE] vectorized BROADCAST [RS_782] Group By Operator [GBY_781] (rows=1 width=12) @@ -794,7 +794,7 @@ Stage-0 SHUFFLE [RS_635] Group By Operator [GBY_627] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_619] (rows=14400 width=471) + Select Operator [SEL_619] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_603] <-Reducer 52 [BROADCAST_EDGE] vectorized @@ -805,7 +805,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_671] Group By Operator [GBY_663] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_655] (rows=3600 width=107) + Select Operator [SEL_655] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 61 [BROADCAST_EDGE] vectorized @@ -816,7 +816,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_707] Group By Operator [GBY_699] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_691] (rows=852 width=1910) + Select Operator [SEL_691] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized @@ -827,7 +827,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_565] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_565] (rows=1806751 width=8) Conds:RS_18._col2=RS_676._col0(Inner) <-Map 53 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_676] @@ -836,7 +836,7 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_564] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_564] (rows=2460956 width=0) Conds:RS_15._col1=RS_640._col0(Inner),Output:["_col2"] <-Map 44 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_640] @@ -845,25 +845,25 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_563] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_563] (rows=16240953 width=0) Conds:RS_712._col0=RS_604._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_604] PartitionCols:_col0 - Select Operator [SEL_596] (rows=14400 width=471) + Select Operator [SEL_596] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_588] (rows=14400 width=471) + Filter Operator [FIL_588] (rows=1515 width=12) predicate:((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_712] PartitionCols:_col0 - Select Operator [SEL_711] (rows=575995635 width=88) + Select Operator [SEL_711] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_710] (rows=575995635 width=88) + Filter Operator [FIL_710] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_16_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_16_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_16_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_13_time_dim_t_time_sk_min) AND DynamicValue(RS_13_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_13_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_0] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 45 [BROADCAST_EDGE] vectorized BROADCAST [RS_673] Group By Operator [GBY_672] (rows=1 width=12) @@ -872,7 +872,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_664] Group By Operator [GBY_656] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_641] (rows=3600 width=107) + Select Operator [SEL_641] (rows=1091 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_639] <-Reducer 54 [BROADCAST_EDGE] vectorized @@ -883,7 +883,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_700] Group By Operator [GBY_692] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_677] (rows=852 width=1910) + Select Operator [SEL_677] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_675] <-Reducer 8 [BROADCAST_EDGE] vectorized @@ -894,7 +894,7 @@ Stage-0 SHUFFLE [RS_628] Group By Operator [GBY_620] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_605] (rows=14400 width=471) + Select Operator [SEL_605] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_596] diff --git a/ql/src/test/results/clientpositive/perf/tez/query89.q.out b/ql/src/test/results/clientpositive/perf/tez/query89.q.out index 265eceab21..a7b6fd4f10 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query89.q.out @@ -55,9 +55,8 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) @@ -71,81 +70,81 @@ Stage-0 limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_122] - Limit [LIM_121] (rows=100 width=88) + File Output Operator [FS_117] + Limit [LIM_116] (rows=100 width=801) Number of rows:100 - Select Operator [SEL_120] (rows=191662559 width=88) + Select Operator [SEL_115] (rows=27081522 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_119] - Select Operator [SEL_118] (rows=191662559 width=88) + SHUFFLE [RS_114] + Select Operator [SEL_113] (rows=27081522 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_117] (rows=191662559 width=88) + Filter Operator [FIL_112] (rows=27081522 width=689) predicate:CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END - Select Operator [SEL_116] (rows=383325119 width=88) + Select Operator [SEL_111] (rows=54163045 width=577) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_115] (rows=383325119 width=88) + PTF Operator [PTF_110] (rows=54163045 width=577) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS FIRST, _col1 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST","partition by:":"_col3, _col1, _col4, _col5"}] - Select Operator [SEL_114] (rows=383325119 width=88) + Select Operator [SEL_109] (rows=54163045 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_113] + SHUFFLE [RS_108] PartitionCols:_col3, _col1, _col4, _col5 - Group By Operator [GBY_112] (rows=383325119 width=88) + Group By Operator [GBY_107] (rows=54163045 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_22] (rows=766650239 width=88) + Group By Operator [GBY_22] (rows=54163045 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col6, _col8, _col9, _col10, _col12, _col13 - Merge Join Operator [MERGEJOIN_84] (rows=766650239 width=88) - Conds:RS_18._col2=RS_103._col0(Inner),Output:["_col3","_col6","_col8","_col9","_col10","_col12","_col13"] + Merge Join Operator [MERGEJOIN_84] (rows=54163045 width=528) + Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col6","_col8","_col9","_col10","_col12","_col13"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] + SHUFFLE [RS_106] PartitionCols:_col0 - Select Operator [SEL_102] (rows=1704 width=1910) + Select Operator [SEL_105] (rows=1704 width=183) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_101] (rows=1704 width=1910) + Filter Operator [FIL_104] (rows=1704 width=183) predicate:s_store_sk is not null - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_company_name"] + TableScan [TS_9] (rows=1704 width=183) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_company_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_83] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_83] (rows=54163045 width=351) Conds:RS_15._col1=RS_95._col0(Inner),Output:["_col2","_col3","_col6","_col8","_col9","_col10"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=462000 width=1436) + Select Operator [SEL_94] (rows=13860 width=286) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_93] (rows=462000 width=1436) + Filter Operator [FIL_93] (rows=13860 width=286) predicate:((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category"] + TableScan [TS_6] (rows=462000 width=286) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_82] (rows=633595212 width=88) - Conds:RS_111._col0=RS_87._col0(Inner),Output:["_col1","_col2","_col3","_col6"] + Merge Join Operator [MERGEJOIN_82] (rows=187574154 width=109) + Conds:RS_103._col0=RS_87._col0(Inner),Output:["_col1","_col2","_col3","_col6"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=36524 width=1119) + Select Operator [SEL_86] (rows=652 width=12) Output:["_col0","_col2"] - Filter Operator [FIL_85] (rows=36524 width=1119) + Filter Operator [FIL_85] (rows=652 width=12) predicate:((d_year = 2000) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_3] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] + SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_110] (rows=575995635 width=88) + Select Operator [SEL_102] (rows=525329897 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_109] (rows=575995635 width=88) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_16_item_i_item_sk_min) AND DynamicValue(RS_16_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_16_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + Filter Operator [FIL_101] (rows=525329897 width=118) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_16_item_i_item_sk_min) AND DynamicValue(RS_16_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_16_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_100] Group By Operator [GBY_99] (rows=1 width=12) @@ -154,20 +153,9 @@ Stage-0 SHUFFLE [RS_98] Group By Operator [GBY_97] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_96] (rows=462000 width=1436) + Select Operator [SEL_96] (rows=13860 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_94] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_108] - Group By Operator [GBY_107] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_104] (rows=1704 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_92] Group By Operator [GBY_91] (rows=1 width=12) @@ -176,7 +164,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_90] Group By Operator [GBY_89] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_88] (rows=36524 width=1119) + Select Operator [SEL_88] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_86] diff --git a/ql/src/test/results/clientpositive/perf/tez/query9.q.out b/ql/src/test/results/clientpositive/perf/tez/query9.q.out index 611daa8b88..f109afd04b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query9.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query9.q.out @@ -151,37 +151,37 @@ Stage-0 Stage-1 Reducer 16 File Output Operator [FS_154] - Select Operator [SEL_153] (rows=36 width=1455) + Select Operator [SEL_153] (rows=2 width=560) Output:["_col0","_col1","_col2","_col3","_col4"] - Merge Join Operator [MERGEJOIN_185] (rows=36 width=1455) + Merge Join Operator [MERGEJOIN_185] (rows=2 width=1160) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_150] - Merge Join Operator [MERGEJOIN_184] (rows=36 width=1334) + Merge Join Operator [MERGEJOIN_184] (rows=2 width=1048) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 14 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_147] - Merge Join Operator [MERGEJOIN_183] (rows=36 width=1213) + Merge Join Operator [MERGEJOIN_183] (rows=2 width=936) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Reducer 13 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_144] - Merge Join Operator [MERGEJOIN_182] (rows=36 width=1204) + Merge Join Operator [MERGEJOIN_182] (rows=2 width=928) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_141] - Merge Join Operator [MERGEJOIN_181] (rows=36 width=1083) + Merge Join Operator [MERGEJOIN_181] (rows=2 width=816) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_138] - Merge Join Operator [MERGEJOIN_180] (rows=36 width=962) + Merge Join Operator [MERGEJOIN_180] (rows=2 width=704) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 10 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_135] - Merge Join Operator [MERGEJOIN_179] (rows=36 width=953) + Merge Join Operator [MERGEJOIN_179] (rows=2 width=696) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_272] - Select Operator [SEL_271] (rows=1 width=120) + Select Operator [SEL_271] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_270] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -189,19 +189,19 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_253] Group By Operator [GBY_248] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_243] (rows=63999515 width=88) + Select Operator [SEL_243] (rows=63999515 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_238] (rows=63999515 width=88) + Filter Operator [FIL_238] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_80] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_net_paid_inc_tax"] + TableScan [TS_80] (rows=575995635 width=110) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity","ss_net_paid_inc_tax"] <-Reducer 9 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_132] - Merge Join Operator [MERGEJOIN_178] (rows=36 width=832) + Merge Join Operator [MERGEJOIN_178] (rows=2 width=584) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_269] - Select Operator [SEL_268] (rows=1 width=120) + Select Operator [SEL_268] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_267] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -209,15 +209,15 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_230] Group By Operator [GBY_225] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_220] (rows=63999515 width=88) + Select Operator [SEL_220] (rows=63999515 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_215] (rows=63999515 width=88) + Filter Operator [FIL_215] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_73] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_ext_list_price"] + TableScan [TS_73] (rows=575995635 width=110) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity","ss_ext_list_price"] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_129] - Merge Join Operator [MERGEJOIN_177] (rows=36 width=711) + Merge Join Operator [MERGEJOIN_177] (rows=2 width=472) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 22 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_266] @@ -227,18 +227,18 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_208] Group By Operator [GBY_203] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_198] (rows=63999515 width=88) - Filter Operator [FIL_193] (rows=63999515 width=88) + Select Operator [SEL_198] (rows=63999515 width=3) + Filter Operator [FIL_193] (rows=63999515 width=3) predicate:ss_quantity BETWEEN 41 AND 60 - TableScan [TS_66] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity"] + TableScan [TS_66] (rows=575995635 width=3) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_quantity"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_126] - Merge Join Operator [MERGEJOIN_176] (rows=36 width=702) + Merge Join Operator [MERGEJOIN_176] (rows=2 width=464) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 33 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_264] - Select Operator [SEL_263] (rows=1 width=120) + Select Operator [SEL_263] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_262] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -246,18 +246,18 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_252] Group By Operator [GBY_247] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_242] (rows=63999515 width=88) + Select Operator [SEL_242] (rows=63999515 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_237] (rows=63999515 width=88) + Filter Operator [FIL_237] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 21 AND 40 Please refer to the previous TableScan [TS_80] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_123] - Merge Join Operator [MERGEJOIN_175] (rows=36 width=581) + Merge Join Operator [MERGEJOIN_175] (rows=2 width=352) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4","_col5"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_261] - Select Operator [SEL_260] (rows=1 width=120) + Select Operator [SEL_260] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_259] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -265,14 +265,14 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_229] Group By Operator [GBY_224] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_219] (rows=63999515 width=88) + Select Operator [SEL_219] (rows=63999515 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_214] (rows=63999515 width=88) + Filter Operator [FIL_214] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 21 AND 40 Please refer to the previous TableScan [TS_73] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_120] - Merge Join Operator [MERGEJOIN_174] (rows=36 width=460) + Merge Join Operator [MERGEJOIN_174] (rows=2 width=240) Conds:(Left Outer),Output:["_col1","_col2","_col3","_col4"] <-Reducer 21 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_258] @@ -282,29 +282,29 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_207] Group By Operator [GBY_202] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_197] (rows=63999515 width=88) - Filter Operator [FIL_192] (rows=63999515 width=88) + Select Operator [SEL_197] (rows=63999515 width=3) + Filter Operator [FIL_192] (rows=63999515 width=3) predicate:ss_quantity BETWEEN 21 AND 40 Please refer to the previous TableScan [TS_66] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_117] - Merge Join Operator [MERGEJOIN_173] (rows=36 width=451) + Merge Join Operator [MERGEJOIN_173] (rows=2 width=232) Conds:(Left Outer),Output:["_col1","_col2","_col3"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_114] - Merge Join Operator [MERGEJOIN_172] (rows=36 width=330) + Merge Join Operator [MERGEJOIN_172] (rows=2 width=120) Conds:(Left Outer),Output:["_col1","_col2"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_111] - Merge Join Operator [MERGEJOIN_171] (rows=36 width=209) + Merge Join Operator [MERGEJOIN_171] (rows=2 width=8) Conds:(Left Outer),Output:["_col1"] <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_188] - Select Operator [SEL_187] (rows=36 width=200) - Filter Operator [FIL_186] (rows=36 width=200) + Select Operator [SEL_187] (rows=2 width=4) + Filter Operator [FIL_186] (rows=2 width=4) predicate:(r_reason_sk = 1) - TableScan [TS_0] (rows=72 width=200) - default@reason,reason,Tbl:COMPLETE,Col:NONE,Output:["r_reason_sk"] + TableScan [TS_0] (rows=72 width=4) + default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk"] <-Reducer 20 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_210] Group By Operator [GBY_209] (rows=1 width=8) @@ -313,13 +313,13 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_206] Group By Operator [GBY_201] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_196] (rows=63999515 width=88) - Filter Operator [FIL_191] (rows=63999515 width=88) + Select Operator [SEL_196] (rows=191998545 width=3) + Filter Operator [FIL_191] (rows=191998545 width=3) predicate:ss_quantity BETWEEN 1 AND 20 Please refer to the previous TableScan [TS_66] <-Reducer 26 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_233] - Select Operator [SEL_232] (rows=1 width=120) + Select Operator [SEL_232] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_231] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -327,14 +327,14 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_228] Group By Operator [GBY_223] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_218] (rows=63999515 width=88) + Select Operator [SEL_218] (rows=191998545 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_213] (rows=63999515 width=88) + Filter Operator [FIL_213] (rows=191998545 width=110) predicate:ss_quantity BETWEEN 1 AND 20 Please refer to the previous TableScan [TS_73] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_256] - Select Operator [SEL_255] (rows=1 width=120) + Select Operator [SEL_255] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_254] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -342,9 +342,9 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_251] Group By Operator [GBY_246] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_241] (rows=63999515 width=88) + Select Operator [SEL_241] (rows=191998545 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_236] (rows=63999515 width=88) + Filter Operator [FIL_236] (rows=191998545 width=110) predicate:ss_quantity BETWEEN 1 AND 20 Please refer to the previous TableScan [TS_80] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized @@ -355,13 +355,13 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_204] Group By Operator [GBY_199] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_194] (rows=63999515 width=88) - Filter Operator [FIL_189] (rows=63999515 width=88) + Select Operator [SEL_194] (rows=63999515 width=3) + Filter Operator [FIL_189] (rows=63999515 width=3) predicate:ss_quantity BETWEEN 61 AND 80 Please refer to the previous TableScan [TS_66] <-Reducer 24 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_277] - Select Operator [SEL_276] (rows=1 width=120) + Select Operator [SEL_276] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_275] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -369,14 +369,14 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_226] Group By Operator [GBY_221] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_216] (rows=63999515 width=88) + Select Operator [SEL_216] (rows=63999515 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_211] (rows=63999515 width=88) + Filter Operator [FIL_211] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 61 AND 80 Please refer to the previous TableScan [TS_73] <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_280] - Select Operator [SEL_279] (rows=1 width=120) + Select Operator [SEL_279] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_278] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -384,9 +384,9 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_249] Group By Operator [GBY_244] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_239] (rows=63999515 width=88) + Select Operator [SEL_239] (rows=63999515 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_234] (rows=63999515 width=88) + Filter Operator [FIL_234] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 61 AND 80 Please refer to the previous TableScan [TS_80] <-Reducer 19 [CUSTOM_SIMPLE_EDGE] vectorized @@ -397,13 +397,13 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_205] Group By Operator [GBY_200] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_195] (rows=63999515 width=88) - Filter Operator [FIL_190] (rows=63999515 width=88) + Select Operator [SEL_195] (rows=63999515 width=3) + Filter Operator [FIL_190] (rows=63999515 width=3) predicate:ss_quantity BETWEEN 81 AND 100 Please refer to the previous TableScan [TS_66] <-Reducer 25 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_285] - Select Operator [SEL_284] (rows=1 width=120) + Select Operator [SEL_284] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_283] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -411,14 +411,14 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_227] Group By Operator [GBY_222] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_ext_list_price)","count(ss_ext_list_price)"] - Select Operator [SEL_217] (rows=63999515 width=88) + Select Operator [SEL_217] (rows=63999515 width=110) Output:["ss_ext_list_price"] - Filter Operator [FIL_212] (rows=63999515 width=88) + Filter Operator [FIL_212] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 81 AND 100 Please refer to the previous TableScan [TS_73] <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_288] - Select Operator [SEL_287] (rows=1 width=120) + Select Operator [SEL_287] (rows=1 width=112) Output:["_col0"] Group By Operator [GBY_286] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] @@ -426,9 +426,9 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_250] Group By Operator [GBY_245] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(ss_net_paid_inc_tax)","count(ss_net_paid_inc_tax)"] - Select Operator [SEL_240] (rows=63999515 width=88) + Select Operator [SEL_240] (rows=63999515 width=110) Output:["ss_net_paid_inc_tax"] - Filter Operator [FIL_235] (rows=63999515 width=88) + Filter Operator [FIL_235] (rows=63999515 width=110) predicate:ss_quantity BETWEEN 81 AND 100 Please refer to the previous TableScan [TS_80] diff --git a/ql/src/test/results/clientpositive/perf/tez/query90.q.out b/ql/src/test/results/clientpositive/perf/tez/query90.q.out index ae5c596192..a8cef1227b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query90.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query90.q.out @@ -69,15 +69,15 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_209] - Limit [LIM_208] (rows=1 width=17) + Limit [LIM_208] (rows=1 width=112) Number of rows:100 - Select Operator [SEL_207] (rows=1 width=17) + Select Operator [SEL_207] (rows=1 width=112) Output:["_col0"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_56] - Select Operator [SEL_55] (rows=1 width=17) + Select Operator [SEL_55] (rows=1 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_152] (rows=1 width=17) + Merge Join Operator [MERGEJOIN_152] (rows=1 width=16) Conds:(Inner),Output:["_col0","_col1"] <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_206] @@ -87,54 +87,54 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_49] Group By Operator [GBY_48] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_151] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_151] (rows=161506 width=8) Conds:RS_44._col1=RS_183._col0(Inner) <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_183] PartitionCols:_col0 - Select Operator [SEL_180] (rows=3600 width=107) + Select Operator [SEL_180] (rows=655 width=8) Output:["_col0"] - Filter Operator [FIL_179] (rows=3600 width=107) + Filter Operator [FIL_179] (rows=655 width=8) predicate:((hd_dep_count = 8) and hd_demo_sk is not null) - TableScan [TS_9] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"] + TableScan [TS_9] (rows=7200 width=8) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_150] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_150] (rows=1775325 width=3) Conds:RS_41._col0=RS_171._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_168] (rows=9600 width=471) + Select Operator [SEL_168] (rows=9600 width=8) Output:["_col0"] - Filter Operator [FIL_166] (rows=9600 width=471) + Filter Operator [FIL_166] (rows=9600 width=8) predicate:(t_hour BETWEEN 14 AND 15 and t_time_sk is not null) - TableScan [TS_6] (rows=86400 width=471) - default@time_dim,time_dim,Tbl:COMPLETE,Col:NONE,Output:["t_time_sk","t_hour"] + TableScan [TS_6] (rows=86400 width=8) + default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_149] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_149] (rows=15977923 width=7) Conds:RS_204._col2=RS_157._col0(Inner),Output:["_col0","_col1"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_154] (rows=511 width=585) + Select Operator [SEL_154] (rows=511 width=7) Output:["_col0"] - Filter Operator [FIL_153] (rows=511 width=585) + Filter Operator [FIL_153] (rows=511 width=7) predicate:(wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) - TableScan [TS_3] (rows=4602 width=585) - default@web_page,web_page,Tbl:COMPLETE,Col:NONE,Output:["wp_web_page_sk","wp_char_count"] + TableScan [TS_3] (rows=4602 width=7) + default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk","wp_char_count"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_204] PartitionCols:_col2 - Select Operator [SEL_203] (rows=144002668 width=135) + Select Operator [SEL_203] (rows=143895111 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_202] (rows=144002668 width=135) + Filter Operator [FIL_202] (rows=143895111 width=11) predicate:((ws_ship_hdemo_sk BETWEEN DynamicValue(RS_45_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_45_household_demographics_hd_demo_sk_max) and in_bloom_filter(ws_ship_hdemo_sk, DynamicValue(RS_45_household_demographics_hd_demo_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_42_time_dim_t_time_sk_min) AND DynamicValue(RS_42_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_42_time_dim_t_time_sk_bloom_filter))) and (ws_web_page_sk BETWEEN DynamicValue(RS_39_web_page_wp_web_page_sk_min) AND DynamicValue(RS_39_web_page_wp_web_page_sk_max) and in_bloom_filter(ws_web_page_sk, DynamicValue(RS_39_web_page_wp_web_page_sk_bloom_filter))) and ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) - TableScan [TS_26] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_time_sk","ws_ship_hdemo_sk","ws_web_page_sk"] + TableScan [TS_26] (rows=144002668 width=11) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_time_sk","ws_ship_hdemo_sk","ws_web_page_sk"] <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_197] Group By Operator [GBY_196] (rows=1 width=12) @@ -143,7 +143,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_162] Group By Operator [GBY_160] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_158] (rows=511 width=585) + Select Operator [SEL_158] (rows=511 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_154] <-Reducer 17 [BROADCAST_EDGE] vectorized @@ -154,7 +154,7 @@ Stage-0 SHUFFLE [RS_176] Group By Operator [GBY_174] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_172] (rows=9600 width=471) + Select Operator [SEL_172] (rows=9600 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_168] <-Reducer 20 [BROADCAST_EDGE] vectorized @@ -165,7 +165,7 @@ Stage-0 SHUFFLE [RS_188] Group By Operator [GBY_186] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_184] (rows=3600 width=107) + Select Operator [SEL_184] (rows=655 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_180] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized @@ -176,7 +176,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_148] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_148] (rows=161506 width=8) Conds:RS_18._col1=RS_181._col0(Inner) <-Map 18 [SIMPLE_EDGE] vectorized SHUFFLE [RS_181] @@ -185,20 +185,20 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_147] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_147] (rows=1775325 width=3) Conds:RS_15._col0=RS_169._col0(Inner),Output:["_col1"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_169] PartitionCols:_col0 - Select Operator [SEL_167] (rows=9600 width=471) + Select Operator [SEL_167] (rows=9600 width=8) Output:["_col0"] - Filter Operator [FIL_165] (rows=9600 width=471) + Filter Operator [FIL_165] (rows=9600 width=8) predicate:(t_hour BETWEEN 6 AND 7 and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_146] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_146] (rows=15977923 width=7) Conds:RS_193._col2=RS_155._col0(Inner),Output:["_col0","_col1"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_155] @@ -207,12 +207,12 @@ Stage-0 <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_193] PartitionCols:_col2 - Select Operator [SEL_192] (rows=144002668 width=135) + Select Operator [SEL_192] (rows=143895111 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_191] (rows=144002668 width=135) + Filter Operator [FIL_191] (rows=143895111 width=11) predicate:((ws_ship_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ws_ship_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_16_time_dim_t_time_sk_min) AND DynamicValue(RS_16_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_16_time_dim_t_time_sk_bloom_filter))) and (ws_web_page_sk BETWEEN DynamicValue(RS_13_web_page_wp_web_page_sk_min) AND DynamicValue(RS_13_web_page_wp_web_page_sk_max) and in_bloom_filter(ws_web_page_sk, DynamicValue(RS_13_web_page_wp_web_page_sk_bloom_filter))) and ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_time_sk","ws_ship_hdemo_sk","ws_web_page_sk"] + TableScan [TS_0] (rows=144002668 width=11) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_time_sk","ws_ship_hdemo_sk","ws_web_page_sk"] <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_178] Group By Operator [GBY_177] (rows=1 width=12) @@ -221,7 +221,7 @@ Stage-0 SHUFFLE [RS_175] Group By Operator [GBY_173] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_170] (rows=9600 width=471) + Select Operator [SEL_170] (rows=9600 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_167] <-Reducer 19 [BROADCAST_EDGE] vectorized @@ -232,7 +232,7 @@ Stage-0 SHUFFLE [RS_187] Group By Operator [GBY_185] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_182] (rows=3600 width=107) + Select Operator [SEL_182] (rows=655 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_180] <-Reducer 9 [BROADCAST_EDGE] vectorized @@ -243,7 +243,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_161] Group By Operator [GBY_159] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_156] (rows=511 width=585) + Select Operator [SEL_156] (rows=511 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_154] diff --git a/ql/src/test/results/clientpositive/perf/tez/query91.q.out b/ql/src/test/results/clientpositive/perf/tez/query91.q.out index 7a64949c3f..9dfb877dad 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query91.q.out @@ -76,107 +76,107 @@ Stage-0 Stage-1 Reducer 7 vectorized File Output Operator [FS_170] - Select Operator [SEL_169] (rows=58564004 width=860) + Select Operator [SEL_169] (rows=1 width=406) Output:["_col0","_col1","_col2","_col3"] <-Reducer 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_168] - Select Operator [SEL_167] (rows=58564004 width=860) + Select Operator [SEL_167] (rows=1 width=518) Output:["_col0","_col1","_col2","_col4"] - Group By Operator [GBY_166] (rows=58564004 width=860) + Group By Operator [GBY_166] (rows=1 width=585) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_41] (rows=117128008 width=860) + Group By Operator [GBY_41] (rows=1 width=585) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col12)"],keys:_col5, _col6, _col17, _col18, _col19 - Merge Join Operator [MERGEJOIN_144] (rows=117128008 width=860) + Merge Join Operator [MERGEJOIN_144] (rows=10438 width=473) Conds:RS_37._col2=RS_165._col0(Inner),Output:["_col5","_col6","_col12","_col17","_col18","_col19"] <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_165] PartitionCols:_col0 - Select Operator [SEL_164] (rows=3600 width=107) + Select Operator [SEL_164] (rows=3600 width=96) Output:["_col0"] - Filter Operator [FIL_163] (rows=3600 width=107) + Filter Operator [FIL_163] (rows=3600 width=96) predicate:((hd_buy_potential like '0-500%') and hd_demo_sk is not null) - TableScan [TS_25] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential"] + TableScan [TS_25] (rows=7200 width=96) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_143] (rows=106480005 width=860) + Merge Join Operator [MERGEJOIN_143] (rows=20876 width=473) Conds:RS_34._col0=RS_35._col1(Inner),Output:["_col2","_col5","_col6","_col12","_col17","_col18","_col19"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_142] (rows=34846646 width=106) + Merge Join Operator [MERGEJOIN_142] (rows=657590 width=312) Conds:RS_21._col2=RS_162._col0(Inner),Output:["_col1","_col3","_col8","_col9","_col10"] <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_162] PartitionCols:_col0 - Select Operator [SEL_161] (rows=60 width=2045) + Select Operator [SEL_161] (rows=60 width=298) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_160] (rows=60 width=2045) + Filter Operator [FIL_160] (rows=60 width=298) predicate:cc_call_center_sk is not null - TableScan [TS_15] (rows=60 width=2045) - default@call_center,call_center,Tbl:COMPLETE,Col:NONE,Output:["cc_call_center_sk","cc_call_center_id","cc_name","cc_manager"] + TableScan [TS_15] (rows=60 width=298) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_call_center_id","cc_name","cc_manager"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_141] (rows=31678769 width=106) + Merge Join Operator [MERGEJOIN_141] (rows=657590 width=19) Conds:RS_156._col0=RS_159._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_156] PartitionCols:_col0 - Select Operator [SEL_155] (rows=28798881 width=106) + Select Operator [SEL_155] (rows=27658583 width=121) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_154] (rows=28798881 width=106) + Filter Operator [FIL_154] (rows=27658583 width=121) predicate:(cr_call_center_sk is not null and cr_returned_date_sk is not null and cr_returning_customer_sk is not null) - TableScan [TS_9] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_call_center_sk","cr_net_loss"] + TableScan [TS_9] (rows=28798881 width=121) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_call_center_sk","cr_net_loss"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_159] PartitionCols:_col0 - Select Operator [SEL_158] (rows=18262 width=1119) + Select Operator [SEL_158] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_157] (rows=18262 width=1119) + Filter Operator [FIL_157] (rows=50 width=12) predicate:((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) - TableScan [TS_12] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + TableScan [TS_12] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_140] (rows=96800003 width=860) + Merge Join Operator [MERGEJOIN_140] (rows=479709 width=183) Conds:RS_31._col3=RS_153._col0(Inner),Output:["_col0","_col2","_col5","_col6"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_153] PartitionCols:_col0 - Select Operator [SEL_152] (rows=20000000 width=1014) + Select Operator [SEL_152] (rows=8000000 width=116) Output:["_col0"] - Filter Operator [FIL_151] (rows=20000000 width=1014) + Filter Operator [FIL_151] (rows=8000000 width=112) predicate:((ca_gmt_offset = -7) and ca_address_sk is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"] + TableScan [TS_6] (rows=40000000 width=112) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_139] (rows=88000001 width=860) + Merge Join Operator [MERGEJOIN_139] (rows=2398543 width=187) Conds:RS_147._col1=RS_150._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_147] PartitionCols:_col1 - Select Operator [SEL_146] (rows=80000000 width=860) + Select Operator [SEL_146] (rows=74500295 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_145] (rows=80000000 width=860) + Filter Operator [FIL_145] (rows=74500295 width=15) predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk"] + TableScan [TS_0] (rows=80000000 width=15) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_150] PartitionCols:_col0 - Select Operator [SEL_149] (rows=930900 width=385) + Select Operator [SEL_149] (rows=59105 width=183) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_148] (rows=930900 width=385) + Filter Operator [FIL_148] (rows=59105 width=183) predicate:((cd_education_status) IN ('Unknown', 'Advanced Degree') and (cd_marital_status) IN ('M', 'W') and (struct(cd_marital_status,cd_education_status)) IN (const struct('M','Unknown'), const struct('W','Advanced Degree')) and cd_demo_sk is not null) - TableScan [TS_3] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] + TableScan [TS_3] (rows=1861800 width=183) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"] diff --git a/ql/src/test/results/clientpositive/perf/tez/query92.q.out b/ql/src/test/results/clientpositive/perf/tez/query92.q.out index 4b4afa9a95..b13c80959c 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query92.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query92.q.out @@ -59,112 +59,155 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (ONE_TO_ONE_EDGE) +Map 1 <- Reducer 15 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Map 13 <- Reducer 12 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 14 (SIMPLE_EDGE), Reducer 10 (ONE_TO_ONE_EDGE) +Reducer 12 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 3 <- Reducer 11 (ONE_TO_ONE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 2 (SIMPLE_EDGE) -Reducer 7 <- Map 10 (SIMPLE_EDGE), Reducer 6 (ONE_TO_ONE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 13 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 vectorized - File Output Operator [FS_135] - Limit [LIM_134] (rows=1 width=112) + File Output Operator [FS_147] + Limit [LIM_146] (rows=1 width=224) Number of rows:100 - Select Operator [SEL_133] (rows=1 width=112) + Select Operator [SEL_145] (rows=1 width=224) Output:["_col0"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_132] - Select Operator [SEL_131] (rows=1 width=112) + SHUFFLE [RS_144] + Select Operator [SEL_143] (rows=1 width=224) Output:["_col1"] - Group By Operator [GBY_130] (rows=1 width=112) + Group By Operator [GBY_142] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_36] Group By Operator [GBY_35] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col2)"] - Select Operator [SEL_34] (rows=58081078 width=135) + Select Operator [SEL_34] (rows=2478 width=112) Output:["_col2"] - Filter Operator [FIL_33] (rows=58081078 width=135) + Filter Operator [FIL_33] (rows=2478 width=112) predicate:(_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) - Merge Join Operator [MERGEJOIN_107] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_107] (rows=7434 width=112) Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col6"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_30] + PARTITION_ONLY_SHUFFLE [RS_30] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_104] (rows=158402938 width=135) - Conds:RS_126._col0=RS_110._col0(Inner),Output:["_col1","_col2"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_110] + Merge Join Operator [MERGEJOIN_104] (rows=15995224 width=115) + Conds:RS_131._col0=RS_110._col0(Inner),Output:["_col1","_col2"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=8116 width=1119) + Select Operator [SEL_109] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_108] (rows=8116 width=1119) + Filter Operator [FIL_108] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] + SHUFFLE [RS_131] PartitionCols:_col0 - Select Operator [SEL_125] (rows=144002668 width=135) + Select Operator [SEL_130] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_124] (rows=144002668 width=135) + Filter Operator [FIL_129] (rows=143966864 width=119) predicate:((ws_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) + TableScan [TS_0] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_127] + Group By Operator [GBY_126] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] - Group By Operator [GBY_120] (rows=1 width=12) + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_125] + Group By Operator [GBY_124] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_119] (rows=231000 width=1436) + Select Operator [SEL_123] (rows=669 width=4) Output:["_col0"] - Select Operator [SEL_117] (rows=231000 width=1436) + Select Operator [SEL_121] (rows=669 width=8) Output:["_col0"] - Filter Operator [FIL_116] (rows=231000 width=1436) + Filter Operator [FIL_120] (rows=669 width=7) predicate:((i_manufact_id = 269) and i_item_sk is not null) - TableScan [TS_20] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_115] - Group By Operator [GBY_114] (rows=1 width=12) + TableScan [TS_20] (rows=462000 width=7) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_manufact_id"] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_119] + Group By Operator [GBY_118] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_113] - Group By Operator [GBY_112] (rows=1 width=12) + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_116] + Group By Operator [GBY_114] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_111] (rows=8116 width=1119) + Select Operator [SEL_111] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_109] - <-Reducer 7 [ONE_TO_ONE_EDGE] + <-Reducer 11 [ONE_TO_ONE_EDGE] FORWARD [RS_31] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_106] (rows=87121617 width=135) - Conds:RS_129._col0=RS_118._col0(Inner),Output:["_col1","_col2"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] + Merge Join Operator [MERGEJOIN_106] (rows=97 width=116) + Conds:RS_141._col0=RS_122._col0(Inner),Output:["_col1","_col2"] + <-Map 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_122] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_117] - <-Reducer 6 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_129] + Please refer to the previous Select Operator [SEL_121] + <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_141] PartitionCols:_col0 - Select Operator [SEL_128] (rows=79201469 width=135) + Select Operator [SEL_140] (rows=6951 width=116) Output:["_col0","_col1"] - Group By Operator [GBY_127] (rows=79201469 width=135) + Group By Operator [GBY_139] (rows=6951 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 - <-Reducer 2 [SIMPLE_EDGE] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=158402938 width=135) + Group By Operator [GBY_16] (rows=55608 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 - Please refer to the previous Merge Join Operator [MERGEJOIN_104] + Merge Join Operator [MERGEJOIN_105] (rows=15995224 width=115) + Conds:RS_138._col0=RS_112._col0(Inner),Output:["_col1","_col2"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_112] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_109] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_138] + PartitionCols:_col0 + Select Operator [SEL_137] (rows=143966864 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_136] (rows=143966864 width=119) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_30_web_sales_ws_item_sk_min) AND DynamicValue(RS_30_web_sales_ws_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_30_web_sales_ws_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_6] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_128] + Please refer to the previous Group By Operator [GBY_126] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_133] + Group By Operator [GBY_132] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_117] + Group By Operator [GBY_115] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_113] (rows=8116 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_109] + <-Reducer 6 [BROADCAST_EDGE] vectorized + BROADCAST [RS_135] + Group By Operator [GBY_134] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_94] + Group By Operator [GBY_93] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_92] (rows=15995224 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_104] diff --git a/ql/src/test/results/clientpositive/perf/tez/query93.q.out b/ql/src/test/results/clientpositive/perf/tez/query93.q.out index d3ab839b42..8ef2b6ce3e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query93.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query93.q.out @@ -49,75 +49,75 @@ Stage-0 Stage-1 Reducer 5 vectorized File Output Operator [FS_82] - Limit [LIM_81] (rows=100 width=88) + Limit [LIM_81] (rows=100 width=112) Number of rows:100 - Select Operator [SEL_80] (rows=316797606 width=88) + Select Operator [SEL_80] (rows=38308 width=112) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_79] - Group By Operator [GBY_78] (rows=316797606 width=88) + Group By Operator [GBY_78] (rows=38308 width=112) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Group By Operator [GBY_17] (rows=633595212 width=88) + Group By Operator [GBY_17] (rows=38308 width=112) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_15] (rows=633595212 width=88) + Select Operator [SEL_15] (rows=15586502 width=3) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_64] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_64] (rows=15586502 width=3) Conds:RS_12._col0, _col2=RS_77._col0, _col2(Inner),Output:["_col3","_col7","_col9","_col10"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_12] PartitionCols:_col0, _col2 - Merge Join Operator [MERGEJOIN_63] (rows=63350266 width=77) + Merge Join Operator [MERGEJOIN_63] (rows=1522298 width=8) Conds:RS_67._col1=RS_70._col0(Inner),Output:["_col0","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_67] PartitionCols:_col1 - Select Operator [SEL_66] (rows=57591150 width=77) + Select Operator [SEL_66] (rows=55574563 width=15) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_65] (rows=57591150 width=77) + Filter Operator [FIL_65] (rows=55574563 width=15) predicate:(sr_item_sk is not null and sr_reason_sk is not null and sr_ticket_number is not null) - TableScan [TS_0] (rows=57591150 width=77) - default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_reason_sk","sr_ticket_number","sr_return_quantity"] + TableScan [TS_0] (rows=57591150 width=15) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_reason_sk","sr_ticket_number","sr_return_quantity"] <-Map 8 [SIMPLE_EDGE] vectorized SHUFFLE [RS_70] PartitionCols:_col0 - Select Operator [SEL_69] (rows=36 width=200) + Select Operator [SEL_69] (rows=1 width=113) Output:["_col0"] - Filter Operator [FIL_68] (rows=36 width=200) + Filter Operator [FIL_68] (rows=1 width=101) predicate:((r_reason_desc = 'Did not like the warranty') and r_reason_sk is not null) - TableScan [TS_3] (rows=72 width=200) - default@reason,reason,Tbl:COMPLETE,Col:NONE,Output:["r_reason_sk","r_reason_desc"] + TableScan [TS_3] (rows=72 width=101) + default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk","r_reason_desc"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_77] PartitionCols:_col0, _col2 - Select Operator [SEL_76] (rows=575995635 width=88) + Select Operator [SEL_76] (rows=575995635 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_75] (rows=575995635 width=88) + Filter Operator [FIL_75] (rows=575995635 width=122) predicate:((ss_item_sk BETWEEN DynamicValue(RS_12_store_returns_sr_item_sk_min) AND DynamicValue(RS_12_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_12_store_returns_sr_item_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_12_store_returns_sr_ticket_number_min) AND DynamicValue(RS_12_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_12_store_returns_sr_ticket_number_bloom_filter))) and ss_item_sk is not null and ss_ticket_number is not null) - TableScan [TS_6] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_ticket_number","ss_quantity","ss_sales_price"] + TableScan [TS_6] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_ticket_number","ss_quantity","ss_sales_price"] <-Reducer 6 [BROADCAST_EDGE] vectorized BROADCAST [RS_72] Group By Operator [GBY_71] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_55] Group By Operator [GBY_54] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_53] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_53] (rows=1522298 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_63] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_74] Group By Operator [GBY_73] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_60] Group By Operator [GBY_59] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] - Select Operator [SEL_58] (rows=63350266 width=77) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_58] (rows=1522298 width=8) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_63] diff --git a/ql/src/test/results/clientpositive/perf/tez/query94.q.out b/ql/src/test/results/clientpositive/perf/tez/query94.q.out index 396be11245..5fb42b9cba 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query94.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query94.q.out @@ -57,16 +57,18 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) -Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 18 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE) +Map 17 <- Reducer 10 (BROADCAST_EDGE) +Reducer 10 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 19 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) @@ -76,150 +78,161 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_176] - Limit [LIM_175] (rows=1 width=344) + File Output Operator [FS_178] + Limit [LIM_177] (rows=1 width=240) Number of rows:100 - Select Operator [SEL_174] (rows=1 width=344) + Select Operator [SEL_176] (rows=1 width=240) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_173] - Select Operator [SEL_172] (rows=1 width=344) + SHUFFLE [RS_175] + Select Operator [SEL_174] (rows=1 width=240) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_171] (rows=1 width=344) + Group By Operator [GBY_173] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_170] - Group By Operator [GBY_169] (rows=1 width=344) + PARTITION_ONLY_SHUFFLE [RS_172] + Group By Operator [GBY_171] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_168] (rows=115958879 width=135) + Group By Operator [GBY_170] (rows=1 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_74] PartitionCols:_col0 - Group By Operator [GBY_73] (rows=115958879 width=135) + Group By Operator [GBY_73] (rows=1 width=228) Output:["_col0","_col2","_col3"],aggregations:["sum(_col5)","sum(_col6)"],keys:_col4 - Select Operator [SEL_42] (rows=115958879 width=135) + Select Operator [SEL_42] (rows=1 width=232) Output:["_col4","_col5","_col6"] - Filter Operator [FIL_41] (rows=115958879 width=135) + Filter Operator [FIL_41] (rows=1 width=232) predicate:_col14 is null - Merge Join Operator [MERGEJOIN_130] (rows=231917759 width=135) - Conds:RS_38._col4=RS_167._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] - <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_167] + Merge Join Operator [MERGEJOIN_130] (rows=5022875 width=231) + Conds:RS_38._col4=RS_169._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] + <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_169] PartitionCols:_col0 - Select Operator [SEL_166] (rows=7199233 width=92) + Select Operator [SEL_168] (rows=8007986 width=8) Output:["_col0","_col1"] - Group By Operator [GBY_165] (rows=7199233 width=92) + Group By Operator [GBY_167] (rows=8007986 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_164] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_166] PartitionCols:_col0 - Group By Operator [GBY_163] (rows=14398467 width=92) + Group By Operator [GBY_165] (rows=14398467 width=4) Output:["_col0"],keys:wr_order_number - Filter Operator [FIL_162] (rows=14398467 width=92) + Filter Operator [FIL_164] (rows=14398467 width=4) predicate:wr_order_number is not null - TableScan [TS_25] (rows=14398467 width=92) - default@web_returns,wr1,Tbl:COMPLETE,Col:NONE,Output:["wr_order_number"] + TableScan [TS_25] (rows=14398467 width=4) + default@web_returns,wr1,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_order_number"] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_38] PartitionCols:_col4 - Select Operator [SEL_37] (rows=210834322 width=135) + Select Operator [SEL_37] (rows=5022875 width=231) Output:["_col4","_col5","_col6"] - Merge Join Operator [MERGEJOIN_129] (rows=210834322 width=135) - Conds:RS_34._col4=RS_161._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_161] - PartitionCols:_col0 - Group By Operator [GBY_160] (rows=144002668 width=135) - Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_159] (rows=144002668 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=144002668 width=135) - predicate:(ws_order_number is not null and ws_warehouse_sk is not null) - TableScan [TS_22] (rows=144002668 width=135) - default@web_sales,ws2,Tbl:COMPLETE,Col:NONE,Output:["ws_warehouse_sk","ws_order_number"] + Merge Join Operator [MERGEJOIN_129] (rows=5022875 width=235) + Conds:RS_34._col4=RS_163._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_128] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_128] (rows=5022875 width=231) Conds:RS_18._col2=RS_149._col0(Inner),Output:["_col3","_col4","_col5","_col6"] - <-Map 14 [SIMPLE_EDGE] vectorized + <-Map 15 [SIMPLE_EDGE] vectorized SHUFFLE [RS_149] PartitionCols:_col0 - Select Operator [SEL_148] (rows=42 width=1850) + Select Operator [SEL_148] (rows=12 width=91) Output:["_col0"] - Filter Operator [FIL_147] (rows=42 width=1850) + Filter Operator [FIL_147] (rows=12 width=92) predicate:((web_company_name = 'pri') and web_site_sk is not null) - TableScan [TS_9] (rows=84 width=1850) - default@web_site,web_site,Tbl:COMPLETE,Col:NONE,Output:["web_site_sk","web_company_name"] + TableScan [TS_9] (rows=84 width=92) + default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_company_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_127] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_127] (rows=15673790 width=235) Conds:RS_15._col1=RS_141._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] - <-Map 12 [SIMPLE_EDGE] vectorized + <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_141] PartitionCols:_col0 - Select Operator [SEL_140] (rows=20000000 width=1014) + Select Operator [SEL_140] (rows=784314 width=90) Output:["_col0"] - Filter Operator [FIL_139] (rows=20000000 width=1014) + Filter Operator [FIL_139] (rows=784314 width=90) predicate:((ca_state = 'TX') and ca_address_sk is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + TableScan [TS_6] (rows=40000000 width=90) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_126] (rows=158402938 width=135) + Merge Join Operator [MERGEJOIN_126] (rows=15987241 width=239) Conds:RS_157._col0=RS_133._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] - <-Map 10 [SIMPLE_EDGE] vectorized + <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_133] PartitionCols:_col0 - Select Operator [SEL_132] (rows=8116 width=1119) + Select Operator [SEL_132] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_131] (rows=8116 width=1119) + Filter Operator [FIL_131] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_156] (rows=144002668 width=135) + Select Operator [SEL_156] (rows=143895019 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_155] (rows=144002668 width=135) + Filter Operator [FIL_155] (rows=143895019 width=243) predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_16_customer_address_ca_address_sk_min) AND DynamicValue(RS_16_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_16_customer_address_ca_address_sk_bloom_filter))) and (ws_ship_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ws_ship_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_19_web_site_web_site_sk_min) AND DynamicValue(RS_19_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_19_web_site_web_site_sk_bloom_filter))) and ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,ws1,Tbl:COMPLETE,Col:NONE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_warehouse_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] - <-Reducer 11 [BROADCAST_EDGE] vectorized + TableScan [TS_0] (rows=144002668 width=243) + default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_warehouse_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] + <-Reducer 12 [BROADCAST_EDGE] vectorized BROADCAST [RS_138] Group By Operator [GBY_137] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_136] Group By Operator [GBY_135] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_134] (rows=8116 width=1119) + Select Operator [SEL_134] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_132] - <-Reducer 13 [BROADCAST_EDGE] vectorized + <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_146] Group By Operator [GBY_145] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_144] Group By Operator [GBY_143] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_142] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_142] (rows=784314 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_140] - <-Reducer 15 [BROADCAST_EDGE] vectorized + <-Reducer 16 [BROADCAST_EDGE] vectorized BROADCAST [RS_154] Group By Operator [GBY_153] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_152] Group By Operator [GBY_151] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_150] (rows=42 width=1850) + Select Operator [SEL_150] (rows=12 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_148] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_163] + PartitionCols:_col0 + Group By Operator [GBY_162] (rows=143966743 width=7) + Output:["_col0","_col1"],keys:_col0, _col1 + Select Operator [SEL_161] (rows=143966743 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_160] (rows=143966743 width=7) + predicate:((ws_order_number BETWEEN DynamicValue(RS_34_ws1_ws_order_number_min) AND DynamicValue(RS_34_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_34_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null and ws_warehouse_sk is not null) + TableScan [TS_22] (rows=144002668 width=7) + default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_159] + Group By Operator [GBY_158] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_116] + Group By Operator [GBY_115] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_114] (rows=5022875 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_128] diff --git a/ql/src/test/results/clientpositive/perf/tez/query95.q.out b/ql/src/test/results/clientpositive/perf/tez/query95.q.out index 86e892f786..a54ec583ad 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query95.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query95.q.out @@ -63,226 +63,223 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE) -Map 15 <- Reducer 23 (BROADCAST_EDGE) -Map 21 <- Reducer 23 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 17 <- Map 22 (SIMPLE_EDGE), Reducer 16 (ONE_TO_ONE_EDGE) -Reducer 18 <- Reducer 17 (SIMPLE_EDGE) -Reducer 19 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 20 <- Reducer 19 (SIMPLE_EDGE) -Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 18 (ONE_TO_ONE_EDGE), Reducer 20 (ONE_TO_ONE_EDGE), Reducer 4 (SIMPLE_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE) +Map 16 <- Reducer 9 (BROADCAST_EDGE) +Map 22 <- Reducer 9 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) +Reducer 18 <- Map 23 (SIMPLE_EDGE), Reducer 17 (ONE_TO_ONE_EDGE) +Reducer 19 <- Reducer 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 20 <- Map 16 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) +Reducer 21 <- Reducer 20 (SIMPLE_EDGE) +Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 19 (ONE_TO_ONE_EDGE), Reducer 21 (ONE_TO_ONE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 8 vectorized - File Output Operator [FS_286] - Limit [LIM_285] (rows=1 width=344) + File Output Operator [FS_282] + Limit [LIM_281] (rows=1 width=240) Number of rows:100 - Select Operator [SEL_284] (rows=1 width=344) + Select Operator [SEL_280] (rows=1 width=240) Output:["_col0","_col1","_col2"] <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_283] - Select Operator [SEL_282] (rows=1 width=344) + SHUFFLE [RS_279] + Select Operator [SEL_278] (rows=1 width=240) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_281] (rows=1 width=344) + Group By Operator [GBY_277] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_280] - Group By Operator [GBY_279] (rows=1 width=344) + PARTITION_ONLY_SHUFFLE [RS_276] + Group By Operator [GBY_275] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_278] (rows=421668645 width=135) + Group By Operator [GBY_274] (rows=2511437 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_116] PartitionCols:_col0 - Group By Operator [GBY_115] (rows=421668645 width=135) + Group By Operator [GBY_115] (rows=2511437 width=228) Output:["_col0","_col2","_col3"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col3 - Merge Join Operator [MERGEJOIN_228] (rows=421668645 width=135) - Conds:RS_58._col3=RS_277._col0(Inner),RS_58._col3=RS_275._col0(Inner),Output:["_col3","_col4","_col5"] - <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_275] - PartitionCols:_col0 - Group By Operator [GBY_274] (rows=87121617 width=135) - Output:["_col0"],keys:KEY._col0 - <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_46] - PartitionCols:_col0 - Group By Operator [GBY_45] (rows=174243235 width=135) - Output:["_col0"],keys:_col14 - Merge Join Operator [MERGEJOIN_227] (rows=174243235 width=135) - Conds:RS_41._col0=RS_255._col13(Inner),Output:["_col14"] - <-Map 22 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_255] - PartitionCols:_col13 - Select Operator [SEL_254] (rows=14398467 width=92) - Output:["_col13"] - Filter Operator [FIL_253] (rows=14398467 width=92) - predicate:wr_order_number is not null - TableScan [TS_38] (rows=14398467 width=92) - default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_order_number"] - <-Reducer 16 [ONE_TO_ONE_EDGE] - FORWARD [RS_41] - PartitionCols:_col0 - Select Operator [SEL_37] (rows=158402938 width=135) - Output:["_col0"] - Filter Operator [FIL_36] (rows=158402938 width=135) - predicate:(_col0 <> _col2) - Merge Join Operator [MERGEJOIN_226] (rows=158402938 width=135) - Conds:RS_268._col1=RS_272._col1(Inner),Output:["_col0","_col1","_col2"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_268] - PartitionCols:_col1 - Select Operator [SEL_267] (rows=144002668 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_266] (rows=144002668 width=135) - predicate:((ws_order_number BETWEEN DynamicValue(RS_42_web_returns_wr_order_number_min) AND DynamicValue(RS_42_web_returns_wr_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_42_web_returns_wr_order_number_bloom_filter))) and ws_order_number is not null) - TableScan [TS_27] (rows=144002668 width=135) - default@web_sales,ws1,Tbl:COMPLETE,Col:NONE,Output:["ws_warehouse_sk","ws_order_number"] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_261] - Group By Operator [GBY_259] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=14398467)"] - <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_258] - Group By Operator [GBY_257] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=14398467)"] - Select Operator [SEL_256] (rows=14398467 width=92) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_254] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_272] - PartitionCols:_col1 - Select Operator [SEL_271] (rows=144002668 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_270] (rows=144002668 width=135) - predicate:((ws_order_number BETWEEN DynamicValue(RS_42_web_returns_wr_order_number_min) AND DynamicValue(RS_42_web_returns_wr_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_42_web_returns_wr_order_number_bloom_filter))) and ws_order_number is not null) - TableScan [TS_30] (rows=144002668 width=135) - default@web_sales,ws2,Tbl:COMPLETE,Col:NONE,Output:["ws_warehouse_sk","ws_order_number"] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_262] - Please refer to the previous Group By Operator [GBY_259] - <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_277] - PartitionCols:_col0 - Group By Operator [GBY_276] (rows=79201469 width=135) - Output:["_col0"],keys:KEY._col0 - <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col0 - Group By Operator [GBY_23] (rows=158402938 width=135) - Output:["_col0"],keys:_col1 - Select Operator [SEL_22] (rows=158402938 width=135) - Output:["_col1"] - Filter Operator [FIL_21] (rows=158402938 width=135) - predicate:(_col0 <> _col2) - Merge Join Operator [MERGEJOIN_225] (rows=158402938 width=135) - Conds:RS_269._col1=RS_273._col1(Inner),Output:["_col0","_col1","_col2"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_269] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_267] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_273] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_271] + Merge Join Operator [MERGEJOIN_228] (rows=5022875 width=227) + Conds:RS_58._col3=RS_273._col0(Inner),RS_58._col3=RS_271._col0(Inner),Output:["_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_58] + PARTITION_ONLY_SHUFFLE [RS_58] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_224] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_224] (rows=5022875 width=227) Conds:RS_55._col2=RS_247._col0(Inner),Output:["_col3","_col4","_col5"] - <-Map 13 [SIMPLE_EDGE] vectorized + <-Map 14 [SIMPLE_EDGE] vectorized SHUFFLE [RS_247] PartitionCols:_col0 - Select Operator [SEL_246] (rows=42 width=1850) + Select Operator [SEL_246] (rows=12 width=91) Output:["_col0"] - Filter Operator [FIL_245] (rows=42 width=1850) + Filter Operator [FIL_245] (rows=12 width=92) predicate:((web_company_name = 'pri') and web_site_sk is not null) - TableScan [TS_9] (rows=84 width=1850) - default@web_site,web_site,Tbl:COMPLETE,Col:NONE,Output:["web_site_sk","web_company_name"] + TableScan [TS_9] (rows=84 width=92) + default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_company_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_223] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_223] (rows=15673790 width=231) Conds:RS_52._col1=RS_239._col0(Inner),Output:["_col2","_col3","_col4","_col5"] - <-Map 11 [SIMPLE_EDGE] vectorized + <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_239] PartitionCols:_col0 - Select Operator [SEL_238] (rows=20000000 width=1014) + Select Operator [SEL_238] (rows=784314 width=90) Output:["_col0"] - Filter Operator [FIL_237] (rows=20000000 width=1014) + Filter Operator [FIL_237] (rows=784314 width=90) predicate:((ca_state = 'TX') and ca_address_sk is not null) - TableScan [TS_6] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + TableScan [TS_6] (rows=40000000 width=90) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_222] (rows=158402938 width=135) - Conds:RS_265._col0=RS_231._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 9 [SIMPLE_EDGE] vectorized + Merge Join Operator [MERGEJOIN_222] (rows=15987241 width=235) + Conds:RS_255._col0=RS_231._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_231] PartitionCols:_col0 - Select Operator [SEL_230] (rows=8116 width=1119) + Select Operator [SEL_230] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_229] (rows=8116 width=1119) + Filter Operator [FIL_229] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_265] + SHUFFLE [RS_255] PartitionCols:_col0 - Select Operator [SEL_264] (rows=144002668 width=135) + Select Operator [SEL_254] (rows=143895019 width=239) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_263] (rows=144002668 width=135) - predicate:((ws_order_number BETWEEN DynamicValue(RS_42_web_returns_wr_order_number_min) AND DynamicValue(RS_42_web_returns_wr_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_42_web_returns_wr_order_number_bloom_filter))) and (ws_ship_addr_sk BETWEEN DynamicValue(RS_53_customer_address_ca_address_sk_min) AND DynamicValue(RS_53_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_53_customer_address_ca_address_sk_bloom_filter))) and (ws_ship_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ws_ship_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_56_web_site_web_site_sk_min) AND DynamicValue(RS_56_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_56_web_site_web_site_sk_bloom_filter))) and ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) - TableScan [TS_0] (rows=144002668 width=135) - default@web_sales,ws1,Tbl:COMPLETE,Col:NONE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_260] - Please refer to the previous Group By Operator [GBY_259] - <-Reducer 10 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_253] (rows=143895019 width=239) + predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_53_customer_address_ca_address_sk_min) AND DynamicValue(RS_53_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_53_customer_address_ca_address_sk_bloom_filter))) and (ws_ship_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ws_ship_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_56_web_site_web_site_sk_min) AND DynamicValue(RS_56_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_56_web_site_web_site_sk_bloom_filter))) and ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) + TableScan [TS_0] (rows=144002668 width=239) + default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] + <-Reducer 11 [BROADCAST_EDGE] vectorized BROADCAST [RS_236] Group By Operator [GBY_235] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_234] Group By Operator [GBY_233] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_232] (rows=8116 width=1119) + Select Operator [SEL_232] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_230] - <-Reducer 12 [BROADCAST_EDGE] vectorized + <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_244] Group By Operator [GBY_243] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_242] Group By Operator [GBY_241] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] - Select Operator [SEL_240] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_240] (rows=784314 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_238] - <-Reducer 14 [BROADCAST_EDGE] vectorized + <-Reducer 15 [BROADCAST_EDGE] vectorized BROADCAST [RS_252] Group By Operator [GBY_251] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_250] Group By Operator [GBY_249] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_248] (rows=42 width=1850) + Select Operator [SEL_248] (rows=12 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_246] + <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_271] + PartitionCols:_col0 + Group By Operator [GBY_270] (rows=8007986 width=4) + Output:["_col0"],keys:KEY._col0 + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_46] + PartitionCols:_col0 + Group By Operator [GBY_45] (rows=1384229738 width=4) + Output:["_col0"],keys:_col14 + Merge Join Operator [MERGEJOIN_227] (rows=1384229738 width=4) + Conds:RS_41._col0=RS_269._col13(Inner),Output:["_col14"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_269] + PartitionCols:_col13 + Select Operator [SEL_268] (rows=14398467 width=272) + Output:["_col13"] + Filter Operator [FIL_267] (rows=14398467 width=4) + predicate:wr_order_number is not null + TableScan [TS_38] (rows=14398467 width=4) + default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_order_number"] + <-Reducer 17 [ONE_TO_ONE_EDGE] + FORWARD [RS_41] + PartitionCols:_col0 + Select Operator [SEL_37] (rows=1411940834 width=4) + Output:["_col0"] + Filter Operator [FIL_36] (rows=1411940834 width=11) + predicate:(_col0 <> _col2) + Merge Join Operator [MERGEJOIN_226] (rows=1411940834 width=11) + Conds:RS_261._col1=RS_265._col1(Inner),Output:["_col0","_col1","_col2"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_261] + PartitionCols:_col1 + Select Operator [SEL_260] (rows=144002668 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_259] (rows=144002668 width=7) + predicate:((ws_order_number BETWEEN DynamicValue(RS_58_ws1_ws_order_number_min) AND DynamicValue(RS_58_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_58_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null) + TableScan [TS_27] (rows=144002668 width=7) + default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_257] + Group By Operator [GBY_256] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 4 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_184] + Group By Operator [GBY_183] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_182] (rows=5022875 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_224] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_265] + PartitionCols:_col1 + Select Operator [SEL_264] (rows=144002668 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_263] (rows=144002668 width=7) + predicate:((ws_order_number BETWEEN DynamicValue(RS_58_ws1_ws_order_number_min) AND DynamicValue(RS_58_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_58_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null) + TableScan [TS_30] (rows=144002668 width=7) + default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_258] + Please refer to the previous Group By Operator [GBY_256] + <-Reducer 21 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_273] + PartitionCols:_col0 + Group By Operator [GBY_272] (rows=14686712 width=4) + Output:["_col0"],keys:KEY._col0 + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col0 + Group By Operator [GBY_23] (rows=1411940834 width=4) + Output:["_col0"],keys:_col1 + Select Operator [SEL_22] (rows=1411940834 width=11) + Output:["_col1"] + Filter Operator [FIL_21] (rows=1411940834 width=11) + predicate:(_col0 <> _col2) + Merge Join Operator [MERGEJOIN_225] (rows=1411940834 width=11) + Conds:RS_262._col1=RS_266._col1(Inner),Output:["_col0","_col1","_col2"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_262] + PartitionCols:_col1 + Please refer to the previous Select Operator [SEL_260] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_266] + PartitionCols:_col1 + Please refer to the previous Select Operator [SEL_264] diff --git a/ql/src/test/results/clientpositive/perf/tez/query96.q.out b/ql/src/test/results/clientpositive/perf/tez/query96.q.out index f7d828a44d..ad14391bb1 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query96.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query96.q.out @@ -47,13 +47,13 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_109] - Limit [LIM_108] (rows=1 width=8) + Limit [LIM_108] (rows=1 width=16) Number of rows:100 - Select Operator [SEL_107] (rows=1 width=8) + Select Operator [SEL_107] (rows=1 width=16) Output:["_col0"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] - Select Operator [SEL_105] (rows=1 width=8) + Select Operator [SEL_105] (rows=1 width=16) Output:["_col1"] Group By Operator [GBY_104] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] @@ -61,54 +61,54 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_76] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_76] (rows=1084713 width=8) Conds:RS_18._col2=RS_95._col0(Inner) <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_95] PartitionCols:_col0 - Select Operator [SEL_94] (rows=852 width=1910) + Select Operator [SEL_94] (rows=155 width=91) Output:["_col0"] - Filter Operator [FIL_93] (rows=852 width=1910) + Filter Operator [FIL_93] (rows=155 width=92) predicate:((s_store_name = 'ese') and s_store_sk is not null) - TableScan [TS_9] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name"] + TableScan [TS_9] (rows=1704 width=92) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_75] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_75] (rows=1477476 width=0) Conds:RS_15._col1=RS_87._col0(Inner),Output:["_col2"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_86] (rows=3600 width=107) + Select Operator [SEL_86] (rows=655 width=8) Output:["_col0"] - Filter Operator [FIL_85] (rows=3600 width=107) + Filter Operator [FIL_85] (rows=655 width=8) predicate:((hd_dep_count = 5) and hd_demo_sk is not null) - TableScan [TS_6] (rows=7200 width=107) - default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count"] + TableScan [TS_6] (rows=7200 width=8) + default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_74] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_74] (rows=16240953 width=0) Conds:RS_103._col0=RS_79._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_79] PartitionCols:_col0 - Select Operator [SEL_78] (rows=14400 width=471) + Select Operator [SEL_78] (rows=1515 width=12) Output:["_col0"] - Filter Operator [FIL_77] (rows=14400 width=471) + Filter Operator [FIL_77] (rows=1515 width=12) predicate:((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) - TableScan [TS_3] (rows=86400 width=471) - default@time_dim,time_dim,Tbl:COMPLETE,Col:NONE,Output:["t_time_sk","t_hour","t_minute"] + TableScan [TS_3] (rows=86400 width=12) + default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_102] (rows=575995635 width=88) + Select Operator [SEL_102] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_101] (rows=575995635 width=88) + Filter Operator [FIL_101] (rows=501695814 width=11) predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_16_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_16_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_16_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_13_time_dim_t_time_sk_min) AND DynamicValue(RS_13_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_13_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] + TableScan [TS_0] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_92] Group By Operator [GBY_91] (rows=1 width=12) @@ -117,7 +117,7 @@ Stage-0 SHUFFLE [RS_90] Group By Operator [GBY_89] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_88] (rows=3600 width=107) + Select Operator [SEL_88] (rows=655 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_86] <-Reducer 12 [BROADCAST_EDGE] vectorized @@ -128,7 +128,7 @@ Stage-0 SHUFFLE [RS_98] Group By Operator [GBY_97] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_96] (rows=852 width=1910) + Select Operator [SEL_96] (rows=155 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_94] <-Reducer 8 [BROADCAST_EDGE] vectorized @@ -139,7 +139,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_82] Group By Operator [GBY_81] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_80] (rows=14400 width=471) + Select Operator [SEL_80] (rows=1515 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_78] diff --git a/ql/src/test/results/clientpositive/perf/tez/query97.q.out b/ql/src/test/results/clientpositive/perf/tez/query97.q.out index b65b57aac1..d76d6d2699 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query97.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query97.q.out @@ -74,40 +74,40 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_34] Group By Operator [GBY_33] (rows=1 width=24) Output:["_col0","_col1","_col2"],aggregations:["sum(_col0)","sum(_col1)","sum(_col2)"] - Select Operator [SEL_31] (rows=348477374 width=88) + Select Operator [SEL_31] (rows=12370931353 width=7) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_69] (rows=348477374 width=88) + Merge Join Operator [MERGEJOIN_69] (rows=12370931353 width=7) Conds:RS_86._col0, _col1=RS_93._col0, _col1(Outer),Output:["_col0","_col2"] <-Reducer 3 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_86] PartitionCols:_col0, _col1 - Group By Operator [GBY_85] (rows=316797606 width=88) + Group By Operator [GBY_85] (rows=61115434 width=6) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_11] PartitionCols:_col0, _col1 - Group By Operator [GBY_10] (rows=633595212 width=88) + Group By Operator [GBY_10] (rows=61115434 width=6) Output:["_col0","_col1"],keys:_col2, _col1 - Merge Join Operator [MERGEJOIN_67] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_67] (rows=61115434 width=6) Conds:RS_84._col0=RS_72._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_72] PartitionCols:_col0 - Select Operator [SEL_71] (rows=8116 width=1119) + Select Operator [SEL_71] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_70] (rows=8116 width=1119) + Filter Operator [FIL_70] (rows=8116 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_84] PartitionCols:_col0 - Select Operator [SEL_83] (rows=575995635 width=88) + Select Operator [SEL_83] (rows=550076554 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_82] (rows=575995635 width=88) + Filter Operator [FIL_82] (rows=550076554 width=11) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] + TableScan [TS_0] (rows=575995635 width=11) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] <-Reducer 7 [BROADCAST_EDGE] vectorized BROADCAST [RS_81] Group By Operator [GBY_80] (rows=1 width=12) @@ -116,20 +116,20 @@ Stage-0 SHUFFLE [RS_78] Group By Operator [GBY_76] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_73] (rows=8116 width=1119) + Select Operator [SEL_73] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_71] <-Reducer 9 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_93] PartitionCols:_col0, _col1 - Group By Operator [GBY_92] (rows=158394413 width=135) + Group By Operator [GBY_92] (rows=31836679 width=7) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0, _col1 - Group By Operator [GBY_24] (rows=316788826 width=135) + Group By Operator [GBY_24] (rows=31836679 width=7) Output:["_col0","_col1"],keys:_col1, _col2 - Merge Join Operator [MERGEJOIN_68] (rows=316788826 width=135) + Merge Join Operator [MERGEJOIN_68] (rows=31836679 width=7) Conds:RS_91._col0=RS_74._col0(Inner),Output:["_col1","_col2"] <-Map 6 [SIMPLE_EDGE] vectorized SHUFFLE [RS_74] @@ -138,12 +138,12 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_91] PartitionCols:_col0 - Select Operator [SEL_90] (rows=287989836 width=135) + Select Operator [SEL_90] (rows=286549727 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_89] (rows=287989836 width=135) + Filter Operator [FIL_89] (rows=286549727 width=11) predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_21_date_dim_d_date_sk_min) AND DynamicValue(RS_21_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_21_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) - TableScan [TS_14] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk"] + TableScan [TS_14] (rows=287989836 width=11) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_88] Group By Operator [GBY_87] (rows=1 width=12) @@ -152,7 +152,7 @@ Stage-0 SHUFFLE [RS_79] Group By Operator [GBY_77] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_75] (rows=8116 width=1119) + Select Operator [SEL_75] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_71] diff --git a/ql/src/test/results/clientpositive/perf/tez/query98.q.out b/ql/src/test/results/clientpositive/perf/tez/query98.q.out index 02609726fe..8bcd4bac48 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query98.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query98.q.out @@ -78,60 +78,60 @@ Stage-0 Stage-1 Reducer 6 vectorized File Output Operator [FS_84] - Select Operator [SEL_83] (rows=348477374 width=88) + Select Operator [SEL_83] (rows=18334631 width=701) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized SHUFFLE [RS_82] - Select Operator [SEL_81] (rows=348477374 width=88) + Select Operator [SEL_81] (rows=18334631 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_80] (rows=348477374 width=88) + PTF Operator [PTF_80] (rows=18334631 width=689) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"_col1"}] - Select Operator [SEL_79] (rows=348477374 width=88) + Select Operator [SEL_79] (rows=18334631 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] vectorized SHUFFLE [RS_78] PartitionCols:_col1 - Group By Operator [GBY_77] (rows=348477374 width=88) + Group By Operator [GBY_77] (rows=18334631 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0, _col1, _col2, _col3, _col4 - Group By Operator [GBY_16] (rows=696954748 width=88) + Group By Operator [GBY_16] (rows=18334631 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8 - Merge Join Operator [MERGEJOIN_57] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_57] (rows=18334631 width=577) Conds:RS_12._col1=RS_68._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_68] PartitionCols:_col0 - Select Operator [SEL_67] (rows=462000 width=1436) + Select Operator [SEL_67] (rows=138600 width=581) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_66] (rows=462000 width=1436) + Filter Operator [FIL_66] (rows=138600 width=581) predicate:((i_category) IN ('Jewelry', 'Sports', 'Books') and i_item_sk is not null) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] + TableScan [TS_6] (rows=462000 width=581) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_56] (rows=633595212 width=88) + Merge Join Operator [MERGEJOIN_56] (rows=61115434 width=70) Conds:RS_76._col0=RS_60._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 - Select Operator [SEL_59] (rows=8116 width=1119) + Select Operator [SEL_59] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_58] (rows=8116 width=1119) + Filter Operator [FIL_58] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_76] PartitionCols:_col0 - Select Operator [SEL_75] (rows=575995635 width=88) + Select Operator [SEL_75] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_74] (rows=575995635 width=88) + Filter Operator [FIL_74] (rows=550076554 width=114) predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] + TableScan [TS_0] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] <-Reducer 10 [BROADCAST_EDGE] vectorized BROADCAST [RS_73] Group By Operator [GBY_72] (rows=1 width=12) @@ -140,7 +140,7 @@ Stage-0 SHUFFLE [RS_71] Group By Operator [GBY_70] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_69] (rows=462000 width=1436) + Select Operator [SEL_69] (rows=138600 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_67] <-Reducer 8 [BROADCAST_EDGE] vectorized @@ -151,7 +151,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_63] Group By Operator [GBY_62] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_61] (rows=8116 width=1119) + Select Operator [SEL_61] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_59] diff --git a/ql/src/test/results/clientpositive/perf/tez/query99.q.out b/ql/src/test/results/clientpositive/perf/tez/query99.q.out index 456fd8c96f..a93cc87835 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query99.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query99.q.out @@ -69,14 +69,12 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) @@ -86,121 +84,99 @@ Stage-0 limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_142] - Limit [LIM_141] (rows=100 width=135) + File Output Operator [FS_132] + Limit [LIM_131] (rows=100 width=590) Number of rows:100 - Select Operator [SEL_140] (rows=210822976 width=135) + Select Operator [SEL_130] (rows=3920200 width=590) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_139] - Select Operator [SEL_138] (rows=210822976 width=135) + SHUFFLE [RS_129] + Select Operator [SEL_128] (rows=3920200 width=590) Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Group By Operator [GBY_137] (rows=210822976 width=135) + Group By Operator [GBY_127] (rows=3920200 width=406) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_29] (rows=421645953 width=135) + Group By Operator [GBY_29] (rows=7840400 width=406) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)"],keys:_col0, _col1, _col2 - Top N Key Operator [TNK_57] (rows=421645953 width=135) + Top N Key Operator [TNK_57] (rows=15680800 width=289) keys:_col0, _col1, _col2,sort order:+++,top n:100 - Select Operator [SEL_27] (rows=421645953 width=135) + Select Operator [SEL_27] (rows=15680800 width=289) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_101] (rows=421645953 width=135) - Conds:RS_24._col3=RS_128._col0(Inner),Output:["_col0","_col1","_col8","_col10","_col12"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_128] + Merge Join Operator [MERGEJOIN_101] (rows=15680800 width=289) + Conds:RS_24._col3=RS_112._col0(Inner),Output:["_col0","_col1","_col8","_col10","_col12"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_112] PartitionCols:_col0 - Select Operator [SEL_127] (rows=1 width=0) + Select Operator [SEL_111] (rows=1 width=88) Output:["_col0","_col1"] - Filter Operator [FIL_126] (rows=1 width=0) + Filter Operator [FIL_110] (rows=1 width=88) predicate:sm_ship_mode_sk is not null - TableScan [TS_12] (rows=1 width=0) - default@ship_mode,ship_mode,Tbl:PARTIAL,Col:NONE,Output:["sm_ship_mode_sk","sm_type"] + TableScan [TS_12] (rows=1 width=88) + default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_100] (rows=383314495 width=135) - Conds:RS_21._col4=RS_120._col0(Inner),Output:["_col0","_col1","_col3","_col8","_col10"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] + Merge Join Operator [MERGEJOIN_100] (rows=31361601 width=209) + Conds:RS_21._col4=RS_126._col0(Inner),Output:["_col0","_col1","_col3","_col8","_col10"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_126] PartitionCols:_col0 - Select Operator [SEL_119] (rows=27 width=1029) + Select Operator [SEL_125] (rows=27 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_118] (rows=27 width=1029) + Filter Operator [FIL_124] (rows=27 width=104) predicate:w_warehouse_sk is not null - TableScan [TS_9] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_warehouse_name"] + TableScan [TS_9] (rows=27 width=104) + default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_99] (rows=348467716 width=135) - Conds:RS_18._col2=RS_112._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col8"] + Merge Join Operator [MERGEJOIN_99] (rows=31361601 width=113) + Conds:RS_18._col2=RS_123._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col8"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] + SHUFFLE [RS_123] PartitionCols:_col0 - Select Operator [SEL_111] (rows=60 width=2045) + Select Operator [SEL_122] (rows=60 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_110] (rows=60 width=2045) + Filter Operator [FIL_121] (rows=60 width=102) predicate:cc_call_center_sk is not null - TableScan [TS_6] (rows=60 width=2045) - default@call_center,call_center,Tbl:COMPLETE,Col:NONE,Output:["cc_call_center_sk","cc_name"] + TableScan [TS_6] (rows=60 width=102) + default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_98] (rows=316788826 width=135) - Conds:RS_136._col1=RS_104._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_98] (rows=31361601 width=19) + Conds:RS_120._col1=RS_104._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_104] PartitionCols:_col0 - Select Operator [SEL_103] (rows=8116 width=1119) + Select Operator [SEL_103] (rows=8116 width=8) Output:["_col0"] - Filter Operator [FIL_102] (rows=8116 width=1119) + Filter Operator [FIL_102] (rows=8116 width=8) predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_136] + SHUFFLE [RS_120] PartitionCols:_col1 - Select Operator [SEL_135] (rows=287989836 width=135) + Select Operator [SEL_119] (rows=282273729 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_134] (rows=287989836 width=135) - predicate:((cs_call_center_sk BETWEEN DynamicValue(RS_19_call_center_cc_call_center_sk_min) AND DynamicValue(RS_19_call_center_cc_call_center_sk_max) and in_bloom_filter(cs_call_center_sk, DynamicValue(RS_19_call_center_cc_call_center_sk_bloom_filter))) and (cs_ship_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (cs_ship_mode_sk BETWEEN DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_bloom_filter))) and (cs_warehouse_sk BETWEEN DynamicValue(RS_22_warehouse_w_warehouse_sk_min) AND DynamicValue(RS_22_warehouse_w_warehouse_sk_max) and in_bloom_filter(cs_warehouse_sk, DynamicValue(RS_22_warehouse_w_warehouse_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"] - <-Reducer 11 [BROADCAST_EDGE] vectorized + Filter Operator [FIL_118] (rows=282273729 width=19) + predicate:((cs_ship_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (cs_ship_mode_sk BETWEEN DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_25_ship_mode_sm_ship_mode_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) + TableScan [TS_0] (rows=287989836 width=19) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"] + <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_117] Group By Operator [GBY_116] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_115] Group By Operator [GBY_114] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_113] (rows=60 width=2045) + Select Operator [SEL_113] (rows=1 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_111] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_125] - Group By Operator [GBY_124] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_121] (rows=27 width=1029) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_119] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_133] - Group By Operator [GBY_132] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_131] - Group By Operator [GBY_130] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_129] (rows=1 width=0) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_127] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_109] Group By Operator [GBY_108] (rows=1 width=12) @@ -209,7 +185,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_107] Group By Operator [GBY_106] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_105] (rows=8116 width=1119) + Select Operator [SEL_105] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_103] diff --git a/ql/src/test/results/clientpositive/pointlookup.q.out b/ql/src/test/results/clientpositive/pointlookup.q.out index a4ca8030e3..10f8869a31 100644 --- a/ql/src/test/results/clientpositive/pointlookup.q.out +++ b/ql/src/test/results/clientpositive/pointlookup.q.out @@ -41,17 +41,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (((key = '0') and (value = 'val_0')) or ((key = '1') and (value = 'val_1')) or ((key = '2') and (value = 'val_2')) or ((key = '3') and (value = 'val_3')) or ((key = '4') and (value = 'val_4')) or ((key = '5') and (value = 'val_5')) or ((key = '6') and (value = 'val_6')) or ((key = '7') and (value = 'val_7')) or ((key = '8') and (value = 'val_8')) or ((key = '9') and (value = 'val_9')) or ((key = '10') and (value = 'val_10'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = '0') and (value = 'val_0')) or ((key = '1') and (value = 'val_1')) or ((key = '10') and (value = 'val_10')) or ((key = '2') and (value = 'val_2')) or ((key = '3') and (value = 'val_3')) or ((key = '4') and (value = 'val_4')) or ((key = '5') and (value = 'val_5')) or ((key = '6') and (value = 'val_6')) or ((key = '7') and (value = 'val_7')) or ((key = '8') and (value = 'val_8')) or ((key = '9') and (value = 'val_9'))) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -146,17 +146,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2175 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2175 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -251,17 +251,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2175 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2175 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/pointlookup2.q.out b/ql/src/test/results/clientpositive/pointlookup2.q.out index b627a56daf..bd2bf6fdba 100644 --- a/ql/src/test/results/clientpositive/pointlookup2.q.out +++ b/ql/src/test/results/clientpositive/pointlookup2.q.out @@ -113,21 +113,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n2 filterExpr: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -238,13 +238,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -301,44 +301,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -404,11 +404,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -437,7 +437,7 @@ STAGE PLANS: key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false @@ -474,13 +474,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -537,44 +537,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -689,11 +689,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -722,7 +722,7 @@ STAGE PLANS: key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false @@ -759,13 +759,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -822,36 +822,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), key (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) auto parallelism: false @@ -1015,11 +1015,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 40 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: (((_col2 = '2000-04-08') and (_col4 = 1)) or ((_col2 = '2000-04-09') and (_col4 = 2))) (type: boolean) - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -1048,7 +1048,7 @@ STAGE PLANS: key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) auto parallelism: false @@ -1085,13 +1085,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1148,40 +1148,40 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: PARTIAL tag: 0 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), key (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) auto parallelism: false @@ -1394,11 +1394,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 60 Data size: 1620 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4650 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator isSamplingPred: false predicate: (((_col3 = '2000-04-08') and (_col0 = 1)) or ((_col3 = '2000-04-09') and (_col0 = 2))) (type: boolean) - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 930 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -1427,7 +1427,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 930 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string) auto parallelism: false @@ -1464,13 +1464,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 930 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 930 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1695,21 +1695,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n2 filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -1820,13 +1820,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1883,44 +1883,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -1986,11 +1986,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -2019,7 +2019,7 @@ STAGE PLANS: key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false @@ -2056,13 +2056,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2119,44 +2119,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -2271,11 +2271,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -2304,7 +2304,7 @@ STAGE PLANS: key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false @@ -2341,13 +2341,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2396,36 +2396,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), key (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) auto parallelism: false @@ -2589,11 +2589,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 40 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: (struct(_col2,_col4)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -2622,7 +2622,7 @@ STAGE PLANS: key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) auto parallelism: false @@ -2659,13 +2659,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 540 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2714,40 +2714,40 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: PARTIAL tag: 0 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), key (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) auto parallelism: false @@ -2960,11 +2960,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 60 Data size: 1620 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator isSamplingPred: false predicate: (struct(_col0,_col3)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -2993,7 +2993,7 @@ STAGE PLANS: key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string) auto parallelism: false @@ -3030,13 +3030,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/pointlookup3.q.out b/ql/src/test/results/clientpositive/pointlookup3.q.out index 855e2da0bf..2efd76aa6e 100644 --- a/ql/src/test/results/clientpositive/pointlookup3.q.out +++ b/ql/src/test/results/clientpositive/pointlookup3.q.out @@ -67,21 +67,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n1 filterExpr: (((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -194,13 +194,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -252,21 +252,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n1 filterExpr: ((ds2 = '2001-04-08') and (((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2)))) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = 1) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -329,13 +329,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -392,44 +392,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string), _col3 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds2 = '2001-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string), _col2 (type: string) auto parallelism: false @@ -496,11 +496,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -529,7 +529,7 @@ STAGE PLANS: key expressions: _col3 (type: int), _col4 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) auto parallelism: false @@ -566,13 +566,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), '2001-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -629,44 +629,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string), _col3 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds1 = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string), _col3 (type: string) auto parallelism: false @@ -783,11 +783,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -816,7 +816,7 @@ STAGE PLANS: key expressions: _col3 (type: int), _col4 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) auto parallelism: false @@ -853,13 +853,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2000-04-09' (type: string), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -916,36 +916,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds1 = '2000-04-08') or (ds1 = '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 27720 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4620 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4620 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4620 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) auto parallelism: false @@ -1112,11 +1112,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2400 Data size: 40800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 400 Data size: 369600 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator isSamplingPred: false predicate: (((_col2 = '2000-04-08') and (_col4 = 1)) or ((_col2 = '2000-04-09') and (_col4 = 2))) (type: boolean) - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 36960 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -1145,7 +1145,7 @@ STAGE PLANS: key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 36960 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) auto parallelism: false @@ -1182,13 +1182,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 36960 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 36960 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1461,21 +1461,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n1 filterExpr: ((struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds1)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -1588,13 +1588,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1641,21 +1641,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n1 filterExpr: ((struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds2 = '2001-04-08')) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -1718,13 +1718,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1781,44 +1781,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string), _col3 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds2 = '2001-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string), _col2 (type: string) auto parallelism: false @@ -1885,11 +1885,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -1918,7 +1918,7 @@ STAGE PLANS: key expressions: _col3 (type: int), _col4 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) auto parallelism: false @@ -1955,13 +1955,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), '2001-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2018,44 +2018,44 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string), _col3 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: ((ds1 = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string), _col3 (type: string) auto parallelism: false @@ -2172,11 +2172,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -2205,7 +2205,7 @@ STAGE PLANS: key expressions: _col3 (type: int), _col4 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) auto parallelism: false @@ -2242,13 +2242,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2000-04-09' (type: string), VALUE._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2297,36 +2297,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (ds1) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) auto parallelism: false TableScan alias: t2 filterExpr: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 27720 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) auto parallelism: false @@ -2493,11 +2493,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2400 Data size: 40800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 332640 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator isSamplingPred: false predicate: (struct(_col2,_col4)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -2526,7 +2526,7 @@ STAGE PLANS: key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) null sort order: aaa sort order: +++ - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) auto parallelism: false @@ -2563,13 +2563,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1200 Data size: 20400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/pointlookup4.q.out b/ql/src/test/results/clientpositive/pointlookup4.q.out index 63a0e37f2f..bf87d67025 100644 --- a/ql/src/test/results/clientpositive/pointlookup4.q.out +++ b/ql/src/test/results/clientpositive/pointlookup4.q.out @@ -67,21 +67,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n0 filterExpr: (((ds1 = '2000-04-08') and (ds2 = '2001-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (ds2 = '2001-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (((ds1 = '2000-04-08') and (ds2 = '2001-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (ds2 = '2001-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -194,13 +194,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -266,21 +266,21 @@ STAGE PLANS: TableScan alias: pcr_t1_n0 filterExpr: ((struct(key,ds1,ds2)) IN (const struct(1,'2000-04-08','2001-04-08'), const struct(2,'2000-04-09','2001-04-09')) and (struct(ds1,ds2)) IN (struct('2000-04-08','2001-04-08'), struct('2000-04-09','2001-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (struct(key,ds1,ds2)) IN (const struct(1,'2000-04-08','2001-04-08'), const struct(2,'2000-04-09','2001-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -393,13 +393,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/position_alias_test_1.q.out b/ql/src/test/results/clientpositive/position_alias_test_1.q.out index 9e6fa762dd..eb394e44c9 100644 --- a/ql/src/test/results/clientpositive/position_alias_test_1.q.out +++ b/ql/src/test/results/clientpositive/position_alias_test_1.q.out @@ -59,32 +59,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alias_test_02 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: b (type: string) outputColumnNames: b - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: b (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 2017 (type: int), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -97,19 +97,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alias01 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -122,7 +122,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 373 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -138,20 +138,20 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 373 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) TableScan alias: alias03 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -161,10 +161,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd1.q.out b/ql/src/test/results/clientpositive/ppd1.q.out index 752ec31e3b..41dd06a7ae 100644 --- a/ql/src/test/results/clientpositive/ppd1.q.out +++ b/ql/src/test/results/clientpositive/ppd1.q.out @@ -15,17 +15,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -444,17 +444,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd2.q.out b/ql/src/test/results/clientpositive/ppd2.q.out index 2bed372c3a..844ce62944 100644 --- a/ql/src/test/results/clientpositive/ppd2.q.out +++ b/ql/src/test/results/clientpositive/ppd2.q.out @@ -37,22 +37,22 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -61,13 +61,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 1L) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -282,17 +282,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: UDFToInteger(key) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -323,28 +323,28 @@ STAGE PLANS: TableScan alias: x filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 20) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: y filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 20) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -353,11 +353,11 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -373,17 +373,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -434,22 +434,22 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(value) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -458,13 +458,13 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 1L) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_clusterby.q.out b/ql/src/test/results/clientpositive/ppd_clusterby.q.out index 0440e286f4..9bdb3ceb85 100644 --- a/ql/src/test/results/clientpositive/ppd_clusterby.q.out +++ b/ql/src/test/results/clientpositive/ppd_clusterby.q.out @@ -15,29 +15,29 @@ STAGE PLANS: TableScan alias: x filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 10) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -76,28 +76,28 @@ STAGE PLANS: TableScan alias: x filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = 20) and key is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: y filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = 20) and key is not null) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -106,14 +106,14 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 = 20) (type: boolean) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -129,17 +129,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -177,29 +177,29 @@ STAGE PLANS: TableScan alias: x filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 10) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -238,28 +238,28 @@ STAGE PLANS: TableScan alias: x filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 20) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: y filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 20) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -268,11 +268,11 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -288,17 +288,17 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_constant_expr.q.out b/ql/src/test/results/clientpositive/ppd_constant_expr.q.out index f59ef81145..9bcedc0ffe 100644 --- a/ql/src/test/results/clientpositive/ppd_constant_expr.q.out +++ b/ql/src/test/results/clientpositive/ppd_constant_expr.q.out @@ -30,14 +30,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: string), UDFToInteger((UDFToDouble(key) - null)) (type: int), null (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -46,25 +46,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) outputColumnNames: c1, c2, c3 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -197,14 +197,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: string), UDFToInteger((UDFToDouble(key) - null)) (type: int), null (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -213,25 +213,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) outputColumnNames: c1, c2, c3 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_gby.q.out b/ql/src/test/results/clientpositive/ppd_gby.q.out index 239a8d9b30..953454beb2 100644 --- a/ql/src/test/results/clientpositive/ppd_gby.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby.q.out @@ -21,21 +21,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -44,17 +44,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 < 'val_400') or (_col1 > 30L)) (type: boolean) - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -232,21 +232,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -255,17 +255,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 < 'val_400') or (_col1 > 30L)) (type: boolean) - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_gby2.q.out b/ql/src/test/results/clientpositive/ppd_gby2.q.out index 7526d263dd..56792dfbc2 100644 --- a/ql/src/test/results/clientpositive/ppd_gby2.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby2.q.out @@ -24,21 +24,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -47,16 +47,16 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 < 'val_400') or (_col1 > 30L)) (type: boolean) - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col0) keys: _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -72,7 +72,7 @@ STAGE PLANS: key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -81,14 +81,14 @@ STAGE PLANS: keys: KEY._col0 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -147,21 +147,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -170,16 +170,16 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 < 'val_400') or (_col1 > 30L)) (type: boolean) - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col0) keys: _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -195,7 +195,7 @@ STAGE PLANS: key expressions: _col0 (type: bigint) sort order: + Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: @@ -204,14 +204,14 @@ STAGE PLANS: keys: KEY._col0 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_gby_join.q.out b/ql/src/test/results/clientpositive/ppd_gby_join.q.out index a6b3c6670b..3dbf3f59a7 100644 --- a/ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -30,35 +30,35 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value < 'val_50') or (key > '2')) and (key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -67,13 +67,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -89,7 +89,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -98,10 +98,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -296,35 +296,35 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value < 'val_50') or (key > '2')) and (key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -333,13 +333,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -355,7 +355,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -364,10 +364,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2565 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join.q.out b/ql/src/test/results/clientpositive/ppd_join.q.out index 065e53accd..71d8dac8d3 100644 --- a/ql/src/test/results/clientpositive/ppd_join.q.out +++ b/ql/src/test/results/clientpositive/ppd_join.q.out @@ -27,35 +27,35 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value < 'val_50') or (key > '2')) and (key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -65,14 +65,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -551,35 +551,35 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key < '400') and (key > '20') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value < 'val_50') or (key > '2')) and (key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 382 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '4') and (key > '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -589,14 +589,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join2.q.out b/ql/src/test/results/clientpositive/ppd_join2.q.out index 1dbedea5b1..56f37b25fe 100644 --- a/ql/src/test/results/clientpositive/ppd_join2.q.out +++ b/ql/src/test/results/clientpositive/ppd_join2.q.out @@ -34,36 +34,36 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311')) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value <> 'val_50') or (key > '1')) and (key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -73,10 +73,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -92,24 +92,24 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: src filterExpr: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -118,14 +118,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1717,36 +1717,36 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key <> '305') and (key <> '302') and (key < '400') and (key <> '14') and (key <> '311')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311')) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: ((key <> '302') and (key < '400') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and (key <> '14') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value <> 'val_50') or (key > '1')) and (key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1756,10 +1756,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1775,24 +1775,24 @@ STAGE PLANS: key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: src filterExpr: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1801,14 +1801,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 270 Data size: 48060 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join3.q.out b/ql/src/test/results/clientpositive/ppd_join3.q.out index bf58c1f1b2..dea5cf95ea 100644 --- a/ql/src/test/results/clientpositive/ppd_join3.q.out +++ b/ql/src/test/results/clientpositive/ppd_join3.q.out @@ -33,51 +33,51 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key <> '13') and (key <> '11') and (key < '400') and (key <> '12') and (key <> '1') and (key > '0') and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and (key <> '4') and (key > '0')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value <> 'val_500') or (key > '1')) and (key < '400') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and (key <> '4') and (key > '0')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key <> '12') and (key <> '11') and (key < '400') and (key <> '13') and (key <> '4') and (key > '0') and (key <> '1')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and (key <> '4') and (key > '0')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -89,17 +89,17 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 <> '10') or (_col2 > '10')) (type: boolean) - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1747,51 +1747,51 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key <> '13') and (key <> '11') and (key < '400') and (key <> '12') and (key <> '1') and (key > '0') and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and (key <> '4') and (key > '0')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key <> '11') and (key < '400') and (key <> '12') and (key <> '13') and (key > '0') and ((value <> 'val_500') or (key > '1')) and (key <> '4') and (key <> '1')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value <> 'val_500') or (key > '1')) and (key < '400') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and (key <> '4') and (key > '0')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key <> '12') and (key <> '11') and (key < '400') and (key <> '13') and (key <> '4') and (key > '0') and (key <> '1')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '400') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and (key <> '4') and (key > '0')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1803,17 +1803,17 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 <> '10') or (_col2 > '10')) (type: boolean) - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join4.q.out b/ql/src/test/results/clientpositive/ppd_join4.q.out index 56a1905885..d09bea7127 100644 --- a/ql/src/test/results/clientpositive/ppd_join4.q.out +++ b/ql/src/test/results/clientpositive/ppd_join4.q.out @@ -55,29 +55,29 @@ STAGE PLANS: TableScan alias: test_tbl filterExpr: ((name = 'c') and (id = 'a')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((id = 'a') and (name = 'c')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 'a' (type: string) sort order: + Map-reduce partition columns: 'a' (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t3 filterExpr: (id = 'a') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (id = 'a') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 'a' (type: string) sort order: + Map-reduce partition columns: 'a' (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -85,14 +85,14 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 id (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'a' (type: string), 'c' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join5.q.out b/ql/src/test/results/clientpositive/ppd_join5.q.out index a8486638bf..00e23e936a 100644 --- a/ql/src/test/results/clientpositive/ppd_join5.q.out +++ b/ql/src/test/results/clientpositive/ppd_join5.q.out @@ -55,32 +55,32 @@ STAGE PLANS: TableScan alias: a filterExpr: (id1 is not null and id2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (id1 is not null and id2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id1 (type: string), id2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: c filterExpr: (d <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (d <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -90,7 +90,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -106,24 +106,24 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) TableScan alias: b filterExpr: ((d <= 1) and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d <= 1) and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), d (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col0 (type: string) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -133,14 +133,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,31 +178,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id1 (type: string), id2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: d (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -212,7 +212,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -228,23 +228,23 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int) TableScan alias: b - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), d (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col0 (type: string) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -254,14 +254,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_join_filter.q.out b/ql/src/test/results/clientpositive/ppd_join_filter.q.out index 3c22bc10d6..c4f65cd954 100644 --- a/ql/src/test/results/clientpositive/ppd_join_filter.q.out +++ b/ql/src/test/results/clientpositive/ppd_join_filter.q.out @@ -45,24 +45,24 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -127,15 +127,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -161,22 +161,22 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan @@ -186,7 +186,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: double), _col2 (type: double) auto parallelism: false @@ -275,17 +275,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -390,24 +390,24 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -472,15 +472,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -506,22 +506,22 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan @@ -531,7 +531,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: double), _col2 (type: double) auto parallelism: false @@ -620,17 +620,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -734,24 +734,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -816,15 +816,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -849,22 +849,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan @@ -874,7 +874,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: double), _col2 (type: double) auto parallelism: false @@ -963,17 +963,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1078,24 +1078,24 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(key) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -1160,15 +1160,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -1194,22 +1194,22 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan @@ -1219,7 +1219,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: double), _col2 (type: double) auto parallelism: false @@ -1308,17 +1308,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/ppd_multi_insert.q.out b/ql/src/test/results/clientpositive/ppd_multi_insert.q.out index 4a3ed61e89..c902b39c93 100644 --- a/ql/src/test/results/clientpositive/ppd_multi_insert.q.out +++ b/ql/src/test/results/clientpositive/ppd_multi_insert.q.out @@ -64,28 +64,28 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -94,17 +94,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -113,12 +113,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -127,14 +127,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col0 < 200) and (_col0 >= 100)) (type: boolean) - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -143,12 +143,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -157,14 +157,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col0 < 300) and (_col0 >= 200)) (type: boolean) - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -173,13 +173,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: key - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') keys: '2008-04-08' (type: string), '12' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -188,14 +188,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (_col0 >= 300) (type: boolean) - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -225,7 +225,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -233,10 +233,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -274,7 +274,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -282,10 +282,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -312,7 +312,7 @@ STAGE PLANS: key expressions: '2008-04-08' (type: string), '12' (type: string) sort order: ++ Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -321,14 +321,14 @@ STAGE PLANS: keys: '2008-04-08' (type: string), '12' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 318 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 318 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 318 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1471,28 +1471,28 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1501,17 +1501,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1520,12 +1520,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1534,14 +1534,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col0 < 200) and (_col0 >= 100)) (type: boolean) - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1550,12 +1550,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1564,14 +1564,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: ((_col0 < 300) and (_col0 >= 200)) (type: boolean) - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1580,13 +1580,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: key - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') keys: '2008-04-08' (type: string), '12' (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1595,14 +1595,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (_col0 >= 300) (type: boolean) - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 183 Data size: 1944 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1632,7 +1632,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1640,10 +1640,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1681,7 +1681,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1689,10 +1689,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1719,7 +1719,7 @@ STAGE PLANS: key expressions: '2008-04-08' (type: string), '12' (type: string) sort order: ++ Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) - Statistics: Num rows: 61 Data size: 648 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1728,14 +1728,14 @@ STAGE PLANS: keys: '2008-04-08' (type: string), '12' (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 318 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 318 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 318 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_outer_join1.q.out b/ql/src/test/results/clientpositive/ppd_outer_join1.q.out index 2d0ffcd334..5305a12132 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join1.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join1.q.out @@ -27,36 +27,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -66,10 +66,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -136,36 +136,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -175,10 +175,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_outer_join2.q.out b/ql/src/test/results/clientpositive/ppd_outer_join2.q.out index a6e10af807..c60bd83732 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join2.q.out @@ -27,36 +27,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -66,10 +66,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -256,36 +256,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -295,10 +295,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_outer_join3.q.out b/ql/src/test/results/clientpositive/ppd_outer_join3.q.out index 33d0e9ad81..7d2c98a2c9 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join3.q.out @@ -27,36 +27,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -66,10 +66,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -256,36 +256,36 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -295,10 +295,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_outer_join4.q.out b/ql/src/test/results/clientpositive/ppd_outer_join4.q.out index de799fd5ca..8f00821afb 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join4.q.out @@ -33,52 +33,52 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: c filterExpr: ((sqrt(key) <> 13.0D) and (key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -90,14 +90,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -400,52 +400,52 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: c filterExpr: ((sqrt(key) <> 13.0D) and (key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -457,14 +457,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 24365 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_outer_join5.q.out b/ql/src/test/results/clientpositive/ppd_outer_join5.q.out index 35decf23ef..a4e36d938d 100644 --- a/ql/src/test/results/clientpositive/ppd_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/ppd_outer_join5.q.out @@ -48,32 +48,32 @@ STAGE PLANS: TableScan alias: t1_n98 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 20 (type: int), key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) TableScan alias: t2_n61 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -86,7 +86,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -100,22 +100,22 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: string) TableScan alias: t3_n23 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -125,14 +125,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col7, _col8 - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col4 (type: string), _col5 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -162,32 +162,32 @@ STAGE PLANS: TableScan alias: t1_n98 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: t3_n23 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 20 (type: int), key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -197,7 +197,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -211,22 +211,22 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) TableScan alias: t2_n61 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -236,14 +236,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7, _col8 - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -273,32 +273,32 @@ STAGE PLANS: TableScan alias: t1_n98 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) TableScan alias: t3_n23 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 20 (type: int), key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -308,7 +308,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -322,22 +322,22 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) TableScan alias: t2_n61 filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -347,14 +347,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7, _col8 - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 20 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col7 (type: string), _col8 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 2 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_random.q.out b/ql/src/test/results/clientpositive/ppd_random.q.out index 6075646420..164f0cc408 100644 --- a/ql/src/test/results/clientpositive/ppd_random.q.out +++ b/ql/src/test/results/clientpositive/ppd_random.q.out @@ -27,35 +27,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -65,17 +65,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 46636 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (rand() > 0.5D) (type: boolean) - Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -116,35 +116,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -154,17 +154,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 46636 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (rand() > 0.5D) (type: boolean) - Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out b/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out index ccecfede51..4712d7ce02 100644 --- a/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out +++ b/ql/src/test/results/clientpositive/ppd_repeated_alias.q.out @@ -45,35 +45,35 @@ STAGE PLANS: TableScan alias: a filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -82,14 +82,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -126,35 +126,35 @@ STAGE PLANS: TableScan alias: a filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -163,14 +163,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -207,35 +207,35 @@ STAGE PLANS: TableScan alias: a filterExpr: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -244,14 +244,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), 3 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -280,35 +280,35 @@ STAGE PLANS: TableScan alias: b filterExpr: ((bar = 2) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((bar = 2) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE TableScan alias: c filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: foo (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -317,7 +317,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -331,22 +331,22 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: int) TableScan alias: d filterExpr: (foo = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (foo = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bar (type: int) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -356,14 +356,14 @@ STAGE PLANS: 0 1 outputColumnNames: _col2, _col4 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: int), _col4 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_transform.q.out b/ql/src/test/results/clientpositive/ppd_transform.q.out index 6d5da08faf..2b8ee6388f 100644 --- a/ql/src/test/results/clientpositive/ppd_transform.q.out +++ b/ql/src/test/results/clientpositive/ppd_transform.q.out @@ -26,35 +26,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -200,35 +200,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -369,34 +369,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0) IN ('a', 'b') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Filter Operator predicate: (_col0) IN ('c', 'd') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_udf_case.q.out b/ql/src/test/results/clientpositive/ppd_udf_case.q.out index 3dbe21ce32..6592e5a46b 100644 --- a/ql/src/test/results/clientpositive/ppd_udf_case.q.out +++ b/ql/src/test/results/clientpositive/ppd_udf_case.q.out @@ -37,32 +37,32 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (key = '27')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2008-04-08') and (key = '27')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1638 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string), hr (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col3 (type: string) TableScan alias: b filterExpr: ((ds = '2008-04-08') and (key = '27')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2008-04-08') and (key = '27')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1638 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string), hr (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator @@ -72,11 +72,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col3, _col5, _col7 - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -91,16 +91,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -188,32 +188,32 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (key = '27')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = '27') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string), hr (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col3 (type: string) TableScan alias: b filterExpr: ((ds = '2008-04-08') and (key = '27')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = '27') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string), hr (type: string) outputColumnNames: _col1, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator @@ -223,11 +223,11 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col3, _col5, _col7 - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -242,16 +242,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) sort order: ++++ - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 250000 Data size: 5562000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_udf_col.q.out b/ql/src/test/results/clientpositive/ppd_udf_col.q.out index dfc2d0465d..0f0adde6f0 100644 --- a/ql/src/test/results/clientpositive/ppd_udf_col.q.out +++ b/ql/src/test/results/clientpositive/ppd_udf_col.q.out @@ -19,20 +19,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 <= 0.1D) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -69,20 +69,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -115,17 +115,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double), '4' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -159,17 +159,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(value) * 10.0D) <= 200.0D) and (UDFToDouble(key) = 100.0D)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double), (UDFToDouble(value) * 10.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -203,20 +203,20 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 <= 0.1D) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -253,20 +253,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -299,17 +299,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double), '4' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -343,17 +343,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToDouble(value) * 10.0D) <= 200.0D) and (UDFToDouble(key) = 100.0D)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double), (UDFToDouble(value) * 10.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -387,24 +387,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col2 <= 0.1) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -442,27 +442,27 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 <= 0.1) and (_col2 > 0.1)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -495,17 +495,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double), '4' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -539,17 +539,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value * 10) <= 200.0D) and (key = 100)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double), (value * 10) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -583,24 +583,24 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col2 <= 0.1) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -638,30 +638,30 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col2 <= 0.1) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 > 0.1) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -694,24 +694,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = 100) and false) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), '4' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -745,24 +745,24 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((value * 10) <= 200.0D) and (key = 100)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), rand() (type: double), (value * 10) (type: double) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col3 <= 200.0D) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_udtf.q.out b/ql/src/test/results/clientpositive/ppd_udtf.q.out index 820faa8154..e0ca174c49 100644 --- a/ql/src/test/results/clientpositive/ppd_udtf.q.out +++ b/ql/src/test/results/clientpositive/ppd_udtf.q.out @@ -23,27 +23,27 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 400.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 400.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: array(key,value) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 318720 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 318720 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Filter Operator predicate: (UDFToDouble(col) < 450.0D) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 105600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: col (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_union.q.out b/ql/src/test/results/clientpositive/ppd_union.q.out index e56ebd871b..fa88b15e41 100644 --- a/ql/src/test/results/clientpositive/ppd_union.q.out +++ b/ql/src/test/results/clientpositive/ppd_union.q.out @@ -27,17 +27,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -270,17 +270,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppd_vc.q.out b/ql/src/test/results/clientpositive/ppd_vc.q.out index e8ea1baf60..5157d706b9 100644 --- a/ql/src/test/results/clientpositive/ppd_vc.q.out +++ b/ql/src/test/results/clientpositive/ppd_vc.q.out @@ -18,22 +18,22 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (BLOCK__OFFSET__INSIDE__FILE < 100L) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (BLOCK__OFFSET__INSIDE__FILE < 100L) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -343,43 +343,43 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan alias: srcpart filterExpr: ((BLOCK__OFFSET__INSIDE__FILE < 50L) and key is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((BLOCK__OFFSET__INSIDE__FILE < 50L) and key is not null) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 368964 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 368964 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) auto parallelism: false @@ -645,11 +645,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 732 Data size: 7782 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 732 Data size: 7782 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 @@ -678,7 +678,7 @@ STAGE PLANS: key expressions: _col2 (type: string), _col3 (type: string), _col4 (type: bigint) null sort order: aaa sort order: +++ - Statistics: Num rows: 732 Data size: 7782 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -715,13 +715,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 732 Data size: 7782 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 732 Data size: 7782 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/ppd_windowing1.q.out b/ql/src/test/results/clientpositive/ppd_windowing1.q.out index 5904e3269c..1d94f6301c 100644 --- a/ql/src/test/results/clientpositive/ppd_windowing1.q.out +++ b/ql/src/test/results/clientpositive/ppd_windowing1.q.out @@ -13,21 +13,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -47,14 +47,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -81,21 +81,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -115,14 +115,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -149,21 +149,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -183,14 +183,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -217,21 +217,21 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -251,14 +251,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -285,21 +285,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -319,14 +319,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(_col0) + 2) (type: int), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -353,21 +353,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -387,14 +387,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -421,21 +421,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -455,14 +455,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -489,21 +489,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -523,14 +523,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -557,21 +557,21 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -591,14 +591,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -625,21 +625,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -659,14 +659,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(_col0) + 2) (type: int), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -694,21 +694,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -728,11 +728,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string) outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -748,14 +748,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -775,14 +775,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -810,21 +810,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -844,11 +844,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string) outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -864,14 +864,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -891,14 +891,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -926,21 +926,21 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -960,11 +960,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string) outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -980,14 +980,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1007,14 +1007,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1042,21 +1042,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1076,11 +1076,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string) outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1096,14 +1096,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1123,14 +1123,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(_col1) + 2) (type: int), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1158,21 +1158,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1192,11 +1192,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1212,14 +1212,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1239,14 +1239,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1274,21 +1274,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1308,11 +1308,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1328,14 +1328,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1355,14 +1355,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1390,21 +1390,21 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1424,11 +1424,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1444,14 +1444,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1471,14 +1471,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1506,21 +1506,21 @@ STAGE PLANS: TableScan alias: src filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1540,11 +1540,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1560,14 +1560,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1587,14 +1587,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(_col1) + 2) (type: int), _col0 (type: double), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1621,18 +1621,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1652,11 +1652,11 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1672,14 +1672,14 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: sum_window_0 (type: double), _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: double), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 227000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1699,17 +1699,17 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 227000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: double), avg_window_1 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1735,19 +1735,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (UDFToDouble(key) + UDFToDouble(2)) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(2)) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1767,17 +1767,17 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1803,19 +1803,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (UDFToDouble(key) + UDFToDouble(value)) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(value)) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1835,17 +1835,17 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1871,18 +1871,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1902,17 +1902,17 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col0) + UDFToDouble(_col1)) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1938,19 +1938,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (UDFToDouble(key) + UDFToDouble(value)) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(value)) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -1970,17 +1970,17 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(_col0) + UDFToDouble(_col1)) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2006,19 +2006,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -2038,21 +2038,21 @@ STAGE PLANS: name: sum window function: GenericUDAFSumDouble window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToInteger(_col0) + UDFToInteger(_col1)) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToInteger(_col0) + UDFToInteger(_col1)) (type: int), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out index eef8c228a4..8f0e063084 100644 --- a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out +++ b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out @@ -30,22 +30,22 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and ((value like 'aaa%') or (value like 'vvv%'))) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -229,22 +229,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (((value like 'aaa%') or (value like 'vvv%')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 190000 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 190000 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/ppr_pushdown3.q.out b/ql/src/test/results/clientpositive/ppr_pushdown3.q.out index f802ff7984..d1d5e06739 100644 --- a/ql/src/test/results/clientpositive/ppr_pushdown3.q.out +++ b/ql/src/test/results/clientpositive/ppr_pushdown3.q.out @@ -13,17 +13,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -106,11 +106,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select * from srcpart @@ -2143,11 +2143,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select key from srcpart diff --git a/ql/src/test/results/clientpositive/ptf_matchpath.q.out b/ql/src/test/results/clientpositive/ptf_matchpath.q.out index 8d6f071f7e..87f889a7d0 100644 --- a/ql/src/test/results/clientpositive/ptf_matchpath.q.out +++ b/ql/src/test/results/clientpositive/ptf_matchpath.q.out @@ -66,18 +66,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_n0 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int) sort order: ++++ Map-reduce partition columns: fl_num (type: string) - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE value expressions: origin_city_name (type: string), arr_delay (type: float) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), VALUE._col2 (type: float), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -93,14 +93,14 @@ STAGE PLANS: partition by: _col6 raw input shape: referenced columns: _col0, _col6, _col2, _col3, _col4, tpath, _col5 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: origin_city_name (type: string), fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int), sz (type: int), tpath (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -184,18 +184,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_n0 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 0 (type: int), fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int) sort order: +++++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE value expressions: origin_city_name (type: string), arr_delay (type: float) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), VALUE._col2 (type: float), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -211,17 +211,17 @@ STAGE PLANS: partition by: 0 raw input shape: referenced columns: _col0, _col6, _col2, _col3, _col4, tpath, _col5 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (fl_num = 1142) (type: boolean) - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: origin_city_name (type: string), fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int), sz (type: int), tpath (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -293,25 +293,25 @@ STAGE PLANS: TableScan alias: flights_tiny_n0 filterExpr: (fl_num = -1142) (type: boolean) - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (fl_num = -1142) (type: boolean) - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: origin_city_name (type: string), year (type: int), month (type: int), day_of_month (type: int), arr_delay (type: float), fl_num (type: string) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 0 (type: int), _col6 (type: string), _col2 (type: int), _col3 (type: int), _col4 (type: int) sort order: +++++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col5 (type: float) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), VALUE._col2 (type: float), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -327,14 +327,14 @@ STAGE PLANS: partition by: 0 raw input shape: referenced columns: _col0, _col6, _col2, _col3, _col4, tpath, _col5 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: origin_city_name (type: string), fl_num (type: string), year (type: int), month (type: int), day_of_month (type: int), sz (type: int), tpath (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 53790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out b/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out index bf202ecd96..df72738c9e 100644 --- a/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out +++ b/ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out @@ -76,31 +76,31 @@ STAGE PLANS: TableScan alias: tlb1 filterExpr: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: fkey (type: int), id (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -116,24 +116,24 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: aaa filterExpr: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: fid (type: int), name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -143,14 +143,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -216,27 +216,27 @@ STAGE PLANS: TableScan alias: tlb1 filterExpr: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: id (type: int), fkey (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -256,11 +256,11 @@ STAGE PLANS: window function: GenericUDAFRowNumberEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), row_number_window_0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -276,24 +276,24 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int) TableScan alias: aaa filterExpr: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: fid (type: int), name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -303,14 +303,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col4 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -375,31 +375,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tlb1 - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: fkey (type: int), id (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -415,23 +415,23 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan alias: aaa - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: fid (type: int), name (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -441,14 +441,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/push_or.q.out b/ql/src/test/results/clientpositive/push_or.q.out index c59de9eb3a..eaa7489b21 100644 --- a/ql/src/test/results/clientpositive/push_or.q.out +++ b/ql/src/test/results/clientpositive/push_or.q.out @@ -49,21 +49,21 @@ STAGE PLANS: TableScan alias: push_or filterExpr: ((ds = '2000-04-09') or (key = 5)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2000-04-09') or (key = 5)) (type: boolean) - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: string) auto parallelism: false @@ -175,13 +175,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/query_result_fileformat.q.out b/ql/src/test/results/clientpositive/query_result_fileformat.q.out index a6d3a20068..071205b4ce 100644 --- a/ql/src/test/results/clientpositive/query_result_fileformat.q.out +++ b/ql/src/test/results/clientpositive/query_result_fileformat.q.out @@ -54,17 +54,17 @@ STAGE PLANS: TableScan alias: nzhang_test1 filterExpr: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'key1' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,17 +127,17 @@ STAGE PLANS: TableScan alias: nzhang_test1 filterExpr: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'key1' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/quote1.q.out b/ql/src/test/results/clientpositive/quote1.q.out index 1c23faccdb..caa259a21d 100644 --- a/ql/src/test/results/clientpositive/quote1.q.out +++ b/ql/src/test/results/clientpositive/quote1.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: src filterExpr: ((UDFToDouble(key) >= 200.0D) and (UDFToDouble(key) < 300.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 300.0D) and (UDFToDouble(key) >= 200.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -50,18 +50,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '2008-04-08' (type: string) outputColumnNames: location, type, table - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10395 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(location, 'hll'), compute_stats(type, 'hll') keys: table (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -69,14 +69,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -158,14 +158,14 @@ STAGE PLANS: TableScan alias: int filterExpr: (table = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (table = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: location (type: int), type (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: FROM src diff --git a/ql/src/test/results/clientpositive/quotedid_basic.q.out b/ql/src/test/results/clientpositive/quotedid_basic.q.out index b3b9b4258c..db2fb32982 100644 --- a/ql/src/test/results/clientpositive/quotedid_basic.q.out +++ b/ql/src/test/results/clientpositive/quotedid_basic.q.out @@ -37,11 +37,11 @@ STAGE PLANS: Processor Tree: TableScan alias: t1_n7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' @@ -59,17 +59,17 @@ STAGE PLANS: TableScan alias: t1_n7 filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -97,38 +97,38 @@ STAGE PLANS: TableScan alias: t1_n7 filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string) outputColumnNames: x+1, y&y - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: x+1 (type: string), y&y (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -158,31 +158,31 @@ STAGE PLANS: TableScan alias: t1_n7 filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string) outputColumnNames: x+1, y&y - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: x+1 (type: string), y&y (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -198,14 +198,14 @@ STAGE PLANS: key expressions: '1' (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: '1' (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -226,14 +226,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), '1' (type: string), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -263,31 +263,31 @@ STAGE PLANS: TableScan alias: t1_n7 filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: x+1 (type: string), y&y (type: string) outputColumnNames: x+1, y&y - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: x+1 (type: string), y&y (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -303,14 +303,14 @@ STAGE PLANS: key expressions: '1' (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: '1' (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -331,14 +331,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), '1' (type: string), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/quotedid_partition.q.out b/ql/src/test/results/clientpositive/quotedid_partition.q.out index 01406fe3a8..8fd15cbb53 100644 --- a/ql/src/test/results/clientpositive/quotedid_partition.q.out +++ b/ql/src/test/results/clientpositive/quotedid_partition.q.out @@ -42,38 +42,38 @@ STAGE PLANS: TableScan alias: src_p filterExpr: ((!@#$%^&*()_q = 'a') and (x+1 = '10')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (x+1 = '10') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: y&y (type: string) outputColumnNames: y&y - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: y&y (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '10' (type: string), _col0 (type: string), 'a' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/quotedid_skew.q.out b/ql/src/test/results/clientpositive/quotedid_skew.q.out index 902be6b533..36164929c9 100644 --- a/ql/src/test/results/clientpositive/quotedid_skew.q.out +++ b/ql/src/test/results/clientpositive/quotedid_skew.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: !@#$%^&*()_q is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q is not null and (!@#$%^&*()_q = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: !@#$%^&*()_q (type: string), y&y (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: !@#$%^&*()_q is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q is not null and (!@#$%^&*()_q = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: !@#$%^&*()_q (type: string), y&y (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q is not null and (not (!@#$%^&*()_q = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: !@#$%^&*()_q (type: string), y&y (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (!@#$%^&*()_q is not null and (not (!@#$%^&*()_q = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: !@#$%^&*()_q (type: string), y&y (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out index dc79ab2a71..a49b73ee58 100644 --- a/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out +++ b/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out @@ -15,22 +15,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (rand(1) < 0.1D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out index 414d2d2ab1..c9ffc2b82e 100644 --- a/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out +++ b/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out @@ -33,22 +33,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: (rand(1) < 0.1D) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -79,16 +79,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, hr, ds - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(hr, 'hll'), compute_stats(ds, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: PARTIAL tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -202,13 +202,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out index 3f6efd9a8f..a9fe70eaaf 100644 --- a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out +++ b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out @@ -15,22 +15,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D) and (rand(1) < 0.1D)) (type: boolean) - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 6516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 8208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 8208 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -142,22 +142,22 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 25080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 25080 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/rcfile_null_value.q.out b/ql/src/test/results/clientpositive/rcfile_null_value.q.out index 09398327ed..431613545d 100644 --- a/ql/src/test/results/clientpositive/rcfile_null_value.q.out +++ b/ql/src/test/results/clientpositive/rcfile_null_value.q.out @@ -100,36 +100,36 @@ STAGE PLANS: TableScan alias: src1 filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src2 filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 25.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -139,14 +139,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -155,12 +155,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -192,7 +192,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -200,10 +200,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/reduceSinkDeDuplication_pRS_key_empty.q.out b/ql/src/test/results/clientpositive/reduceSinkDeDuplication_pRS_key_empty.q.out index 7ff79f8b3f..54678e69db 100644 --- a/ql/src/test/results/clientpositive/reduceSinkDeDuplication_pRS_key_empty.q.out +++ b/ql/src/test/results/clientpositive/reduceSinkDeDuplication_pRS_key_empty.q.out @@ -53,30 +53,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(value, 5) (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(_col0, 'fm', 16), compute_stats(_col1, 'fm', 16), compute_stats(_col2, 'fm', 16), compute_stats(_col3, 'fm', 16) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1844 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1844 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -144,22 +144,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: substr(value, 5) (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -173,7 +173,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: string), _col2 (type: double), _col3 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -181,10 +181,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'fm', 16), compute_stats(VALUE._col3, 'fm', 16), compute_stats(VALUE._col4, 'fm', 16), compute_stats(VALUE._col5, 'fm', 16) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1844 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1844 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out index fef6bae8d3..66a987360b 100644 --- a/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out +++ b/ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out @@ -15,26 +15,26 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -53,10 +53,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -73,13 +73,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out index 9157b45113..e2ec376de7 100644 --- a/ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out +++ b/ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out @@ -22,35 +22,35 @@ STAGE PLANS: TableScan alias: f filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: g filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -59,12 +59,12 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -80,17 +80,17 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -128,35 +128,35 @@ STAGE PLANS: TableScan alias: f filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: g filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -165,12 +165,12 @@ STAGE PLANS: 0 _col1 (type: string), _col0 (type: string) 1 _col1 (type: string), _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -186,21 +186,21 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -245,27 +245,27 @@ STAGE PLANS: TableScan alias: src filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -279,25 +279,25 @@ STAGE PLANS: TableScan alias: f filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -306,12 +306,12 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -327,17 +327,17 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -389,27 +389,27 @@ STAGE PLANS: TableScan alias: src filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -425,13 +425,13 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -440,12 +440,12 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -461,17 +461,17 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -483,27 +483,27 @@ STAGE PLANS: TableScan alias: src filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -557,28 +557,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -592,12 +592,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -607,7 +607,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -622,16 +622,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: -+ - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 62500 Data size: 1390500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -642,28 +642,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: value (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -752,31 +752,31 @@ STAGE PLANS: TableScan alias: src filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: value (type: string), key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -792,28 +792,28 @@ STAGE PLANS: key expressions: _col1 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -822,12 +822,12 @@ STAGE PLANS: 0 _col1 (type: string), _col0 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -843,18 +843,18 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -867,26 +867,26 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string) sort order: -- - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Union - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string) sort order: -- - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -898,31 +898,31 @@ STAGE PLANS: TableScan alias: src filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: value (type: string), key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -938,28 +938,28 @@ STAGE PLANS: key expressions: _col1 (type: string), _col0 (type: string) sort order: ++ Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -968,12 +968,12 @@ STAGE PLANS: 0 _col1 (type: string), _col0 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -989,18 +989,18 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/regex_col.q.out b/ql/src/test/results/clientpositive/regex_col.q.out index 7c1801fc15..eb15e14a33 100644 --- a/ql/src/test/results/clientpositive/regex_col.q.out +++ b/ql/src/test/results/clientpositive/regex_col.q.out @@ -14,11 +14,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: EXPLAIN @@ -37,11 +37,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 757248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: EXPLAIN @@ -60,11 +60,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 757248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: EXPLAIN @@ -86,36 +86,36 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: string), _col3 (type: string) TableScan alias: b filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator @@ -125,14 +125,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col2, _col3, _col6, _col7 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -166,35 +166,35 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) = 103.0D) and hr is not null and ds is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (UDFToDouble(key) = 103.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) sort order: +++ Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: PARTIAL TableScan alias: b filterExpr: ((UDFToDouble(key) = 103.0D) and hr is not null and ds is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (UDFToDouble(key) = 103.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) sort order: +++ Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Operator Tree: Join Operator condition map: @@ -203,11 +203,11 @@ STAGE PLANS: 0 _col1 (type: string), _col2 (type: string), _col0 (type: string) 1 _col1 (type: string), _col2 (type: string), _col0 (type: string) outputColumnNames: _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false table: @@ -222,16 +222,16 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -295,11 +295,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: EXPLAIN @@ -318,11 +318,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: EXPLAIN @@ -341,11 +341,11 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: EXPLAIN @@ -364,28 +364,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/regexp_extract.q.out b/ql/src/test/results/clientpositive/regexp_extract.q.out index b76f0ffe7d..f18398bb9c 100644 --- a/ql/src/test/results/clientpositive/regexp_extract.q.out +++ b/ql/src/test/results/clientpositive/regexp_extract.q.out @@ -26,12 +26,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: @@ -45,17 +45,17 @@ STAGE PLANS: serialization.last.column.takes.rest true serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -117,13 +117,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), regexp_extract(VALUE._col1, 'val_(\d+\t\d+)', 1) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 44986 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 44986 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -279,12 +279,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string), 3 (type: int), 7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: @@ -298,17 +298,17 @@ STAGE PLANS: serialization.last.column.takes.rest true serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string) auto parallelism: false @@ -370,13 +370,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), regexp_extract(VALUE._col1, 'val_(\d+\t\d+)') (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 44986 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 44986 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/reloadJar.q.out b/ql/src/test/results/clientpositive/reloadJar.q.out index 878a5b5e20..a56c529df1 100644 --- a/ql/src/test/results/clientpositive/reloadJar.q.out +++ b/ql/src/test/results/clientpositive/reloadJar.q.out @@ -22,17 +22,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: example_iden(key) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/router_join_ppr.q.out b/ql/src/test/results/clientpositive/router_join_ppr.q.out index d592887c1e..55ab779e24 100644 --- a/ql/src/test/results/clientpositive/router_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/router_join_ppr.q.out @@ -34,44 +34,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -237,13 +237,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -341,44 +341,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -544,17 +544,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -652,44 +652,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -855,13 +855,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -959,44 +959,44 @@ STAGE PLANS: TableScan alias: a filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 111 Data size: 30192 Basic stats: COMPLETE Column stats: PARTIAL tag: 0 value expressions: _col1 (type: string) auto parallelism: false TableScan alias: b filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -1162,17 +1162,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/row__id.q.out b/ql/src/test/results/clientpositive/row__id.q.out index 7d296667a3..f0e3634ffc 100644 --- a/ql/src/test/results/clientpositive/row__id.q.out +++ b/ql/src/test/results/clientpositive/row__id.q.out @@ -62,24 +62,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: hello_acid - Statistics: Num rows: 3 Data size: 19860 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 19884 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID.writeid (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 19860 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 19884 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + - Statistics: Num rows: 3 Data size: 19860 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 19884 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 19860 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 19884 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 19860 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 19884 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,17 +125,17 @@ STAGE PLANS: TableScan alias: hello_acid filterExpr: (ROW__ID.writeid = 3) (type: boolean) - Statistics: Num rows: 3 Data size: 19860 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 19884 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ROW__ID.writeid = 3) (type: boolean) - Statistics: Num rows: 1 Data size: 6620 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 6628 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID.writeid (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 6620 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 6628 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 6620 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 6628 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out b/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out index dfda86fa91..6d440f65c6 100644 --- a/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out +++ b/ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out @@ -82,14 +82,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -102,14 +102,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -118,7 +118,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 105270 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -285,14 +285,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -305,14 +305,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -321,7 +321,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 105270 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -351,14 +351,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -368,14 +368,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -394,7 +394,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 105270 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -416,41 +416,41 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -461,7 +461,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 105270 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -485,14 +485,14 @@ STAGE PLANS: TableScan alias: t1_n94 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -504,14 +504,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -519,7 +519,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -591,14 +591,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -611,14 +611,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -627,7 +627,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 105270 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -664,14 +664,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -684,14 +684,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -700,7 +700,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 105270 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -730,14 +730,14 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -747,14 +747,14 @@ STAGE PLANS: TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -773,7 +773,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 105270 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/sample1.q.out b/ql/src/test/results/clientpositive/sample1.q.out index 9c4b2c5797..69614608fe 100644 --- a/ql/src/test/results/clientpositive/sample1.q.out +++ b/ql/src/test/results/clientpositive/sample1.q.out @@ -33,22 +33,22 @@ STAGE PLANS: TableScan alias: s filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(rand()) & 2147483647) % 1) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -79,16 +79,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: key, value, dt, hr - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(dt, 'hll'), compute_stats(hr, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) auto parallelism: false @@ -152,13 +152,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/sample3.q.out b/ql/src/test/results/clientpositive/sample3.q.out index 183ad2d45e..5b1c457e47 100644 --- a/ql/src/test/results/clientpositive/sample3.q.out +++ b/ql/src/test/results/clientpositive/sample3.q.out @@ -16,17 +16,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((hash(key) & 2147483647) % 5) = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/sample5.q.out b/ql/src/test/results/clientpositive/sample5.q.out index 7bb321d932..1ba69b55f7 100644 --- a/ql/src/test/results/clientpositive/sample5.q.out +++ b/ql/src/test/results/clientpositive/sample5.q.out @@ -32,22 +32,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 5) = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -78,16 +78,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -152,13 +152,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/sample6.q.out b/ql/src/test/results/clientpositive/sample6.q.out index a6a6f2cb90..9833eb9b57 100644 --- a/ql/src/test/results/clientpositive/sample6.q.out +++ b/ql/src/test/results/clientpositive/sample6.q.out @@ -30,23 +30,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 4) = 0) (type: boolean) sampleDesc: BUCKET 1 OUT OF 4 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -77,16 +77,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -151,13 +151,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -716,22 +716,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 4) = 3) (type: boolean) sampleDesc: BUCKET 4 OUT OF 4 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -795,13 +795,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1123,22 +1123,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -1202,13 +1202,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1754,21 +1754,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 3) = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -1832,13 +1832,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2266,21 +2266,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 3) = 1) (type: boolean) - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -2344,13 +2344,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2717,22 +2717,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -2796,13 +2796,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3095,22 +3095,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 4) = 1) (type: boolean) sampleDesc: BUCKET 2 OUT OF 4 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Execution mode: vectorized @@ -3174,13 +3174,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -3364,22 +3364,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) null sort order: aa sort order: ++ - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Execution mode: vectorized @@ -3443,13 +3443,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/sample7.q.out b/ql/src/test/results/clientpositive/sample7.q.out index e198b1f773..62e34b5e1b 100644 --- a/ql/src/test/results/clientpositive/sample7.q.out +++ b/ql/src/test/results/clientpositive/sample7.q.out @@ -33,22 +33,22 @@ STAGE PLANS: TableScan alias: s filterExpr: (key > 100) (type: boolean) - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((((hash(key) & 2147483647) % 4) = 0) and (key > 100)) (type: boolean) - Statistics: Num rows: 166 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 166 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -79,16 +79,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 1760 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -153,13 +153,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/sample8.q.out b/ql/src/test/results/clientpositive/sample8.q.out index d3a5251a8f..7366f437d2 100644 --- a/ql/src/test/results/clientpositive/sample8.q.out +++ b/ql/src/test/results/clientpositive/sample8.q.out @@ -21,34 +21,34 @@ STAGE PLANS: TableScan alias: s filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: ((((hash(key) & 2147483647) % 1) = 0) and (((hash(key) & 2147483647) % 10) = 0) and value is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string), value (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 auto parallelism: false TableScan alias: t - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: true predicate: ((((hash(key) & 2147483647) % 1) = 0) and (((hash(key) & 2147483647) % 10) = 0) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: key (type: string), value (type: string) null sort order: aa sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: PARTIAL tag: 1 auto parallelism: false Path -> Alias: @@ -264,21 +264,21 @@ STAGE PLANS: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col7, _col8 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 197 Data size: 70132 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator isSamplingPred: false predicate: ((_col7 = _col0) and (_col8 = _col1)) (type: boolean) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: PARTIAL #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -670,29 +670,29 @@ STAGE PLANS: alias: a filterExpr: key is not null (type: boolean) Row Limit Per Split: 100 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) Row Limit Per Split: 10 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -702,14 +702,14 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -755,29 +755,29 @@ STAGE PLANS: alias: a filterExpr: key is not null (type: boolean) Row Limit Per Split: 100 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) Row Limit Per Split: 10 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) Reduce Operator Tree: Join Operator @@ -787,17 +787,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 = _col5) (type: boolean) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/sample9.q.out b/ql/src/test/results/clientpositive/sample9.q.out index 4819dc1353..b72a02d285 100644 --- a/ql/src/test/results/clientpositive/sample9.q.out +++ b/ql/src/test/results/clientpositive/sample9.q.out @@ -16,23 +16,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/script_pipe.q.out b/ql/src/test/results/clientpositive/script_pipe.q.out index 984934ee74..a439aefef2 100644 --- a/ql/src/test/results/clientpositive/script_pipe.q.out +++ b/ql/src/test/results/clientpositive/script_pipe.q.out @@ -12,17 +12,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -30,20 +30,20 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: true output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -69,21 +69,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), key (type: string), value (type: string), key (type: string), value (type: string), key (type: string), value (type: string), key (type: string), value (type: string), key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 534000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: head -n 1 output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 534000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 534000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/select_as_omitted.q.out b/ql/src/test/results/clientpositive/select_as_omitted.q.out index e89affe66e..858cda6bba 100644 --- a/ql/src/test/results/clientpositive/select_as_omitted.q.out +++ b/ql/src/test/results/clientpositive/select_as_omitted.q.out @@ -22,15 +22,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -38,13 +38,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/select_column_pruning.q.out b/ql/src/test/results/clientpositive/select_column_pruning.q.out index 252bd4c059..565adf7b1e 100644 --- a/ql/src/test/results/clientpositive/select_column_pruning.q.out +++ b/ql/src/test/results/clientpositive/select_column_pruning.q.out @@ -41,57 +41,57 @@ STAGE PLANS: TableScan alias: lv_table1 filterExpr: (c3 = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 800156 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (c3 = 100) (type: boolean) - Statistics: Num rows: 250 Data size: 13000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 250 Data size: 13000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: string), c2 (type: array), c4 (type: char(1)), c5 (type: string), c6 (type: string), c7 (type: string), c8 (type: string), c9 (type: string), c10 (type: string), c11 (type: string) outputColumnNames: c1, c2, c4, c5, c6, c7, c8, c9, c10, c11 - Statistics: Num rows: 250 Data size: 13000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14 - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col14 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col11 (type: int) sort order: ++ - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 13000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 250 Data size: 13000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14 - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col14 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col11 (type: int) sort order: ++ - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), VALUE._col2 (type: char(1)), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 500 Data size: 26000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -106,7 +106,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col11 (type: int) sort order: ++ - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) Execution mode: vectorized @@ -114,13 +114,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), 100 (type: int), VALUE._col2 (type: char(1)), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/select_transform_hint.q.out b/ql/src/test/results/clientpositive/select_transform_hint.q.out index 7442996f17..8ee32bfa83 100644 --- a/ql/src/test/results/clientpositive/select_transform_hint.q.out +++ b/ql/src/test/results/clientpositive/select_transform_hint.q.out @@ -27,10 +27,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string) @@ -42,10 +42,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -53,17 +53,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1144,28 +1144,28 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1174,17 +1174,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/select_unquote_and.q.out b/ql/src/test/results/clientpositive/select_unquote_and.q.out index fbd3b6618a..89b2255e7f 100644 --- a/ql/src/test/results/clientpositive/select_unquote_and.q.out +++ b/ql/src/test/results/clientpositive/select_unquote_and.q.out @@ -54,17 +54,17 @@ STAGE PLANS: TableScan alias: npe_test_n0 filterExpr: ((UDFToDouble(ds) > 1970.0D) and (UDFToDouble(ds) < 1985.0D)) (type: boolean) - Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 498 Data size: 180276 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(ds) < 1985.0D) and (UDFToDouble(ds) > 1970.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/select_unquote_not.q.out b/ql/src/test/results/clientpositive/select_unquote_not.q.out index 57d7c5dda3..3b93ba2f8b 100644 --- a/ql/src/test/results/clientpositive/select_unquote_not.q.out +++ b/ql/src/test/results/clientpositive/select_unquote_not.q.out @@ -54,17 +54,17 @@ STAGE PLANS: TableScan alias: npe_test_n1 filterExpr: (UDFToDouble(ds) >= 1970.0D) (type: boolean) - Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 498 Data size: 180276 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(ds) >= 1970.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/select_unquote_or.q.out b/ql/src/test/results/clientpositive/select_unquote_or.q.out index 325c3e14b1..0e271aefa2 100644 --- a/ql/src/test/results/clientpositive/select_unquote_or.q.out +++ b/ql/src/test/results/clientpositive/select_unquote_or.q.out @@ -54,17 +54,17 @@ STAGE PLANS: TableScan alias: npe_test filterExpr: ((UDFToDouble(ds) > 1970.0D) or (UDFToDouble(ds) < 1985.0D)) (type: boolean) - Statistics: Num rows: 498 Data size: 5290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 498 Data size: 180276 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(ds) < 1985.0D) or (UDFToDouble(ds) > 1970.0D)) (type: boolean) - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 120184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 120184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 120184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/semijoin2.q.out b/ql/src/test/results/clientpositive/semijoin2.q.out index f4454f0f92..b9e50c1c88 100644 --- a/ql/src/test/results/clientpositive/semijoin2.q.out +++ b/ql/src/test/results/clientpositive/semijoin2.q.out @@ -61,28 +61,28 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (bigint_col_22 is not null and decimal1709_col_26 is not null and tinyint_col_8 is not null and timestamp_col_10 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (bigint_col_22 is not null and decimal1709_col_26 is not null and timestamp_col_10 is not null and tinyint_col_8 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) sort order: +++ Map-reduce partition columns: bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE value expressions: smallint_col_25 (type: smallint), double_col_61 (type: double), timestamp_col_10 (type: timestamp) TableScan alias: t2 filterExpr: (UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null and tinyint_col_33 is not null and UDFToInteger(smallint_col_38) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToInteger(smallint_col_38) is not null and UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null and tinyint_col_33 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) sort order: +++ Map-reduce partition columns: UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE value expressions: int_col_2 (type: int), smallint_col_38 (type: smallint) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) 1 UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) outputColumnNames: _col16, _col21, _col72, _col98, _col105 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -108,14 +108,14 @@ STAGE PLANS: key expressions: UDFToInteger(_col105) (type: int), _col72 (type: timestamp) sort order: ++ Map-reduce partition columns: UDFToInteger(_col105) (type: int), _col72 (type: timestamp) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE value expressions: _col16 (type: smallint), _col21 (type: double), _col98 (type: int) TableScan Reduce Output Operator key expressions: -92 (type: int), _col1 (type: timestamp) sort order: ++ Map-reduce partition columns: -92 (type: int), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -124,7 +124,7 @@ STAGE PLANS: 0 UDFToInteger(_col105) (type: int), _col72 (type: timestamp) 1 _col0 (type: int), _col1 (type: timestamp) outputColumnNames: _col16, _col21, _col98 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -140,14 +140,14 @@ STAGE PLANS: key expressions: (_col98 + _col16) (type: int), floor(_col21) (type: bigint) sort order: +- Map-reduce partition columns: (_col98 + _col16) (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE value expressions: _col16 (type: smallint), _col21 (type: double), _col98 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col16 (type: smallint), VALUE._col21 (type: double), VALUE._col98 (type: int) outputColumnNames: _col16, _col21, _col98 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -168,11 +168,11 @@ STAGE PLANS: window function: GenericUDAFLeadEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: LEAD_window_0 (type: int), _col16 (type: smallint), _col21 (type: double), _col98 (type: int) outputColumnNames: LEAD_window_0, _col16, _col21, _col98 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -188,13 +188,13 @@ STAGE PLANS: key expressions: (_col98 + _col16) (type: int), floor(_col21) (type: bigint) sort order: -- Map-reduce partition columns: (_col98 + _col16) (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE value expressions: LEAD_window_0 (type: int), _col16 (type: smallint), _col21 (type: double), _col98 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col17 (type: smallint), VALUE._col22 (type: double), VALUE._col99 (type: int) outputColumnNames: _col0, _col17, _col22, _col99 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -214,14 +214,14 @@ STAGE PLANS: name: SUM window function: GenericUDAFSumLong window frame: ROWS PRECEDING(MAX)~FOLLOWING(48) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: COALESCE(498,_col0,524) (type: int), (_col99 + _col17) (type: int), floor(_col22) (type: bigint), COALESCE(SUM_window_1,704) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -233,27 +233,27 @@ STAGE PLANS: TableScan alias: tt1 filterExpr: decimal1208_col_20 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: decimal1208_col_20 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: decimal1208_col_20 (type: decimal(38,6)) sort order: + Map-reduce partition columns: decimal1208_col_20 (type: decimal(38,6)) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan alias: tt2 filterExpr: (decimal1611_col_22 is not null and timestamp_col_18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal1611_col_22 is not null and timestamp_col_18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: decimal1611_col_22 (type: decimal(38,6)) sort order: + Map-reduce partition columns: decimal1611_col_22 (type: decimal(38,6)) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE value expressions: timestamp_col_18 (type: timestamp) Reduce Operator Tree: Join Operator @@ -263,16 +263,16 @@ STAGE PLANS: 0 decimal1208_col_20 (type: decimal(38,6)) 1 decimal1611_col_22 (type: decimal(38,6)) outputColumnNames: _col115 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col115 (type: timestamp) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: -92 (type: int), _col1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/semijoin3.q.out b/ql/src/test/results/clientpositive/semijoin3.q.out index 1cb89c497f..f2150398ab 100644 --- a/ql/src/test/results/clientpositive/semijoin3.q.out +++ b/ql/src/test/results/clientpositive/semijoin3.q.out @@ -58,31 +58,31 @@ STAGE PLANS: TableScan alias: t1_n59 filterExpr: (key = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 1 (type: int) sort order: + Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE TableScan alias: t2_n37 filterExpr: (key = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 1 (type: int) sort order: + Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 19 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -90,7 +90,7 @@ STAGE PLANS: keys: 0 1 (type: int) 1 1 (type: int) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) mode: hash diff --git a/ql/src/test/results/clientpositive/semijoin4.q.out b/ql/src/test/results/clientpositive/semijoin4.q.out index 802af357c7..aaaa12a4bb 100644 --- a/ql/src/test/results/clientpositive/semijoin4.q.out +++ b/ql/src/test/results/clientpositive/semijoin4.q.out @@ -70,36 +70,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: ((tinyint_col_46 = -92Y) and bigint_col_13 is not null and decimal1309_col_65 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((tinyint_col_46 = -92Y) and bigint_col_13 is not null and decimal1309_col_65 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bigint_col_13 (type: bigint), smallint_col_24 (type: smallint), double_col_60 (type: double), decimal1309_col_65 (type: decimal(13,9)) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: decimal(27,9)), _col0 (type: bigint) sort order: ++ Map-reduce partition columns: _col4 (type: decimal(27,9)), _col0 (type: bigint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: smallint), _col3 (type: double) TableScan alias: t2 filterExpr: ((tinyint_col_21 = -92Y) and tinyint_col_18 is not null and decimal2709_col_9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((tinyint_col_21 = -92Y) and decimal2709_col_9 is not null and tinyint_col_18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal2709_col_9 (type: decimal(27,9)), tinyint_col_18 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(27,9)), UDFToLong(_col1) (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(27,9)), UDFToLong(_col1) (type: bigint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -108,7 +108,7 @@ STAGE PLANS: 0 _col4 (type: decimal(27,9)), _col0 (type: bigint) 1 _col0 (type: decimal(27,9)), UDFToLong(_col1) (type: bigint) outputColumnNames: _col1, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 149 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -122,12 +122,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 149 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: smallint), _col3 (type: double) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -136,7 +136,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col3 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 317 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -152,14 +152,14 @@ STAGE PLANS: key expressions: (UDFToShort(UDFToByte(-92)) + _col1) (type: smallint), floor(_col3) (type: bigint) sort order: +- Map-reduce partition columns: (UDFToShort(UDFToByte(-92)) + _col1) (type: smallint) - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 317 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: smallint), _col3 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: smallint), VALUE._col3 (type: double) outputColumnNames: _col1, _col3 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 317 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -180,14 +180,14 @@ STAGE PLANS: window function: GenericUDAFLeadEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 317 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: COALESCE(498,LEAD_window_0,524) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 317 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 317 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -199,35 +199,35 @@ STAGE PLANS: TableScan alias: tt1 filterExpr: (decimal1309_col_65 is not null and timestamp_col_66 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal1309_col_65 is not null and timestamp_col_66 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal1309_col_65 (type: decimal(13,9)), timestamp_col_66 (type: timestamp) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(19,11)), _col1 (type: timestamp) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(19,11)), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE TableScan alias: tt2 filterExpr: (decimal1911_col_16 is not null and timestamp_col_19 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal1911_col_16 is not null and timestamp_col_19 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_19 (type: timestamp) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(19,11)), _col1 (type: timestamp) sort order: ++ Map-reduce partition columns: _col0 (type: decimal(19,11)), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -235,12 +235,12 @@ STAGE PLANS: keys: 0 _col0 (type: decimal(19,11)), _col1 (type: timestamp) 1 _col0 (type: decimal(19,11)), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: -92 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -256,16 +256,16 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/semijoin5.q.out b/ql/src/test/results/clientpositive/semijoin5.q.out index b4c7af846a..e5220d0695 100644 --- a/ql/src/test/results/clientpositive/semijoin5.q.out +++ b/ql/src/test/results/clientpositive/semijoin5.q.out @@ -61,36 +61,36 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (bigint_col_7 is not null and decimal2016_col_26 is not null and tinyint_col_3 is not null and timestamp_col_9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (bigint_col_7 is not null and decimal2016_col_26 is not null and timestamp_col_9 is not null and tinyint_col_3 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: tinyint_col_3 (type: tinyint), bigint_col_7 (type: bigint), timestamp_col_9 (type: timestamp), double_col_16 (type: double), decimal2016_col_26 (type: decimal(20,16)), smallint_col_50 (type: smallint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: timestamp), _col3 (type: double), _col5 (type: smallint) TableScan alias: t2 filterExpr: (tinyint_col_15 is not null and decimal2709_col_9 is not null and tinyint_col_20 is not null and smallint_col_19 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal2709_col_9 is not null and smallint_col_19 is not null and tinyint_col_15 is not null and tinyint_col_20 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal2709_col_9 (type: decimal(27,9)), int_col_10 (type: int), tinyint_col_15 (type: tinyint), smallint_col_19 (type: smallint), tinyint_col_20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) sort order: +++ Map-reduce partition columns: _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col3 (type: smallint) Reduce Operator Tree: Join Operator @@ -100,7 +100,7 @@ STAGE PLANS: 0 _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) 1 _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) outputColumnNames: _col2, _col3, _col5, _col7, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -116,14 +116,14 @@ STAGE PLANS: key expressions: _col2 (type: timestamp), UDFToInteger(_col9) (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: timestamp), UDFToInteger(_col9) (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: double), _col5 (type: smallint), _col7 (type: int) TableScan Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -132,7 +132,7 @@ STAGE PLANS: 0 _col2 (type: timestamp), UDFToInteger(_col9) (type: int) 1 _col0 (type: timestamp), _col1 (type: int) outputColumnNames: _col3, _col5, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -148,14 +148,14 @@ STAGE PLANS: key expressions: (_col7 + UDFToInteger(_col5)) (type: int), floor(_col3) (type: bigint) sort order: +- Map-reduce partition columns: (_col7 + UDFToInteger(_col5)) (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: double), _col5 (type: smallint), _col7 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col3 (type: double), VALUE._col5 (type: smallint), VALUE._col7 (type: int) outputColumnNames: _col3, _col5, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -176,11 +176,11 @@ STAGE PLANS: window function: GenericUDAFLeadEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: LEAD_window_0 (type: int), _col3 (type: double), _col5 (type: smallint), _col7 (type: int) outputColumnNames: LEAD_window_0, _col3, _col5, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -196,13 +196,13 @@ STAGE PLANS: key expressions: (_col7 + UDFToInteger(_col5)) (type: int), floor(_col3) (type: bigint) sort order: -- Map-reduce partition columns: (_col7 + UDFToInteger(_col5)) (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE value expressions: LEAD_window_0 (type: int), _col3 (type: double), _col5 (type: smallint), _col7 (type: int) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col4 (type: double), VALUE._col6 (type: smallint), VALUE._col8 (type: int) outputColumnNames: _col0, _col4, _col6, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -222,14 +222,14 @@ STAGE PLANS: name: sum window function: GenericUDAFSumLong window frame: ROWS PRECEDING(MAX)~FOLLOWING(48) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: COALESCE(498,_col0,524) (type: int), (_col8 + UDFToInteger(_col6)) (type: int), floor(_col4) (type: bigint), COALESCE(sum_window_1,704) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -241,35 +241,35 @@ STAGE PLANS: TableScan alias: tt1 filterExpr: decimal2612_col_77 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: decimal2612_col_77 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal2612_col_77 (type: decimal(26,12)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(26,12)) sort order: + Map-reduce partition columns: _col0 (type: decimal(26,12)) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan alias: tt2 filterExpr: (timestamp_col_18 is not null and decimal1911_col_16 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal1911_col_16 is not null and timestamp_col_18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_18 (type: timestamp) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(26,12)) sort order: + Map-reduce partition columns: _col0 (type: decimal(26,12)) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: timestamp) Reduce Operator Tree: Join Operator @@ -279,16 +279,16 @@ STAGE PLANS: 0 _col0 (type: decimal(26,12)) 1 _col0 (type: decimal(26,12)) outputColumnNames: _col2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: timestamp), -92 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: timestamp), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/serde_user_properties.q.out b/ql/src/test/results/clientpositive/serde_user_properties.q.out index 7acb443547..3e6a15fd05 100644 --- a/ql/src/test/results/clientpositive/serde_user_properties.q.out +++ b/ql/src/test/results/clientpositive/serde_user_properties.q.out @@ -14,12 +14,12 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select a.key from src a @@ -38,12 +38,12 @@ STAGE PLANS: Processor Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select a.key from src tablesample(1 percent) a @@ -60,18 +60,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -169,12 +169,12 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select key from src ('user.defined.key'='some.value') tablesample(1 percent) @@ -193,18 +193,18 @@ STAGE PLANS: alias: src properties: user.defined.key some.value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -304,12 +304,12 @@ STAGE PLANS: Processor Tree: TableScan alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain extended select a.key from src ('user.defined.key'='some.value') tablesample(1 percent) a @@ -328,18 +328,18 @@ STAGE PLANS: alias: a properties: user.defined.key some.value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/set_processor_namespaces.q.out b/ql/src/test/results/clientpositive/set_processor_namespaces.q.out index 2a611d4abb..db3dec827b 100644 --- a/ql/src/test/results/clientpositive/set_processor_namespaces.q.out +++ b/ql/src/test/results/clientpositive/set_processor_namespaces.q.out @@ -18,17 +18,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 5.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 5.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/set_variable_sub.q.out b/ql/src/test/results/clientpositive/set_variable_sub.q.out index 3550d09397..c4d8ba8f77 100644 --- a/ql/src/test/results/clientpositive/set_variable_sub.q.out +++ b/ql/src/test/results/clientpositive/set_variable_sub.q.out @@ -13,17 +13,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = 'value1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 'value1') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'value1' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -51,17 +51,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = 'value1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 'value1') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'value1' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -89,17 +89,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '1') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '1' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/setop_subq.q.out b/ql/src/test/results/clientpositive/setop_subq.q.out index 5ace690df6..3f53d0a8cd 100644 --- a/ql/src/test/results/clientpositive/setop_subq.q.out +++ b/ql/src/test/results/clientpositive/setop_subq.q.out @@ -12,51 +12,51 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -84,22 +84,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -108,7 +108,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -121,33 +121,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -155,17 +155,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -176,22 +176,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -200,7 +200,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -230,22 +230,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -254,7 +254,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -267,33 +267,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -301,17 +301,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -322,22 +322,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -346,7 +346,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -376,22 +376,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -400,7 +400,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -413,33 +413,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -447,17 +447,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col1 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -468,22 +468,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -492,7 +492,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -523,35 +523,35 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -560,10 +560,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin.q.out b/ql/src/test/results/clientpositive/skewjoin.q.out index fc59630459..2579fcdae5 100644 --- a/ql/src/test/results/clientpositive/skewjoin.q.out +++ b/ql/src/test/results/clientpositive/skewjoin.q.out @@ -94,35 +94,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -133,14 +133,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -149,12 +149,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -193,10 +193,10 @@ STAGE PLANS: Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -205,12 +205,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -244,17 +244,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,54 +304,54 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: d filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -365,14 +365,14 @@ STAGE PLANS: 2 key (type: string) 3 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -428,54 +428,54 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) TableScan alias: d filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: val (type: string) Reduce Operator Tree: Join Operator @@ -489,14 +489,14 @@ STAGE PLANS: 2 key (type: string) 3 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 990 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1214 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -545,28 +545,28 @@ STAGE PLANS: TableScan alias: a filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(key) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(key) (type: double) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: key (type: string), val (type: string) TableScan alias: c filterExpr: (key + 1) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key + 1) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: (key + 1) (type: double) sort order: + Map-reduce partition columns: (key + 1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string) Reduce Operator Tree: Join Operator @@ -576,7 +576,7 @@ STAGE PLANS: 0 UDFToDouble(key) (type: double) 1 (key + 1) (type: double) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col5)) mode: hash @@ -657,35 +657,35 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -696,12 +696,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -741,7 +741,7 @@ STAGE PLANS: aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -757,17 +757,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -827,35 +827,35 @@ STAGE PLANS: TableScan alias: src filterExpr: (key is not null and UDFToDouble(substring(value, 5)) is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(substring(value, 5)) is not null and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: (key is not null and (substring(value, 5) + 1) is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((substring(value, 5) + 1) is not null and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), (substring(_col1, 5) + 1) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), (substring(_col1, 5) + 1) (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -866,12 +866,12 @@ STAGE PLANS: 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) 1 _col0 (type: string), (substring(_col1, 5) + 1) (type: double) outputColumnNames: _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -911,7 +911,7 @@ STAGE PLANS: aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -927,17 +927,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1007,52 +1007,52 @@ STAGE PLANS: TableScan alias: src filterExpr: ((key < 80) and (key < 100)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 100) and (key < 80)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key < 100) and (key < 80)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 100) and (key < 80)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src filterExpr: ((key < 100) and (key < 80)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 100) and (key < 80)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1064,12 +1064,12 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0)), sum(hash(_col3)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1122,7 +1122,7 @@ STAGE PLANS: aggregations: sum(hash(_col0)), sum(hash(_col3)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1138,17 +1138,17 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1196,7 +1196,7 @@ STAGE PLANS: aggregations: sum(hash(_col0)), sum(hash(_col3)) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1259,7 +1259,7 @@ STAGE PLANS: v TableScan alias: v - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 (key + 1) (type: double) @@ -1270,7 +1270,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: k - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -1278,7 +1278,7 @@ STAGE PLANS: 0 (key + 1) (type: double) 1 UDFToDouble(key) (type: double) outputColumnNames: _col0, _col6 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(hash(_col0)), sum(hash(_col6)) mode: hash diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out index df40ba850a..a7b113234c 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -75,14 +75,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -94,14 +94,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -109,26 +109,26 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -136,12 +136,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -198,14 +198,14 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -213,14 +213,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -231,14 +231,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -246,26 +246,26 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -273,12 +273,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -338,14 +338,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -353,14 +353,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -372,23 +372,23 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -400,23 +400,23 @@ STAGE PLANS: value expressions: _col0 (type: bigint) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -484,14 +484,14 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -499,14 +499,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -517,23 +517,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -545,23 +545,23 @@ STAGE PLANS: value expressions: _col0 (type: bigint) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out index b53e83b0e6..bf79da9438 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out @@ -92,14 +92,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 2) or (key = 3)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -107,14 +107,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((not ((key = 2) or (key = 3))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -126,14 +126,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 2) or (key = 3)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -141,26 +141,26 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((not ((key = 2) or (key = 3))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -168,12 +168,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -230,14 +230,14 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -245,14 +245,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -263,14 +263,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -278,26 +278,26 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -305,12 +305,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -370,14 +370,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 2) or (key = 3)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -385,14 +385,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((not ((key = 2) or (key = 3))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -404,59 +404,59 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 2) or (key = 3)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((not ((key = 2) or (key = 3))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work @@ -465,10 +465,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -516,14 +516,14 @@ STAGE PLANS: $hdt$_0:a TableScan alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -531,14 +531,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -549,59 +549,59 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work @@ -610,10 +610,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out index cfa3ffca67..8b57e7a52d 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -75,14 +75,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -94,14 +94,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -109,26 +109,26 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -136,12 +136,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out index 78f20cc96d..e8eae27871 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -75,14 +75,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -94,14 +94,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -109,26 +109,26 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -136,12 +136,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -191,35 +191,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '8')) or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '8')) or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -229,7 +229,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -242,20 +242,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -266,42 +266,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out index 9fa2d3ea90..be602f3aa2 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out @@ -60,14 +60,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -75,14 +75,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -94,14 +94,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -109,26 +109,26 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -136,12 +136,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out index aa3819d753..3e582fb3f1 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out @@ -82,14 +82,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -99,14 +99,14 @@ STAGE PLANS: TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -115,14 +115,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -131,14 +131,14 @@ STAGE PLANS: subquery1:c TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -151,14 +151,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -168,26 +168,26 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -197,12 +197,12 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out index accab1f377..426ff4df6b 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out @@ -67,14 +67,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -86,16 +86,16 @@ STAGE PLANS: TableScan alias: t1_n87 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -103,10 +103,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -114,16 +114,16 @@ STAGE PLANS: TableScan alias: t1_n87 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -131,10 +131,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -211,21 +211,21 @@ STAGE PLANS: TableScan alias: t1_n87 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -234,7 +234,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -253,14 +253,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -277,10 +277,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out index c9de4c7fc5..6b99e18bcb 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out @@ -62,10 +62,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '8') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -73,10 +73,10 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '8')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -88,10 +88,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '8') and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -99,25 +99,25 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col6 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col6 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,26 +125,26 @@ STAGE PLANS: Select Operator expressions: _col1 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '8')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2104 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -152,25 +152,25 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col6 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col6 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,16 +178,16 @@ STAGE PLANS: Select Operator expressions: _col1 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out index a031465139..1b5760b687 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out @@ -71,14 +71,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -86,14 +86,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -105,14 +105,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -120,13 +120,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -135,14 +135,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -150,13 +150,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -171,20 +171,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -204,14 +204,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -219,14 +219,14 @@ STAGE PLANS: subquery2:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -238,14 +238,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -253,13 +253,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -268,14 +268,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -283,13 +283,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out index e3d860d5f7..b776afcc76 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out @@ -80,14 +80,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -96,14 +96,14 @@ STAGE PLANS: TableScan alias: c filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -115,14 +115,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -130,7 +130,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -138,10 +138,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out b/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out index 05e1179948..d596a3508b 100644 --- a/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out @@ -85,14 +85,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -101,14 +101,14 @@ STAGE PLANS: TableScan alias: c filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -116,14 +116,14 @@ STAGE PLANS: subquery1:a TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -135,14 +135,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -150,9 +150,9 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -160,24 +160,24 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -185,9 +185,9 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -195,10 +195,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_noskew.q.out b/ql/src/test/results/clientpositive/skewjoin_noskew.q.out index 6cbd9eae4e..50f754e9c3 100644 --- a/ql/src/test/results/clientpositive/skewjoin_noskew.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_noskew.q.out @@ -21,36 +21,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -60,7 +60,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -112,7 +112,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -120,13 +120,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 30 - Statistics: Num rows: 30 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out b/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out index c420f9a604..f42506cf8d 100644 --- a/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out @@ -94,36 +94,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -133,10 +133,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -173,7 +173,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_union_remove_1.q.out b/ql/src/test/results/clientpositive/skewjoin_union_remove_1.q.out index 6c1a3b92dd..ea44db7a40 100644 --- a/ql/src/test/results/clientpositive/skewjoin_union_remove_1.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_union_remove_1.q.out @@ -52,36 +52,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -91,10 +91,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -105,45 +105,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -190,35 +190,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -228,10 +228,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -242,45 +242,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Right Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -340,36 +340,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -379,10 +379,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -404,45 +404,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -500,35 +500,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -538,10 +538,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -563,45 +563,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Right Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoin_union_remove_2.q.out b/ql/src/test/results/clientpositive/skewjoin_union_remove_2.q.out index 0d0e65e69d..1aeee43752 100644 --- a/ql/src/test/results/clientpositive/skewjoin_union_remove_2.q.out +++ b/ql/src/test/results/clientpositive/skewjoin_union_remove_2.q.out @@ -68,53 +68,53 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -126,10 +126,10 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -140,51 +140,51 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -192,10 +192,10 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoinopt1.q.out b/ql/src/test/results/clientpositive/skewjoinopt1.q.out index 618ca313fb..777e548d49 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt1.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt1.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -214,35 +214,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -252,7 +252,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -265,20 +265,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -289,42 +289,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Right Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -377,35 +377,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -413,7 +413,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -426,7 +426,7 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -438,7 +438,7 @@ STAGE PLANS: value expressions: _col0 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -467,39 +467,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -542,34 +542,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -577,7 +577,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -590,7 +590,7 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -602,7 +602,7 @@ STAGE PLANS: value expressions: _col0 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -631,39 +631,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Right Outer Join 0 to 1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt10.q.out b/ql/src/test/results/clientpositive/skewjoinopt10.q.out index 5f4fd6dc58..7bd449fc0c 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt10.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt10.q.out @@ -55,27 +55,27 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '8') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '8') and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: array) Reduce Operator Tree: Join Operator @@ -85,11 +85,11 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col6 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col6 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -102,19 +102,19 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -122,35 +122,35 @@ STAGE PLANS: Select Operator expressions: _col1 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Forward - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -158,16 +158,16 @@ STAGE PLANS: Select Operator expressions: _col1 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,37 +178,37 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '8')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '8')) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2104 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2104 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: array) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col6 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col6 (type: array) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt11.q.out b/ql/src/test/results/clientpositive/skewjoinopt11.q.out index d595a503ae..4c0d16164e 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt11.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt11.q.out @@ -65,36 +65,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -104,11 +104,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -130,7 +130,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -143,20 +143,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -168,36 +168,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -207,11 +207,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -224,7 +224,7 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -233,7 +233,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -246,46 +246,46 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -298,46 +298,46 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt12.q.out b/ql/src/test/results/clientpositive/skewjoinopt12.q.out index c13c46e071..28a2694d08 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt12.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt12.q.out @@ -53,35 +53,35 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -90,7 +90,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -103,20 +103,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,40 +127,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt13.q.out b/ql/src/test/results/clientpositive/skewjoinopt13.q.out index d320269b19..0798bf67ce 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt13.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt13.q.out @@ -72,36 +72,36 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -111,7 +111,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -127,24 +127,24 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: c filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -154,10 +154,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoinopt14.q.out b/ql/src/test/results/clientpositive/skewjoinopt14.q.out index 4dfce3483e..064bf0e7a1 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt14.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt14.q.out @@ -75,36 +75,36 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -114,7 +114,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -127,38 +127,38 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) TableScan alias: c filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator @@ -168,10 +168,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -182,42 +182,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt16.q.out b/ql/src/test/results/clientpositive/skewjoinopt16.q.out index 3f519baa21..043c18c59e 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt16.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt16.q.out @@ -53,35 +53,35 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') and (val = '12')) or (key = '3')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') and (val = '12')) or (key = '3')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -90,7 +90,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -103,20 +103,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,40 +127,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') and (val = '12')) or (key = '3'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') and (val = '12')) or (key = '3'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt17.q.out b/ql/src/test/results/clientpositive/skewjoinopt17.q.out index b00a6684ee..1c202ad76d 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt17.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt17.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -267,35 +267,35 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') and (val = '12')) or (key = '2')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') and (val = '12')) or (key = '2')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -304,7 +304,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -317,20 +317,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -341,40 +341,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') and (val = '12')) or (key = '2'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') and (val = '12')) or (key = '2'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt18.q.out b/ql/src/test/results/clientpositive/skewjoinopt18.q.out index 92c0742512..dba6bb7fcc 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt18.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt18.q.out @@ -67,36 +67,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Join Operator @@ -106,10 +106,10 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 594 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/skewjoinopt19.q.out b/ql/src/test/results/clientpositive/skewjoinopt19.q.out index 6f4afd798c..037ed6524c 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt19.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt19.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt2.q.out b/ql/src/test/results/clientpositive/skewjoinopt2.q.out index 75eb8e3455..375374f6c9 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt2.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt2.q.out @@ -53,35 +53,35 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -90,7 +90,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -103,20 +103,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,40 +127,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -207,34 +207,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -243,7 +243,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -256,20 +256,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -280,40 +280,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -365,35 +365,35 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -402,7 +402,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -415,33 +415,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -449,10 +449,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -463,40 +463,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) and key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -540,34 +540,34 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -576,7 +576,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -589,33 +589,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -623,10 +623,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -637,40 +637,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Left Outer Join 0 to 1 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt20.q.out b/ql/src/test/results/clientpositive/skewjoinopt20.q.out index 25d67cbfb7..f51d39a41c 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt20.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt20.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt21.q.out b/ql/src/test/results/clientpositive/skewjoinopt21.q.out index 5a3d2e14af..e09994ceaf 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt21.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt21.q.out @@ -63,36 +63,36 @@ STAGE PLANS: TableScan alias: t1_n63 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: t2_n38 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -102,7 +102,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -115,20 +115,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -139,42 +139,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n63 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: t2_n38 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt3.q.out b/ql/src/test/results/clientpositive/skewjoinopt3.q.out index ef8af9fde6..d128a5edf0 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt3.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt3.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -214,35 +214,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '8')) or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '8')) or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -252,7 +252,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -265,20 +265,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -289,42 +289,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (not (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Outer Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt4.q.out b/ql/src/test/results/clientpositive/skewjoinopt4.q.out index 675cf0e9ce..54dfd7b232 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt4.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt4.q.out @@ -51,36 +51,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -90,7 +90,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -103,20 +103,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -127,42 +127,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -213,36 +213,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key = '2') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -252,7 +252,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -265,20 +265,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -289,42 +289,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (key = '2')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt5.q.out b/ql/src/test/results/clientpositive/skewjoinopt5.q.out index 221aaf2041..4ed4800eff 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt5.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt5.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '2') or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '2') or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt6.q.out b/ql/src/test/results/clientpositive/skewjoinopt6.q.out index 6684aa4a66..6260d70fef 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt6.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt6.q.out @@ -53,36 +53,36 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -92,7 +92,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -105,20 +105,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -129,42 +129,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt7.q.out b/ql/src/test/results/clientpositive/skewjoinopt7.q.out index da06be8f17..102f1080ef 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt7.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt7.q.out @@ -69,53 +69,53 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((key = '2') or (key = '8')) or (key = '3')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -127,7 +127,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -140,20 +140,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -164,51 +164,51 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not (((key = '2') or (key = '8')) or (key = '3'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -216,7 +216,7 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt8.q.out b/ql/src/test/results/clientpositive/skewjoinopt8.q.out index df747466d2..05a1c44cda 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt8.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt8.q.out @@ -67,53 +67,53 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '3') or (key = '8')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '3') or (key = '8')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key = '3') or (key = '8')) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -125,7 +125,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -138,20 +138,20 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 1618 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -162,51 +162,51 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '3') or (key = '8'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '3') or (key = '8'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: c - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((not ((key = '3') or (key = '8'))) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -214,7 +214,7 @@ STAGE PLANS: Inner Join 0 to 1 Inner Join 0 to 2 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/skewjoinopt9.q.out b/ql/src/test/results/clientpositive/skewjoinopt9.q.out index d7494dc9c9..0343ccc606 100644 --- a/ql/src/test/results/clientpositive/skewjoinopt9.q.out +++ b/ql/src/test/results/clientpositive/skewjoinopt9.q.out @@ -61,57 +61,57 @@ STAGE PLANS: TableScan alias: t1_n9 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: t1_n9 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -121,10 +121,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -198,21 +198,21 @@ STAGE PLANS: TableScan alias: t1_n9 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -221,7 +221,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -237,24 +237,24 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -264,10 +264,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin9.q.out b/ql/src/test/results/clientpositive/smb_mapjoin9.q.out index 72ffeec0b4..9f848b5ae2 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin9.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin9.q.out @@ -37,12 +37,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and (ds = '2010-10-15')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2010-10-15') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 98 Basic stats: COMPLETE Column stats: PARTIAL Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -122,12 +122,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (key is not null and (ds = '2010-10-15')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Filter Operator isSamplingPred: false predicate: ((ds = '2010-10-15') and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 282 Basic stats: COMPLETE Column stats: PARTIAL Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -236,10 +236,10 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and (ds = '2010-10-15')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_1.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_1.q.out index 1f334bd0c2..25c369f57b 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_1.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_1.q.out @@ -107,10 +107,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -160,7 +160,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -215,7 +215,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -269,7 +269,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 @@ -329,10 +329,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -382,7 +382,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -437,7 +437,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -491,7 +491,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_10.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_10.q.out index 8b48c7f12c..8dd02b317a 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_10.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_10.q.out @@ -79,10 +79,10 @@ STAGE PLANS: TableScan alias: b filterExpr: (userid is not null and pageid is not null and postid is not null and type is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 4140 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 6688 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (pageid is not null and postid is not null and type is not null and userid is not null) (type: boolean) - Statistics: Num rows: 13 Data size: 4140 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 13 Data size: 6688 Basic stats: PARTIAL Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_11.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_11.q.out index f4be7dffb4..8f20eca306 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_11.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_11.q.out @@ -59,12 +59,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1893,23 +1893,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1_n1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 16) = 1) (type: boolean) sampleDesc: BUCKET 2 OUT OF 16 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 69750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2004,23 +2004,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table3_n1 - Statistics: Num rows: 1028 Data size: 10968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1028 Data size: 286812 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: true predicate: (((hash(key) & 2147483647) % 16) = 1) (type: boolean) sampleDesc: BUCKET 2 OUT OF 16 - Statistics: Num rows: 514 Data size: 5484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514 Data size: 143406 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 514 Data size: 5484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514 Data size: 143406 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 514 Data size: 5484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 514 Data size: 143406 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_12.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_12.q.out index f699e81428..2dba4db7a7 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_12.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_12.q.out @@ -70,12 +70,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -273,12 +273,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '1') and key is not null) (type: boolean) - Statistics: Num rows: 3084 Data size: 32904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3084 Data size: 583932 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 3084 Data size: 32904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2930 Data size: 554773 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_13.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_13.q.out index 123e84457a..a5e8a7f504 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_13.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_13.q.out @@ -77,12 +77,12 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -239,12 +239,12 @@ STAGE PLANS: TableScan alias: b filterExpr: UDFToDouble(value) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(value) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 UDFToDouble(key) (type: double) @@ -257,12 +257,12 @@ STAGE PLANS: TableScan alias: a filterExpr: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -271,16 +271,16 @@ STAGE PLANS: 1 UDFToDouble(value) (type: double) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE tag: -1 TopN: 10 TopN Hash Memory Usage: 0.1 @@ -351,16 +351,16 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 52250 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out index 3fb1769a05..e111326a80 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_16.q.out @@ -49,10 +49,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_2.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_2.q.out index e39edcc2fd..5e565016bf 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_2.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_2.q.out @@ -63,10 +63,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -118,7 +118,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -173,7 +173,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -229,7 +229,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 @@ -289,10 +289,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -344,7 +344,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -399,7 +399,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -455,7 +455,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_20.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_20.q.out index 37327d75a9..5d89b8b08c 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_20.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_20.q.out @@ -51,26 +51,26 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: CAST( _col0 AS STRING) (type: string) sort order: + Map-reduce partition columns: CAST( _col0 AS STRING) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: CAST( VALUE._col0 AS STRING) (type: string), VALUE._col1 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 183000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 183000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -79,13 +79,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '1' (type: string) outputColumnNames: key, value1, value2, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 225500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -121,7 +121,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -130,14 +130,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -220,26 +220,26 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -248,13 +248,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), '1' (type: string) outputColumnNames: key, value1, value2, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1389 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -290,7 +290,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1389 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -299,14 +299,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1436,26 +1436,26 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (key + key) (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: CAST( _col0 AS STRING) (type: string) sort order: + Map-reduce partition columns: CAST( _col0 AS STRING) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: CAST( VALUE._col0 AS STRING) (type: string), VALUE._col1 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 183000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 183000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1464,13 +1464,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '2' (type: string) outputColumnNames: key, value1, value2, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 225500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1506,7 +1506,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1515,14 +1515,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out index f8d0d56a70..59fd4ca752 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_21.q.out @@ -50,14 +50,14 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -124,26 +124,26 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -152,13 +152,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -194,7 +194,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -203,14 +203,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -255,25 +255,25 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -282,13 +282,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -324,7 +324,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -333,14 +333,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -385,26 +385,26 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -413,13 +413,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -455,7 +455,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -464,14 +464,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -516,26 +516,26 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -544,13 +544,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -586,7 +586,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -595,14 +595,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -647,25 +647,25 @@ STAGE PLANS: TableScan alias: a filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -674,13 +674,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -716,7 +716,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -725,14 +725,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out index 6652e71adb..a3a648b975 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_22.q.out @@ -47,14 +47,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1_n10 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -193,14 +193,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table1_n10 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out index e756cb16ec..3129d0c724 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out @@ -66,27 +66,27 @@ STAGE PLANS: TableScan alias: c filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: d filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -94,7 +94,7 @@ STAGE PLANS: keys: 0 1 - Statistics: Num rows: 1 Data size: 4281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -108,31 +108,31 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 4281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -142,14 +142,14 @@ STAGE PLANS: 0 1 2 - Statistics: Num rows: 1 Data size: 8422 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), 5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8422 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8422 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -192,12 +192,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -207,12 +207,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -222,12 +222,12 @@ STAGE PLANS: TableScan alias: c filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -239,19 +239,19 @@ STAGE PLANS: TableScan alias: d filterExpr: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 1 - Statistics: Num rows: 1 Data size: 4281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -260,14 +260,14 @@ STAGE PLANS: 0 1 2 - Statistics: Num rows: 1 Data size: 8422 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 5 (type: int), 5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8422 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8422 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_3.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_3.q.out index fa7968da80..d10568ba2b 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_3.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_3.q.out @@ -63,10 +63,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -118,7 +118,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -172,7 +172,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -228,7 +228,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 @@ -287,10 +287,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -342,7 +342,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -396,7 +396,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -452,7 +452,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out index 1627af2561..e28b5aa23a 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_46.q.out @@ -102,11 +102,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -173,11 +173,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -255,14 +255,14 @@ STAGE PLANS: TableScan alias: test2_n3 filterExpr: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {_col0 BETWEEN 100 AND 102} @@ -276,11 +276,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -291,10 +291,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1142 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 116 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1142 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -352,11 +352,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -424,11 +424,11 @@ STAGE PLANS: $hdt$_1:test2_n3 TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {_col0 BETWEEN 100 AND 102} @@ -442,11 +442,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -457,10 +457,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -533,11 +533,11 @@ STAGE PLANS: $hdt$_1:test2_n3 TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -548,11 +548,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -561,10 +561,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -639,11 +639,11 @@ STAGE PLANS: $hdt$_1:test2_n3 TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -654,11 +654,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -667,10 +667,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -743,11 +743,11 @@ STAGE PLANS: $hdt$_1:test2_n3 TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -758,11 +758,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -771,10 +771,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -837,11 +837,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -919,11 +919,11 @@ STAGE PLANS: $hdt$_0:test1_n5 TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -934,11 +934,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -947,10 +947,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1025,11 +1025,11 @@ STAGE PLANS: $hdt$_0:test1_n5 TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1040,11 +1040,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1053,10 +1053,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1126,11 +1126,11 @@ STAGE PLANS: $hdt$_0:test1_n5 TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1141,11 +1141,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1154,10 +1154,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1222,11 +1222,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1296,25 +1296,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1325,10 +1325,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1395,25 +1395,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1424,10 +1424,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1492,25 +1492,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1521,10 +1521,10 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 24 Data size: 476 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1587,29 +1587,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n5 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: test2_n3 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1620,10 +1620,10 @@ STAGE PLANS: 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1711 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out index 9cc2de467f..88c1a3d49b 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_47.q.out @@ -109,14 +109,14 @@ STAGE PLANS: TableScan alias: test1_n8 filterExpr: (key BETWEEN 100 AND 102 and value is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key BETWEEN 100 AND 102 and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -183,14 +183,14 @@ STAGE PLANS: TableScan alias: test1_n8 filterExpr: value is not null (type: boolean) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -267,14 +267,14 @@ STAGE PLANS: TableScan alias: test2_n5 filterExpr: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -286,14 +286,14 @@ STAGE PLANS: TableScan alias: test1_n8 filterExpr: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key BETWEEN 100 AND 102 (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -301,13 +301,13 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 19 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -378,11 +378,11 @@ STAGE PLANS: $hdt$_1:test2_n5 TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -393,11 +393,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n8 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -406,13 +406,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 16 Data size: 317 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1910 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1910 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -488,11 +488,11 @@ STAGE PLANS: $hdt$_1:test2_n5 TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -503,11 +503,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n8 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -516,13 +516,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col0 + _col3) >= 100)} {((_col0 + _col3) <= 102)} - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 382 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -586,11 +586,11 @@ STAGE PLANS: $hdt$_1:test2_n5 TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -601,11 +601,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n8 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -614,13 +614,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(((_col0 + _col3) >= 100) or ((_col0 + _col3) <= 102))} - Statistics: Num rows: 16 Data size: 317 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 3056 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1910 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1910 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -692,11 +692,11 @@ STAGE PLANS: $hdt$_1:test2_n5 TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -707,11 +707,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test1_n8 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -720,13 +720,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {(struct(_col0,_col3)) IN (const struct(100,100), const struct(101,101), const struct(102,102))} - Statistics: Num rows: 18 Data size: 357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 955 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 955 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 955 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -782,11 +782,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -799,14 +799,14 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) TableScan alias: a - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -889,11 +889,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Left Outer Join 0 to 1 @@ -906,14 +906,14 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) TableScan alias: b - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -993,11 +993,11 @@ STAGE PLANS: $hdt$_0:test2_n5 TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1008,11 +1008,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1021,7 +1021,7 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col3 + _col0) >= 100)} - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1053,11 +1053,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1065,13 +1065,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4588 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1088,20 +1088,20 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) TableScan alias: b - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1111,13 +1111,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4588 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1183,11 +1183,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Right Outer Join 0 to 1 @@ -1200,14 +1200,14 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) TableScan alias: b - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1283,11 +1283,11 @@ STAGE PLANS: $hdt$_0:test2_n5 TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1298,24 +1298,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: a - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1324,12 +1324,12 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 residual filter predicates: {((_col3 + _col0) >= 100)} - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 8 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) Local Work: Map Reduce Local Work @@ -1341,13 +1341,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 4588 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 173 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1415,29 +1415,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test2_n5 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 4 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: a - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Reduce Operator Tree: Join Operator @@ -1447,7 +1447,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 61 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1707 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1465,11 +1465,11 @@ STAGE PLANS: $hdt$_2:b TableScan alias: b - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: int), col_1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -1487,13 +1487,13 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 residual filter predicates: {((_col6 + _col0) <= 102)} - Statistics: Num rows: 12 Data size: 246 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5740 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2870 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_7.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_7.q.out index 83033b07c0..69d6335a2f 100644 --- a/ql/src/test/results/clientpositive/smb_mapjoin_7.q.out +++ b/ql/src/test/results/clientpositive/smb_mapjoin_7.q.out @@ -630,7 +630,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Outer Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/sort.q.out b/ql/src/test/results/clientpositive/sort.q.out index f9b5ce6ada..2117452196 100644 --- a/ql/src/test/results/clientpositive/sort.q.out +++ b/ql/src/test/results/clientpositive/sort.q.out @@ -14,25 +14,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out index 3415a54c96..253f0f733a 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_1.q.out @@ -59,10 +59,10 @@ STAGE PLANS: TableScan alias: a filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out index ef621e813f..ef476952d0 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_2.q.out @@ -65,10 +65,10 @@ STAGE PLANS: TableScan alias: a filterExpr: (value is not null and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out index 3930dd5b79..33c100a97c 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_3.q.out @@ -65,10 +65,10 @@ STAGE PLANS: TableScan alias: a filterExpr: (value is not null and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out index cef8d10e48..01cd5a5a24 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_4.q.out @@ -71,10 +71,10 @@ STAGE PLANS: TableScan alias: b filterExpr: (value is not null and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -86,17 +86,17 @@ STAGE PLANS: TableScan alias: a filterExpr: (value is not null and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string), value (type: string) 1 key (type: string), value (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 32502 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out index 447a04952d..ea2961d4dc 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_5.q.out @@ -67,12 +67,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out index 9ef400a854..0118015dd6 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_6.q.out @@ -122,12 +122,12 @@ STAGE PLANS: TableScan alias: b filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: int) @@ -147,12 +147,12 @@ STAGE PLANS: TableScan alias: a filterExpr: ((part = '1') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -160,7 +160,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 2200 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out index 1c3881cd9b..05f1b3eb61 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_7.q.out @@ -206,12 +206,12 @@ STAGE PLANS: TableScan alias: b filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: int) @@ -224,12 +224,12 @@ STAGE PLANS: TableScan alias: a filterExpr: (part is not null and key is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -237,7 +237,7 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 4400 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out b/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out index bf8cf35680..670e94d7a1 100644 --- a/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out +++ b/ql/src/test/results/clientpositive/sort_merge_join_desc_8.q.out @@ -114,10 +114,10 @@ STAGE PLANS: TableScan alias: a filterExpr: (key < 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -187,10 +187,10 @@ STAGE PLANS: TableScan alias: b filterExpr: (value2 is not null and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and value2 is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 2095 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29880 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string), value2 (type: string) @@ -202,17 +202,17 @@ STAGE PLANS: TableScan alias: a filterExpr: (value2 is not null and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 10218 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key < 10) and value2 is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 3392 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29880 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string), value2 (type: string) 1 key (type: string), value2 (type: string) - Statistics: Num rows: 182 Data size: 3731 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 182 Data size: 32868 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/source.q.out b/ql/src/test/results/clientpositive/source.q.out index 82d9e239a2..bcf65f5ff2 100644 --- a/ql/src/test/results/clientpositive/source.q.out +++ b/ql/src/test/results/clientpositive/source.q.out @@ -14,11 +14,11 @@ STAGE PLANS: Processor Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRC x @@ -545,11 +545,11 @@ STAGE PLANS: Processor Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRC x diff --git a/ql/src/test/results/clientpositive/spark/spark_local_queries.q.out b/ql/src/test/results/clientpositive/spark/spark_local_queries.q.out index 6203927d26..30e3b47cab 100644 --- a/ql/src/test/results/clientpositive/spark/spark_local_queries.q.out +++ b/ql/src/test/results/clientpositive/spark/spark_local_queries.q.out @@ -17,15 +17,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Execution mode: vectorized @@ -35,13 +35,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/special_character_in_tabnames_2.q.out b/ql/src/test/results/clientpositive/special_character_in_tabnames_2.q.out index 44ad0f4a6b..3c381a11ac 100644 --- a/ql/src/test/results/clientpositive/special_character_in_tabnames_2.q.out +++ b/ql/src/test/results/clientpositive/special_character_in_tabnames_2.q.out @@ -78,17 +78,17 @@ STAGE PLANS: TableScan alias: s/c filterExpr: ((UDFToDouble(key) > 80.0D) and (UDFToDouble(key) < 100.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(key) < 100.0D) and (UDFToDouble(key) > 80.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats0.q.out b/ql/src/test/results/clientpositive/stats0.q.out index 155e95e575..6683251b64 100644 --- a/ql/src/test/results/clientpositive/stats0.q.out +++ b/ql/src/test/results/clientpositive/stats0.q.out @@ -27,18 +27,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -69,16 +69,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -141,13 +141,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -761,14 +761,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -777,18 +777,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 131500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -796,14 +796,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1438,18 +1438,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1480,16 +1480,16 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct) auto parallelism: false @@ -1552,13 +1552,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -2372,14 +2372,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2388,18 +2388,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 131500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator @@ -2407,14 +2407,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats1.q.out b/ql/src/test/results/clientpositive/stats1.q.out index d77d94e169..8c6e4e804f 100644 --- a/ql/src/test/results/clientpositive/stats1.q.out +++ b/ql/src/test/results/clientpositive/stats1.q.out @@ -67,10 +67,10 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -79,28 +79,28 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -109,25 +109,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats10.q.out b/ql/src/test/results/clientpositive/stats10.q.out index dc81e22c1e..6a5d9666ea 100644 --- a/ql/src/test/results/clientpositive/stats10.q.out +++ b/ql/src/test/results/clientpositive/stats10.q.out @@ -26,25 +26,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -53,13 +53,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -95,7 +95,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -104,14 +104,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -420,7 +420,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: bucket3_1_n0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE Stage: Stage-1 Stats Work diff --git a/ql/src/test/results/clientpositive/stats12.q.out b/ql/src/test/results/clientpositive/stats12.q.out index 923fc788d9..988a4535f3 100644 --- a/ql/src/test/results/clientpositive/stats12.q.out +++ b/ql/src/test/results/clientpositive/stats12.q.out @@ -49,7 +49,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart_n3 - Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE Statistics Aggregation Key Prefix: default.analyze_srcpart_n3/ GatherStats: true Path -> Alias: diff --git a/ql/src/test/results/clientpositive/stats13.q.out b/ql/src/test/results/clientpositive/stats13.q.out index 04a100c7e2..8d5dc4d6fd 100644 --- a/ql/src/test/results/clientpositive/stats13.q.out +++ b/ql/src/test/results/clientpositive/stats13.q.out @@ -49,7 +49,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart - Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE Statistics Aggregation Key Prefix: default.analyze_srcpart/ GatherStats: true Path -> Alias: diff --git a/ql/src/test/results/clientpositive/stats2.q.out b/ql/src/test/results/clientpositive/stats2.q.out index ea831bda79..f618f84fb8 100644 --- a/ql/src/test/results/clientpositive/stats2.q.out +++ b/ql/src/test/results/clientpositive/stats2.q.out @@ -23,14 +23,14 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -131,7 +131,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_t1 - Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE Stage: Stage-1 Stats Work diff --git a/ql/src/test/results/clientpositive/stats4.q.out b/ql/src/test/results/clientpositive/stats4.q.out index bee528c3bc..efa1bf81e1 100644 --- a/ql/src/test/results/clientpositive/stats4.q.out +++ b/ql/src/test/results/clientpositive/stats4.q.out @@ -61,17 +61,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -80,29 +80,29 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: key, value, ds, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Filter Operator predicate: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -111,13 +111,13 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, hr - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') keys: '2008-12-31' (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -130,14 +130,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -232,7 +232,7 @@ STAGE PLANS: key expressions: '2008-12-31' (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: struct), _col3 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -241,14 +241,14 @@ STAGE PLANS: keys: '2008-12-31' (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: struct), _col3 (type: struct), '2008-12-31' (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats7.q.out b/ql/src/test/results/clientpositive/stats7.q.out index 971c934e1e..5fb34d80b1 100644 --- a/ql/src/test/results/clientpositive/stats7.q.out +++ b/ql/src/test/results/clientpositive/stats7.q.out @@ -47,7 +47,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart_n4 - Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE Stage: Stage-1 Stats Work diff --git a/ql/src/test/results/clientpositive/stats8.q.out b/ql/src/test/results/clientpositive/stats8.q.out index 8d77e02e8a..52bdd2a711 100644 --- a/ql/src/test/results/clientpositive/stats8.q.out +++ b/ql/src/test/results/clientpositive/stats8.q.out @@ -82,7 +82,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart_n1 - Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE Stage: Stage-1 Stats Work @@ -226,7 +226,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart_n1 - Statistics: Num rows: 794 Data size: 179672 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 794 Data size: 186024 Basic stats: PARTIAL Column stats: NONE Stage: Stage-1 Stats Work @@ -296,7 +296,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart_n1 - Statistics: Num rows: 1196 Data size: 126864 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1196 Data size: 136432 Basic stats: PARTIAL Column stats: NONE Stage: Stage-1 Stats Work @@ -366,7 +366,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart_n1 - Statistics: Num rows: 1598 Data size: 74056 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1598 Data size: 86840 Basic stats: PARTIAL Column stats: NONE Stage: Stage-1 Stats Work @@ -436,7 +436,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: analyze_srcpart_n1 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE Stage: Stage-1 Stats Work diff --git a/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out b/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out index 6d75f8450a..1ce675f3af 100644 --- a/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out +++ b/ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out @@ -27,17 +27,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = 'no_such_value') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 'no_such_value') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'no_such_value' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -46,18 +46,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, part - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll') keys: part (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator @@ -65,14 +65,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats_empty_partition2.q.out b/ql/src/test/results/clientpositive/stats_empty_partition2.q.out index 3ee46d98ae..521a459211 100644 --- a/ql/src/test/results/clientpositive/stats_empty_partition2.q.out +++ b/ql/src/test/results/clientpositive/stats_empty_partition2.q.out @@ -83,36 +83,36 @@ STAGE PLANS: TableScan alias: p1_n0 filterExpr: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Filter Operator predicate: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Select Operator expressions: a (type: int), p (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: t_n32 filterExpr: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -121,10 +121,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/stats_noscan_2.q.out b/ql/src/test/results/clientpositive/stats_noscan_2.q.out index 26a85def7f..1a0fc31d75 100644 --- a/ql/src/test/results/clientpositive/stats_noscan_2.q.out +++ b/ql/src/test/results/clientpositive/stats_noscan_2.q.out @@ -306,17 +306,17 @@ STAGE PLANS: TableScan alias: anaylyze_external filterExpr: (insertdate = '2008-01-01') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -324,10 +324,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/structin.q.out b/ql/src/test/results/clientpositive/structin.q.out index c07ea92aa7..d24fa1a5e5 100644 --- a/ql/src/test/results/clientpositive/structin.q.out +++ b/ql/src/test/results/clientpositive/structin.q.out @@ -43,17 +43,17 @@ STAGE PLANS: TableScan alias: t11_n1 filterExpr: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1'), const struct('1234-1111-0074580704','1'), const struct('1234-1111-0074581619','2'), const struct('1234-1111-0074582745','1'), const struct('1234-1111-0074586625','1'), const struct('1234-1111-0074019112','1'), const struct('1234-1111-0074019610','1'), const struct('1234-1111-0074022106','1')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1'), const struct('1234-1111-0074580704','1'), const struct('1234-1111-0074581619','2'), const struct('1234-1111-0074582745','1'), const struct('1234-1111-0074586625','1'), const struct('1234-1111-0074019112','1'), const struct('1234-1111-0074019610','1'), const struct('1234-1111-0074022106','1')) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: string), lineid (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -89,17 +89,17 @@ STAGE PLANS: TableScan alias: t11_n1 filterExpr: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695',1)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695',1)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id (type: string), lineid (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subq.q.out b/ql/src/test/results/clientpositive/subq.q.out index b51a1d6d19..5e47405059 100644 --- a/ql/src/test/results/clientpositive/subq.q.out +++ b/ql/src/test/results/clientpositive/subq.q.out @@ -26,17 +26,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/subq2.q.out b/ql/src/test/results/clientpositive/subq2.q.out index 1fa1df8b90..e5cfbde661 100644 --- a/ql/src/test/results/clientpositive/subq2.q.out +++ b/ql/src/test/results/clientpositive/subq2.q.out @@ -19,21 +19,21 @@ STAGE PLANS: TableScan alias: b filterExpr: (UDFToDouble(key) >= 90.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) >= 90.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -42,10 +42,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subq_where_serialization.q.out b/ql/src/test/results/clientpositive/subq_where_serialization.q.out index cf4b101411..9aeacabafb 100644 --- a/ql/src/test/results/clientpositive/subq_where_serialization.q.out +++ b/ql/src/test/results/clientpositive/subq_where_serialization.q.out @@ -19,19 +19,19 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -43,14 +43,14 @@ STAGE PLANS: TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 @@ -58,10 +58,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subquery_alias.q.out b/ql/src/test/results/clientpositive/subquery_alias.q.out index 185236cbed..b63e067253 100644 --- a/ql/src/test/results/clientpositive/subquery_alias.q.out +++ b/ql/src/test/results/clientpositive/subquery_alias.q.out @@ -26,17 +26,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -108,11 +108,11 @@ STAGE PLANS: Processor Tree: TableScan alias: s - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT * FROM diff --git a/ql/src/test/results/clientpositive/subquery_exists.q.out b/ql/src/test/results/clientpositive/subquery_exists.q.out index de5bdfcfde..343cda04e8 100644 --- a/ql/src/test/results/clientpositive/subquery_exists.q.out +++ b/ql/src/test/results/clientpositive/subquery_exists.q.out @@ -27,40 +27,40 @@ STAGE PLANS: TableScan alias: b filterExpr: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: a filterExpr: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -69,10 +69,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -222,41 +222,41 @@ STAGE PLANS: TableScan alias: b filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: a filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -265,10 +265,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 407 Data size: 72446 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 407 Data size: 72446 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -311,31 +311,31 @@ STAGE PLANS: TableScan alias: a filterExpr: (value > 'val_9') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value > 'val_9') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: true (type: boolean) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -348,19 +348,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -369,10 +369,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 41500 Data size: 922896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41500 Data size: 922896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -983,14 +983,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n12 - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan Reduce Output Operator @@ -1004,10 +1004,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1095,41 +1095,41 @@ STAGE PLANS: TableScan alias: u filterExpr: a is not null (type: boolean) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: a is not null (type: boolean) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: v filterExpr: (a is not null and b is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (a is not null and b is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int), b (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -1140,14 +1140,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col3 residual filter predicates: {(_col1 <> _col3)} - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1161,7 +1161,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1169,14 +1169,14 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), 3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1247,41 +1247,41 @@ STAGE PLANS: TableScan alias: t1_n68 filterExpr: i is not null (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i is not null (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int), j (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: t2_n41 filterExpr: (j is not null and i is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (i is not null and j is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int), j (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Join Operator @@ -1292,14 +1292,14 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 residual filter predicates: {(_col3 <> _col1)} - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subquery_exists_having.q.out b/ql/src/test/results/clientpositive/subquery_exists_having.q.out index 013c49d651..97ab2d7263 100644 --- a/ql/src/test/results/clientpositive/subquery_exists_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_exists_having.q.out @@ -30,21 +30,21 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -53,7 +53,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -69,29 +69,29 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: a filterExpr: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -100,10 +100,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -174,54 +174,54 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: a filterExpr: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Demux Operator - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 30971 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Mux Operator - Statistics: Num rows: 999 Data size: 10612 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 583 Data size: 54721 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Left Semi Join 0 to 1 @@ -229,16 +229,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1098 Data size: 11673 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1098 Data size: 11673 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Mux Operator - Statistics: Num rows: 999 Data size: 10612 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 583 Data size: 54721 Basic stats: COMPLETE Column stats: COMPLETE Join Operator condition map: Left Semi Join 0 to 1 @@ -246,10 +246,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1098 Data size: 11673 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1098 Data size: 11673 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subquery_multiinsert.q.out b/ql/src/test/results/clientpositive/subquery_multiinsert.q.out index bc987ca9e5..3e318f0b85 100644 --- a/ql/src/test/results/clientpositive/subquery_multiinsert.q.out +++ b/ql/src/test/results/clientpositive/subquery_multiinsert.q.out @@ -76,20 +76,20 @@ STAGE PLANS: TableScan alias: s1 filterExpr: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -97,17 +97,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 = 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: 0L (type: bigint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -120,14 +120,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -137,7 +137,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -146,7 +146,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -162,24 +162,24 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 9812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: s1 filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -188,14 +188,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 550 Data size: 10793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 111881 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col5 is null (type: boolean) - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 53326 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 53326 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -210,17 +210,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 53326 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -229,19 +229,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -273,28 +273,28 @@ STAGE PLANS: key expressions: key (type: string), value (type: string) sort order: ++ Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: a filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -303,10 +303,10 @@ STAGE PLANS: 0 key (type: string), value (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -315,12 +315,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -352,7 +352,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -360,10 +360,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -615,20 +615,20 @@ STAGE PLANS: TableScan alias: s1 filterExpr: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -636,17 +636,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 = 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: 0L (type: bigint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -676,7 +676,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 @@ -684,7 +684,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -693,7 +693,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -715,14 +715,14 @@ STAGE PLANS: TableScan alias: s1 filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -739,18 +739,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 550 Data size: 10793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 111881 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col5 is null (type: boolean) - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 53326 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 53326 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 53326 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Local Work: @@ -759,10 +759,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -771,19 +771,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 238 Data size: 42364 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -818,19 +818,19 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 key (type: string), value (type: string) @@ -847,10 +847,10 @@ STAGE PLANS: 0 key (type: string), value (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -859,12 +859,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -898,7 +898,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -906,10 +906,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -920,14 +920,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) Filter Operator predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -937,7 +937,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -946,7 +946,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/subquery_notexists.q.out b/ql/src/test/results/clientpositive/subquery_notexists.q.out index 93102ff05a..5436298ac3 100644 --- a/ql/src/test/results/clientpositive/subquery_notexists.q.out +++ b/ql/src/test/results/clientpositive/subquery_notexists.q.out @@ -28,31 +28,31 @@ STAGE PLANS: TableScan alias: a filterExpr: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), true (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -65,22 +65,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: boolean) Reduce Operator Tree: Join Operator @@ -90,17 +90,17 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89528 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col4 is null (type: boolean) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 369 Data size: 66074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 369 Data size: 65682 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 369 Data size: 65682 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -281,40 +281,40 @@ STAGE PLANS: TableScan alias: a filterExpr: (value > 'val_2') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value > 'val_2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: value (type: string), key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -327,23 +327,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -353,17 +353,17 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89544 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col3 is null (type: boolean) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 65370 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 64970 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 365 Data size: 64970 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -545,31 +545,31 @@ STAGE PLANS: TableScan alias: a filterExpr: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), true (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -582,19 +582,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: boolean) Reduce Operator Tree: Join Operator @@ -605,17 +605,17 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4 residual filter predicates: {(_col2 > _col0)} {(_col1 <> _col3)} - Statistics: Num rows: 41500 Data size: 922896 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41500 Data size: 14940000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col4 is null (type: boolean) - Statistics: Num rows: 20750 Data size: 461448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20750 Data size: 461448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20750 Data size: 461448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -673,25 +673,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan alias: part - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_type (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -701,7 +701,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 676 Data size: 152100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -717,14 +717,14 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 676 Data size: 164320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 676 Data size: 152100 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 185 Data size: 23367 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -734,17 +734,17 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 743 Data size: 180752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 676 Data size: 83152 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col3 is null (type: boolean) - Statistics: Num rows: 371 Data size: 90254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 338 Data size: 41578 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 371 Data size: 90254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 338 Data size: 40898 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 371 Data size: 90254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 338 Data size: 40898 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -764,17 +764,17 @@ STAGE PLANS: TableScan alias: part filterExpr: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_type is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_type (type: string) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -784,12 +784,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col1 - Statistics: Num rows: 676 Data size: 85202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 676 Data size: 70304 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 676 Data size: 85202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -805,14 +805,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 676 Data size: 85202 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 338 Data size: 42601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -826,25 +826,25 @@ STAGE PLANS: TableScan alias: pp1 filterExpr: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_partkey is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_partkey (type: int) outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 338 Data size: 42601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reduce Operator Tree: Join Operator @@ -854,12 +854,12 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col1 - Statistics: Num rows: 371 Data size: 46861 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 371 Data size: 46861 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -875,18 +875,18 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 371 Data size: 46861 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 185 Data size: 23367 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 185 Data size: 23367 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/subquery_notexists_having.q.out b/ql/src/test/results/clientpositive/subquery_notexists_having.q.out index 062af9739f..93a3c220dd 100644 --- a/ql/src/test/results/clientpositive/subquery_notexists_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_notexists_having.q.out @@ -30,28 +30,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -67,13 +67,13 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: boolean) Reduce Operator Tree: Join Operator @@ -83,17 +83,17 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44836 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col4 is null (type: boolean) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167 Data size: 29950 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167 Data size: 29726 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167 Data size: 29726 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -105,31 +105,31 @@ STAGE PLANS: TableScan alias: a filterExpr: ((value > 'val_12') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((value > 'val_12') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), true (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -211,32 +211,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: value (type: string), key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -252,14 +252,14 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -269,17 +269,17 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44836 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col3 is null (type: boolean) - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167 Data size: 29950 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167 Data size: 29726 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 167 Data size: 29726 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -291,40 +291,40 @@ STAGE PLANS: TableScan alias: a filterExpr: (value > 'val_12') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (value > 'val_12') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: value (type: string), key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.out index 96c7ff3085..b9e9eceefd 100644 --- a/ql/src/test/results/clientpositive/subquery_notin_having.q.out +++ b/ql/src/test/results/clientpositive/subquery_notin_having.q.out @@ -31,22 +31,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -55,7 +55,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -69,12 +69,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: bigint) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -84,7 +84,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 6906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 27750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -100,14 +100,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 6906 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 27750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -117,17 +117,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 275 Data size: 7596 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 28086 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 182 Data size: 5027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 28086 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 5027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 5027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -139,18 +139,18 @@ STAGE PLANS: TableScan alias: s1 filterExpr: (key > '12') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '12') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(key) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -158,7 +158,7 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -172,31 +172,31 @@ STAGE PLANS: TableScan alias: s1 filterExpr: (key > '12') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > '12') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -245,22 +245,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(p_retailprice) keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -269,7 +269,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -285,14 +285,14 @@ STAGE PLANS: key expressions: _col1 (type: double) sort order: + Map-reduce partition columns: _col1 (type: double) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -302,7 +302,7 @@ STAGE PLANS: 0 _col1 (type: double) 1 _col0 (type: double) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 562 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -318,14 +318,14 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 562 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: boolean) Reduce Operator Tree: Join Operator @@ -335,17 +335,17 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: double) 1 _col0 (type: string), _col1 (type: double) outputColumnNames: _col0, _col1, _col3, _col4, _col7 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 212 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -356,22 +356,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(p_retailprice), max(p_retailprice) keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -380,20 +380,20 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col2 - _col1) > 600.0D) and _col1 is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(_col0) keys: _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -409,7 +409,7 @@ STAGE PLANS: key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -418,7 +418,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -432,21 +432,21 @@ STAGE PLANS: TableScan alias: part filterExpr: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(p_retailprice), max(p_retailprice) keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -455,14 +455,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col2 - _col1) > 600.0D) and _col1 is not null) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), true (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -538,22 +538,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(p_retailprice) keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -562,7 +562,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -576,12 +576,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: double) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -591,7 +591,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 13 Data size: 1898 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -607,14 +607,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1898 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 610 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: bigint), _col3 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -624,17 +624,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 14 Data size: 2087 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 618 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 9 Data size: 1341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 1341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 9 Data size: 1341 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -645,22 +645,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(p_retailprice), min(p_retailprice) keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -669,19 +669,19 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 - _col2) > 600.0D) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(_col0) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -695,7 +695,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -703,7 +703,7 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -716,22 +716,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_mfgr (type: string), p_retailprice (type: double) outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(p_retailprice), min(p_retailprice) keys: p_mfgr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -740,14 +740,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 - _col2) > 600.0D) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -842,28 +842,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n145 - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int) outputColumnNames: c1 - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: c1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -877,12 +877,12 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Reduce Operator Tree: Join Operator @@ -892,7 +892,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -908,14 +908,14 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -925,17 +925,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 2 Data size: 209 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 = 0L) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -946,19 +946,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n85 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int) outputColumnNames: c1 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(c1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -966,7 +966,7 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -979,32 +979,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n85 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int) outputColumnNames: c1 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: c1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1048,28 +1048,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n145 - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int) outputColumnNames: c1 - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: c1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1085,20 +1085,20 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) TableScan Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 2 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -1110,17 +1110,17 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col2 (type: int) outputColumnNames: _col0, _col2, _col3, _col5 - Statistics: Num rows: 4 Data size: 343 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col2 = 0L)) THEN (true) WHEN (_col2 is null) THEN (true) WHEN (_col5 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col3 < _col2)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 2 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1132,21 +1132,21 @@ STAGE PLANS: TableScan alias: t2_n85 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(c1) keys: c1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -1155,7 +1155,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1169,31 +1169,31 @@ STAGE PLANS: TableScan alias: t2_n85 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: c1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1209,14 +1209,14 @@ STAGE PLANS: key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) TableScan Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -1225,7 +1225,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 2 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1239,27 +1239,27 @@ STAGE PLANS: TableScan alias: t1_n145 filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: c1 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 313 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 156 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out b/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out index 642ef461b2..0b0c4a3c41 100644 --- a/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out @@ -16,37 +16,37 @@ STAGE PLANS: alias: src filterExpr: lower(key) is not null (type: boolean) Row Limit Per Split: 10 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: lower(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: lower(key) (type: string) sort order: + Map-reduce partition columns: lower(key) (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) TableScan alias: src filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -55,10 +55,10 @@ STAGE PLANS: 0 lower(key) (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -108,20 +108,20 @@ STAGE PLANS: TableScan alias: src filterExpr: key is null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -129,17 +129,17 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (_col0 = 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: 0L (type: bigint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -153,15 +153,15 @@ STAGE PLANS: TableScan alias: src Row Limit Per Split: 10 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), value (type: string) TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -170,7 +170,7 @@ STAGE PLANS: 0 1 outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 9812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -186,20 +186,20 @@ STAGE PLANS: key expressions: concat(_col0, _col1) (type: string) sort order: + Map-reduce partition columns: concat(_col0, _col1) (type: string) - Statistics: Num rows: 500 Data size: 9812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -208,17 +208,17 @@ STAGE PLANS: 0 concat(_col0, _col1) (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 550 Data size: 10793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 132500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col5 is null (type: boolean) - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 5396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index c65b04c47f..57fcd6a926 100644 --- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -49,40 +49,40 @@ STAGE PLANS: TableScan alias: src11_n0 filterExpr: ((key1 > '9') and value1 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((key1 > '9') and value1 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key1 (type: string), value1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE TableScan alias: src filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -91,10 +91,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 16251 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 91 Data size: 16251 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -121,40 +121,40 @@ STAGE PLANS: TableScan alias: a filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -163,10 +163,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -207,40 +207,40 @@ STAGE PLANS: TableScan alias: b filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -249,10 +249,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -298,15 +298,15 @@ STAGE PLANS: TableScan alias: part filterExpr: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: p_name (type: string) Execution mode: vectorized @@ -314,7 +314,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) outputColumnNames: _col1, _col2, _col5 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -335,20 +335,20 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(_col0) keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -364,7 +364,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -373,7 +373,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -386,23 +386,23 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col2 (type: int) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: Join Operator @@ -412,7 +412,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 6134 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -428,14 +428,14 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 6134 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: boolean) Reduce Operator Tree: Join Operator @@ -445,17 +445,17 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col8 - Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 6154 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 3087 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 2899 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 2899 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -467,15 +467,15 @@ STAGE PLANS: TableScan alias: part filterExpr: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: p_mfgr (type: string), p_size (type: int) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: p_name (type: string) Execution mode: vectorized @@ -483,7 +483,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) outputColumnNames: _col1, _col2, _col5 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -504,19 +504,19 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((rank_window_0 <= 2) and _col1 is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -532,18 +532,18 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), true (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/symlink_text_input_format.q.out b/ql/src/test/results/clientpositive/symlink_text_input_format.q.out index 91a97cddab..379ac3993f 100644 --- a/ql/src/test/results/clientpositive/symlink_text_input_format.q.out +++ b/ql/src/test/results/clientpositive/symlink_text_input_format.q.out @@ -42,24 +42,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: symlink_text_input_format - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -109,24 +109,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: symlink_text_input_format - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -248,24 +248,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: symlink_text_input_format - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -318,24 +318,24 @@ STAGE PLANS: Map Operator Tree: TableScan alias: symlink_text_input_format - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/tablevalues.q.out b/ql/src/test/results/clientpositive/tablevalues.q.out index d3649346fb..89a30d97bf 100644 --- a/ql/src/test/results/clientpositive/tablevalues.q.out +++ b/ql/src/test/results/clientpositive/tablevalues.q.out @@ -190,21 +190,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE function name: inline Select Operator expressions: col3 (type: string), col4 (type: int), col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -662,21 +662,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE function name: inline Select Operator expressions: col3 (type: string), col4 (type: int), col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -734,21 +734,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE function name: inline Select Operator expressions: col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -806,21 +806,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE function name: inline Select Operator expressions: col5 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -878,18 +878,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 0 (type: int), key (type: string) sort order: +- Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition @@ -909,21 +909,21 @@ STAGE PLANS: window function: GenericUDAFRowNumberEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: array(struct(row_number_window_0,'A',10,row_number_window_0),struct(row_number_window_0,'B',20,row_number_window_0)) (type: array>) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE function name: inline Select Operator expressions: col4 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out b/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out index 707306c24e..14c2fa0071 100644 --- a/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out +++ b/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out @@ -168,29 +168,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_web_text_none - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -220,22 +220,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: uservisits_web_text_none - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Statistics Aggregation Key Prefix: default.uservisits_web_text_none/ GatherStats: true Select Operator expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 70600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) auto parallelism: false @@ -298,13 +298,13 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -497,29 +497,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: empty_tab - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary) outputColumnNames: a, b, c, d, e - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll'), compute_stats(e, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 1848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1848 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 1880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1880 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/temp_table_join1.q.out b/ql/src/test/results/clientpositive/temp_table_join1.q.out index 5e39f7e1ca..bf00dc8a90 100644 --- a/ql/src/test/results/clientpositive/temp_table_join1.q.out +++ b/ql/src/test/results/clientpositive/temp_table_join1.q.out @@ -39,35 +39,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -77,14 +77,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -135,35 +135,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -173,14 +173,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -233,35 +233,35 @@ STAGE PLANS: TableScan alias: src1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: src2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -271,14 +271,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out b/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out index 1a7c06536f..d2dbb14606 100644 --- a/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out +++ b/ql/src/test/results/clientpositive/timestamp_ints_casts.q.out @@ -45,17 +45,17 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1684250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 842180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -179,17 +179,17 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1684250 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 842180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/transform1.q.out b/ql/src/test/results/clientpositive/transform1.q.out index eee6d4655f..c554b53af9 100644 --- a/ql/src/test/results/clientpositive/transform1.q.out +++ b/ql/src/test/results/clientpositive/transform1.q.out @@ -22,21 +22,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: transform1_t1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: string), b (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/transform_ppr1.q.out b/ql/src/test/results/clientpositive/transform_ppr1.q.out index 63442399d1..087144a190 100644 --- a/ql/src/test/results/clientpositive/transform_ppr1.q.out +++ b/ql/src/test/results/clientpositive/transform_ppr1.q.out @@ -26,12 +26,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: ds (type: string), key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: @@ -44,17 +44,17 @@ STAGE PLANS: serialization.format 9 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: ((_col0 = '2008-04-08') and (_col1 < 100)) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: '2008-04-08' (type: string), _col1 (type: string), _col2 (type: string) auto parallelism: false @@ -267,13 +267,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/transform_ppr2.q.out b/ql/src/test/results/clientpositive/transform_ppr2.q.out index dd1c130e4c..fd64ff4699 100644 --- a/ql/src/test/results/clientpositive/transform_ppr2.q.out +++ b/ql/src/test/results/clientpositive/transform_ppr2.q.out @@ -29,12 +29,12 @@ STAGE PLANS: TableScan alias: src filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: '2008-04-08' (type: string), key (type: string), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: @@ -47,17 +47,17 @@ STAGE PLANS: serialization.format 9 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 272000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator isSamplingPred: false predicate: (_col1 < 100) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 90576 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 90576 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) auto parallelism: false @@ -170,13 +170,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out b/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out index 60e5cd8c49..4708a0f26f 100644 --- a/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out +++ b/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out @@ -67,22 +67,22 @@ STAGE PLANS: TableScan alias: test_tab_n3 filterExpr: ((part = '1') and (key = '484')) (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '484') (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '484' (type: string), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 526 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 526 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -188,22 +188,22 @@ STAGE PLANS: TableScan alias: test_tab_n3 filterExpr: ((part = '1') and (key = '0')) (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key = '0') (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '0' (type: string), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/type_widening.q.out b/ql/src/test/results/clientpositive/type_widening.q.out index 7224bdcf1b..3a9d201df3 100644 --- a/ql/src/test/results/clientpositive/type_widening.q.out +++ b/ql/src/test/results/clientpositive/type_widening.q.out @@ -1119,14 +1119,14 @@ STAGE PLANS: TableScan alias: t1_n114 filterExpr: (a > 2Y) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (a > 2Y) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: tinyint), b (type: smallint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: explain select * from t1_n114 where b < 2 @@ -1144,14 +1144,14 @@ STAGE PLANS: TableScan alias: t1_n114 filterExpr: (b < 2S) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (b < 2S) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: tinyint), b (type: smallint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: explain select * from t1_n114 where a < 200 @@ -1169,14 +1169,14 @@ STAGE PLANS: TableScan alias: t1_n114 filterExpr: (UDFToInteger(a) < 200) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToInteger(a) < 200) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: tinyint), b (type: smallint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: explain select * from t1_n114 where b > 40000 @@ -1194,14 +1194,14 @@ STAGE PLANS: TableScan alias: t1_n114 filterExpr: (UDFToInteger(b) > 40000) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToInteger(b) > 40000) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: tinyint), b (type: smallint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: drop table t1_n114 diff --git a/ql/src/test/results/clientpositive/udaf_binarysetfunctions.q.out b/ql/src/test/results/clientpositive/udaf_binarysetfunctions.q.out index bac37661fb..2674d4d579 100644 --- a/ql/src/test/results/clientpositive/udaf_binarysetfunctions.q.out +++ b/ql/src/test/results/clientpositive/udaf_binarysetfunctions.q.out @@ -377,22 +377,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n21 - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 5044 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: px (type: int), x (type: decimal(10,0)), y (type: decimal(10,0)), UDFToDouble(x) (type: double), (UDFToDouble(x) * UDFToDouble(x)) (type: double), UDFToDouble(y) (type: double), (UDFToDouble(y) * UDFToDouble(y)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 5044 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col4), sum(_col3), count(_col1), sum(_col6), sum(_col5), count(_col2), corr(_col2, _col1), covar_samp(_col2, _col1), covar_pop(_col2, _col1), regr_count(_col2, _col1), regr_slope(_col2, _col1), regr_intercept(_col2, _col1), regr_r2(_col2, _col1), regr_sxx(_col2, _col1), regr_syy(_col2, _col1), regr_sxy(_col2, _col1), regr_avgx(_col2, _col1), regr_avgy(_col2, _col1) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 11396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 11396 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: bigint), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: bigint), _col11 (type: struct), _col12 (type: struct), _col13 (type: struct), _col14 (type: struct), _col15 (type: struct), _col16 (type: struct), _col17 (type: struct), _col18 (type: struct) Reduce Operator Tree: Group By Operator @@ -400,11 +400,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18 - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), ((_col4 - ((_col5 * _col5) / _col6)) / _col6) (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: bigint), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: decimal(14,4)), _col18 (type: decimal(14,4)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2324 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -419,17 +419,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2324 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: bigint), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(14,4)), _col14 (type: decimal(14,4)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: decimal(14,4)), VALUE._col13 (type: decimal(14,4)), VALUE._col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2324 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2324 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udaf_binarysetfunctions_no_cbo.q.out b/ql/src/test/results/clientpositive/udaf_binarysetfunctions_no_cbo.q.out index 2fb18c46f5..1e496378b0 100644 --- a/ql/src/test/results/clientpositive/udaf_binarysetfunctions_no_cbo.q.out +++ b/ql/src/test/results/clientpositive/udaf_binarysetfunctions_no_cbo.q.out @@ -377,22 +377,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t_n6 - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 5044 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: px (type: int), y (type: decimal(10,0)), x (type: decimal(10,0)) outputColumnNames: px, y, x - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 5044 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: var_pop(x), var_pop(y), corr(y, x), covar_samp(y, x), covar_pop(y, x), regr_count(y, x), regr_slope(y, x), regr_intercept(y, x), regr_r2(y, x), regr_sxx(y, x), regr_syy(y, x), regr_sxy(y, x), regr_avgx(y, x), regr_avgy(y, x) keys: px (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 12180 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 29 Data size: 281 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 12180 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: bigint), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct), _col13 (type: struct), _col14 (type: struct) Reduce Operator Tree: Group By Operator @@ -400,7 +400,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -415,17 +415,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: bigint), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(14,4)), _col14 (type: decimal(14,4)) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: double), VALUE._col11 (type: double), VALUE._col12 (type: decimal(14,4)), VALUE._col13 (type: decimal(14,4)), VALUE._col5 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2324 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 14 Data size: 135 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2324 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udaf_percentile_approx_23.q.out b/ql/src/test/results/clientpositive/udaf_percentile_approx_23.q.out index 7a27cd0a78..dad4bc1ef9 100644 --- a/ql/src/test/results/clientpositive/udaf_percentile_approx_23.q.out +++ b/ql/src/test/results/clientpositive/udaf_percentile_approx_23.q.out @@ -510,29 +510,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: bucket_n0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CASE WHEN ((key < 100.0D)) THEN (NaND) ELSE (key) END (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: percentile_approx(_col0, 0.5) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array) Reduce Operator Tree: Group By Operator aggregations: percentile_approx(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -569,29 +569,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: bucket_n0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: percentile_approx(_col0, 0.5) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array) Reduce Operator Tree: Group By Operator aggregations: percentile_approx(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf1.q.out b/ql/src/test/results/clientpositive/udf1.q.out index 775a412d9a..e5c3a451fe 100644 --- a/ql/src/test/results/clientpositive/udf1.q.out +++ b/ql/src/test/results/clientpositive/udf1.q.out @@ -49,17 +49,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'TRUE' (type: string), 'FALSE' (type: string), 'TRUE' (type: string), 'TRUE' (type: string), 'TRUE' (type: string), 'FALSE' (type: string), 'FALSE' (type: string), 'FALSE' (type: string), 'TRUE' (type: string), 'TRUE' (type: string), 'FALSE' (type: string), 'TRUE' (type: string), 'TRUE' (type: string), 'acc' (type: string), 'abc' (type: string), 'abb' (type: string), 'hive' (type: string), 'hadoop' (type: string), 'AaAbAcA' (type: string), 'FALSE' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 442000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 442000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -68,25 +68,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string) outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16, c17, c18, c19, c20 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 442000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll'), compute_stats(c10, 'hll'), compute_stats(c11, 'hll'), compute_stats(c12, 'hll'), compute_stats(c13, 'hll'), compute_stats(c14, 'hll'), compute_stats(c15, 'hll'), compute_stats(c16, 'hll'), compute_stats(c17, 'hll'), compute_stats(c18, 'hll'), compute_stats(c19, 'hll'), compute_stats(c20, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col5 (type: struct), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct), _col13 (type: struct), _col14 (type: struct), _col15 (type: struct), _col16 (type: struct), _col17 (type: struct), _col18 (type: struct), _col19 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8), compute_stats(VALUE._col9), compute_stats(VALUE._col10), compute_stats(VALUE._col11), compute_stats(VALUE._col12), compute_stats(VALUE._col13), compute_stats(VALUE._col14), compute_stats(VALUE._col15), compute_stats(VALUE._col16), compute_stats(VALUE._col17), compute_stats(VALUE._col18), compute_stats(VALUE._col19) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8800 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf2.q.out b/ql/src/test/results/clientpositive/udf2.q.out index 9d710d1109..1be08fc825 100644 --- a/ql/src/test/results/clientpositive/udf2.q.out +++ b/ql/src/test/results/clientpositive/udf2.q.out @@ -31,14 +31,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: dest1_n55 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: '|' (type: string), trim(c1) (type: string), '|' (type: string), rtrim(c1) (type: string), '|' (type: string), ltrim(c1) (type: string), '|' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf8.q.out b/ql/src/test/results/clientpositive/udf8.q.out index 954b6aac4b..714cd4cd96 100644 --- a/ql/src/test/results/clientpositive/udf8.q.out +++ b/ql/src/test/results/clientpositive/udf8.q.out @@ -40,33 +40,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: dest1_n54 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: string) outputColumnNames: c1 - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(c1), count(c1) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: double), _col0 (type: double), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf9.q.out b/ql/src/test/results/clientpositive/udf9.q.out index 0660ab9379..9d24f467aa 100644 --- a/ql/src/test/results/clientpositive/udf9.q.out +++ b/ql/src/test/results/clientpositive/udf9.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: -1 (type: int), 2 (type: int), 32 (type: int), -1 (type: int), DATE'2009-01-01' (type: date), DATE'2009-12-31' (type: date), DATE'2008-03-01' (type: date), DATE'2009-03-02' (type: date), DATE'2008-02-28' (type: date), DATE'2009-02-27' (type: date), DATE'2008-12-31' (type: date), DATE'2008-01-02' (type: date), DATE'2008-02-26' (type: date), DATE'2009-02-26' (type: date), DATE'2006-02-28' (type: date), DATE'2005-02-28' (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 172000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 172000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_10_trims.q.out b/ql/src/test/results/clientpositive/udf_10_trims.q.out index 48cc473e39..87ad9d0a42 100644 --- a/ql/src/test/results/clientpositive/udf_10_trims.q.out +++ b/ql/src/test/results/clientpositive/udf_10_trims.q.out @@ -35,17 +35,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'abc' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -54,25 +54,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(c1, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_between.q.out b/ql/src/test/results/clientpositive/udf_between.q.out index 5e86c0889f..3d0aca2bf1 100644 --- a/ql/src/test/results/clientpositive/udf_between.q.out +++ b/ql/src/test/results/clientpositive/udf_between.q.out @@ -25,17 +25,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) + 100.0D) BETWEEN 100.0D AND 200.0D (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) + 100.0D) BETWEEN 100.0D AND 200.0D (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT * FROM src where key + 100 between (150 + -50) AND (150 + 50) LIMIT 20 @@ -81,17 +81,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (not (UDFToDouble(key) + 100.0D) BETWEEN 100.0D AND 200.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not (UDFToDouble(key) + 100.0D) BETWEEN 100.0D AND 200.0D) (type: boolean) - Statistics: Num rows: 445 Data size: 4727 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 445 Data size: 79210 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 445 Data size: 4727 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 445 Data size: 79210 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT * FROM src where key + 100 not between (150 + -50) AND (150 + 50) LIMIT 20 @@ -136,14 +136,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT * FROM src where 'b' between 'a' AND 'c' LIMIT 1 @@ -169,14 +169,14 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT * FROM src where 2 between 2 AND '3' LIMIT 1 diff --git a/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out b/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out index b9d6e2a687..da4a3ce2d9 100644 --- a/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out +++ b/ql/src/test/results/clientpositive/udf_case_column_pruning.q.out @@ -30,35 +30,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -67,11 +67,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CASE WHEN ((_col0 = '1')) THEN (2) WHEN ((_col0 = '3')) THEN (4) ELSE (5) END (type: int) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 3164 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -86,20 +86,20 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 3164 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 3164 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_case_thrift.q.out b/ql/src/test/results/clientpositive/udf_case_thrift.q.out index ba0784218a..46c564a4c8 100644 --- a/ql/src/test/results/clientpositive/udf_case_thrift.q.out +++ b/ql/src/test/results/clientpositive/udf_case_thrift.q.out @@ -45,11 +45,11 @@ STAGE PLANS: TableScan alias: src_thrift Row Limit Per Split: 3 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 22440 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CASE (lint[0]) WHEN (0) THEN ((lint[0] + 1)) WHEN (1) THEN ((lint[0] + 2)) WHEN (2) THEN (100) ELSE (5) END (type: int), CASE (lstring[0]) WHEN ('0') THEN ('zero') WHEN ('10') THEN (concat(lstring[0], ' is ten')) ELSE ('default') END (type: string), CASE (lstring[0]) WHEN ('0') THEN (lstring) ELSE (null) END[0] (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 22440 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT CASE src_thrift.lint[0] diff --git a/ql/src/test/results/clientpositive/udf_character_length.q.out b/ql/src/test/results/clientpositive/udf_character_length.q.out index 046d207376..5fe61d2fb7 100644 --- a/ql/src/test/results/clientpositive/udf_character_length.q.out +++ b/ql/src/test/results/clientpositive/udf_character_length.q.out @@ -58,14 +58,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: character_length(value) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -74,25 +74,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: len - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(len, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -244,11 +244,11 @@ STAGE PLANS: Processor Tree: TableScan alias: dest1_n97 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: character_length(name) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT character_length(dest1_n97.name) FROM dest1_n97 @@ -275,11 +275,11 @@ STAGE PLANS: Processor Tree: TableScan alias: dest1_n97 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: character_length(name) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT char_length(dest1_n97.name) FROM dest1_n97 diff --git a/ql/src/test/results/clientpositive/udf_concat_ws.q.out b/ql/src/test/results/clientpositive/udf_concat_ws.q.out index 3c5622540a..3b8c4bc959 100644 --- a/ql/src/test/results/clientpositive/udf_concat_ws.q.out +++ b/ql/src/test/results/clientpositive/udf_concat_ws.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Processor Tree: TableScan alias: dest1_n8 - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: concat_ws(c1, c2, c3) (type: string), concat_ws(',', c1, c2, c3) (type: string), concat_ws(null, c1, c2, c3) (type: string), concat_ws('**', c1, null, c3) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT concat_ws(dest1_n8.c1, dest1_n8.c2, dest1_n8.c3), diff --git a/ql/src/test/results/clientpositive/udf_count.q.out b/ql/src/test/results/clientpositive/udf_count.q.out index 29e4f6879d..9ac83b4349 100644 --- a/ql/src/test/results/clientpositive/udf_count.q.out +++ b/ql/src/test/results/clientpositive/udf_count.q.out @@ -52,33 +52,33 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -92,7 +92,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -100,10 +100,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -138,30 +138,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT key, value) keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col0:0._col0, KEY._col0:0._col1) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_find_in_set.q.out b/ql/src/test/results/clientpositive/udf_find_in_set.q.out index 79ce3322e6..2eea3a465b 100644 --- a/ql/src/test/results/clientpositive/udf_find_in_set.q.out +++ b/ql/src/test/results/clientpositive/udf_find_in_set.q.out @@ -32,11 +32,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: find_in_set(key, concat(key, ',', value)) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: FROM src1 SELECT find_in_set(src1.key,concat(src1.key,',',src1.value)) diff --git a/ql/src/test/results/clientpositive/udf_folder_constants.q.out b/ql/src/test/results/clientpositive/udf_folder_constants.q.out index bdaef121c6..b74a42df25 100644 --- a/ql/src/test/results/clientpositive/udf_folder_constants.q.out +++ b/ql/src/test/results/clientpositive/udf_folder_constants.q.out @@ -58,35 +58,35 @@ STAGE PLANS: TableScan alias: udf_tb1 filterExpr: ((year = 2001) and month is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((year = 2001) and month is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: month (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: month is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: month is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: month (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -94,14 +94,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 978307200L (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_get_json_object.q.out b/ql/src/test/results/clientpositive/udf_get_json_object.q.out index 8e3b52accd..9711c41741 100644 --- a/ql/src/test/results/clientpositive/udf_get_json_object.q.out +++ b/ql/src/test/results/clientpositive/udf_get_json_object.q.out @@ -58,11 +58,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src_json - Statistics: Num rows: 1 Data size: 644 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE Select Operator #### A masked pattern was here #### outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 644 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT get_json_object(src_json.json, '$') FROM src_json diff --git a/ql/src/test/results/clientpositive/udf_hour.q.out b/ql/src/test/results/clientpositive/udf_hour.q.out index 353f9240ed..732be0e779 100644 --- a/ql/src/test/results/clientpositive/udf_hour.q.out +++ b/ql/src/test/results/clientpositive/udf_hour.q.out @@ -37,14 +37,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 13 (type: int), null (type: int), 0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2004 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT hour('2009-08-07 13:14:15'), hour('13:14:15'), hour('2009-08-07') diff --git a/ql/src/test/results/clientpositive/udf_in_file.q.out b/ql/src/test/results/clientpositive/udf_in_file.q.out index f5310c6dff..492eb7caa9 100644 --- a/ql/src/test/results/clientpositive/udf_in_file.q.out +++ b/ql/src/test/results/clientpositive/udf_in_file.q.out @@ -57,17 +57,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: value_src - Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 730 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: in_file(str_val, '../../data/files/test2.dat') (type: boolean), in_file(ch_val, '../../data/files/test2.dat') (type: boolean), in_file(vch_val, '../../data/files/test2.dat') (type: boolean), in_file(str_val_neg, '../../data/files/test2.dat') (type: boolean), in_file(ch_val_neg, '../../data/files/test2.dat') (type: boolean), in_file(vch_val_neg, '../../data/files/test2.dat') (type: boolean), in_file('303', '../../data/files/test2.dat') (type: boolean), in_file('304', '../../data/files/test2.dat') (type: boolean), in_file(null, '../../data/files/test2.dat') (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 730 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 730 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 730 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out b/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out index 09a4deae4a..d272164172 100644 --- a/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out +++ b/ql/src/test/results/clientpositive/udf_isnull_isnotnull.q.out @@ -100,17 +100,17 @@ STAGE PLANS: TableScan alias: src_thrift filterExpr: (lint is not null and mstringstring is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (lint is not null and mstringstring is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lint is not null (type: boolean), lintstring is not null (type: boolean), mstringstring is not null (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 2790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3600 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: FROM src_thrift diff --git a/ql/src/test/results/clientpositive/udf_length.q.out b/ql/src/test/results/clientpositive/udf_length.q.out index d463b29691..b910ac7342 100644 --- a/ql/src/test/results/clientpositive/udf_length.q.out +++ b/ql/src/test/results/clientpositive/udf_length.q.out @@ -41,14 +41,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: length(value) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -57,25 +57,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: len - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(len, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -218,11 +218,11 @@ STAGE PLANS: Processor Tree: TableScan alias: dest1_n134 - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: length(name) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 60 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT length(dest1_n134.name) FROM dest1_n134 diff --git a/ql/src/test/results/clientpositive/udf_like.q.out b/ql/src/test/results/clientpositive/udf_like.q.out index 8a94e0e7d9..f05e0e59c5 100644 --- a/ql/src/test/results/clientpositive/udf_like.q.out +++ b/ql/src/test/results/clientpositive/udf_like.q.out @@ -36,14 +36,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: true (type: boolean), false (type: boolean), true (type: boolean), true (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), true (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), false (type: boolean), true (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT '_%_' LIKE '%\_\%\_%', '__' LIKE '%\_\%\_%', '%%_%_' LIKE '%\_\%\_%', '%_%_%' LIKE '%\%\_\%', diff --git a/ql/src/test/results/clientpositive/udf_lower.q.out b/ql/src/test/results/clientpositive/udf_lower.q.out index 52bb21704e..a76394a7f6 100644 --- a/ql/src/test/results/clientpositive/udf_lower.q.out +++ b/ql/src/test/results/clientpositive/udf_lower.q.out @@ -31,17 +31,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'abc 123' (type: string), 'ABC 123' (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_minute.q.out b/ql/src/test/results/clientpositive/udf_minute.q.out index 5a262358ce..ac74f139b2 100644 --- a/ql/src/test/results/clientpositive/udf_minute.q.out +++ b/ql/src/test/results/clientpositive/udf_minute.q.out @@ -37,17 +37,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 14 (type: int), null (type: int), 0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2004 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2004 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_notequal.q.out b/ql/src/test/results/clientpositive/udf_notequal.q.out index 41d973bd20..5491d91044 100644 --- a/ql/src/test/results/clientpositive/udf_notequal.q.out +++ b/ql/src/test/results/clientpositive/udf_notequal.q.out @@ -45,14 +45,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (key <> '302') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key <> '302') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT key, value @@ -587,14 +587,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (key <> '302') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key <> '302') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT key, value diff --git a/ql/src/test/results/clientpositive/udf_octet_length.q.out b/ql/src/test/results/clientpositive/udf_octet_length.q.out index cbb614c235..6d14bfb7aa 100644 --- a/ql/src/test/results/clientpositive/udf_octet_length.q.out +++ b/ql/src/test/results/clientpositive/udf_octet_length.q.out @@ -41,14 +41,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: octet_length(value) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -57,25 +57,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: len - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(len, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -227,11 +227,11 @@ STAGE PLANS: Processor Tree: TableScan alias: dest1_n165 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: octet_length(name) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: SELECT octet_length(dest1_n165.name) FROM dest1_n165 diff --git a/ql/src/test/results/clientpositive/udf_parse_url.q.out b/ql/src/test/results/clientpositive/udf_parse_url.q.out index f1254dcc1f..f5e73ca0c5 100644 --- a/ql/src/test/results/clientpositive/udf_parse_url.q.out +++ b/ql/src/test/results/clientpositive/udf_parse_url.q.out @@ -58,17 +58,17 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'facebook.com' (type: string), '/path1/p.php' (type: string), 'k1=v1&k2=v2' (type: string), 'Ref1' (type: string), 'v2' (type: string), 'v1' (type: string), null (type: string), '/path1/p.php?k1=v1&k2=v2' (type: string), 'http' (type: string), null (type: string), 'facebook.com' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 209918 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 209918 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_reflect.q.out b/ql/src/test/results/clientpositive/udf_reflect.q.out index 97e40d1509..012174e5a3 100644 --- a/ql/src/test/results/clientpositive/udf_reflect.q.out +++ b/ql/src/test/results/clientpositive/udf_reflect.q.out @@ -46,12 +46,12 @@ STAGE PLANS: TableScan alias: src Row Limit Per Split: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: reflect('java.lang.String','valueOf',1) (type: string), reflect('java.lang.String','isEmpty') (type: string), reflect('java.lang.Math','max',2,3) (type: string), reflect('java.lang.Math','min',2,3) (type: string), reflect('java.lang.Math','round',2.5D) (type: string), round(reflect('java.lang.Math','exp',1.0D), 6) (type: double), reflect('java.lang.Math','floor',1.9D) (type: string), reflect('java.lang.Integer','valueOf',key,16) (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 648000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT reflect("java.lang.String", "valueOf", 1), diff --git a/ql/src/test/results/clientpositive/udf_reflect2.q.out b/ql/src/test/results/clientpositive/udf_reflect2.q.out index f3bbff24d6..afe25975ba 100644 --- a/ql/src/test/results/clientpositive/udf_reflect2.q.out +++ b/ql/src/test/results/clientpositive/udf_reflect2.q.out @@ -93,15 +93,15 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: UDFToInteger(key) (type: int), reflect2(UDFToInteger(key),'byteValue') (type: tinyint), reflect2(UDFToInteger(key),'shortValue') (type: smallint), reflect2(UDFToInteger(key),'intValue') (type: int), reflect2(UDFToInteger(key),'longValue') (type: bigint), reflect2(UDFToInteger(key),'floatValue') (type: float), reflect2(UDFToInteger(key),'doubleValue') (type: double), reflect2(UDFToInteger(key),'toString') (type: string), value (type: string), reflect2(value,'concat','_concat') (type: string), reflect2(value,'contains','86') (type: boolean), reflect2(value,'startsWith','v') (type: boolean), reflect2(value,'endsWith','6') (type: boolean), reflect2(value,'equals','val_86') (type: boolean), reflect2(value,'equalsIgnoreCase','VAL_86') (type: boolean), reflect2(value,'getBytes') (type: binary), reflect2(value,'indexOf','1') (type: int), reflect2(value,'lastIndexOf','1') (type: int), reflect2(value,'replace','val','VALUE') (type: string), reflect2(value,'substring',1) (type: string), reflect2(value,'substring',1,5) (type: string), reflect2(value,'toUpperCase') (type: string), reflect2(value,'trim') (type: string), TIMESTAMP'2013-02-15 19:41:20' (type: timestamp), 2013 (type: int), 2 (type: int), 15 (type: int), 19 (type: int), 41 (type: int), 20 (type: int), 1360957280000L (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 829500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 8295 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT key, diff --git a/ql/src/test/results/clientpositive/udf_reverse.q.out b/ql/src/test/results/clientpositive/udf_reverse.q.out index fc39abb0e7..05e45b0bbc 100644 --- a/ql/src/test/results/clientpositive/udf_reverse.q.out +++ b/ql/src/test/results/clientpositive/udf_reverse.q.out @@ -41,14 +41,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(value) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -57,25 +57,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: len - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(len, 'hll') mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udf_second.q.out b/ql/src/test/results/clientpositive/udf_second.q.out index 47652447fb..cd2ab8fb19 100644 --- a/ql/src/test/results/clientpositive/udf_second.q.out +++ b/ql/src/test/results/clientpositive/udf_second.q.out @@ -37,14 +37,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 86.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 15 (type: int), null (type: int), 0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2004 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT second('2009-08-07 13:14:15'), second('13:14:15'), second('2009-08-07') diff --git a/ql/src/test/results/clientpositive/udf_size.q.out b/ql/src/test/results/clientpositive/udf_size.q.out index 99cd74ed77..a91f80e161 100644 --- a/ql/src/test/results/clientpositive/udf_size.q.out +++ b/ql/src/test/results/clientpositive/udf_size.q.out @@ -39,17 +39,17 @@ STAGE PLANS: TableScan alias: src_thrift filterExpr: (lint is not null and mstringstring is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (lint is not null and mstringstring is not null) (type: boolean) - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: size(lint) (type: int), size(lintstring) (type: int), size(mstringstring) (type: int), -1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 39600 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 2790 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3600 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: FROM src_thrift diff --git a/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out b/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out index 328926038b..c285682f5f 100644 --- a/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out +++ b/ql/src/test/results/clientpositive/udf_to_unix_timestamp.q.out @@ -102,14 +102,14 @@ STAGE PLANS: TableScan alias: src filterExpr: (to_unix_timestamp(key) > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (to_unix_timestamp(key) > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from (select * from src) a where to_unix_timestamp(a.key) > 10 @@ -127,13 +127,13 @@ STAGE PLANS: TableScan alias: src filterExpr: (to_unix_timestamp(key) > 10) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (to_unix_timestamp(key) > 10) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE ListSink diff --git a/ql/src/test/results/clientpositive/udf_trunc_number.q.out b/ql/src/test/results/clientpositive/udf_trunc_number.q.out index 9deb381b41..cf1a3f4f44 100644 --- a/ql/src/test/results/clientpositive/udf_trunc_number.q.out +++ b/ql/src/test/results/clientpositive/udf_trunc_number.q.out @@ -69,11 +69,11 @@ STAGE PLANS: Processor Tree: TableScan alias: sampletable - Statistics: Num rows: 1 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: trunc(c, d) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select trunc (c,d) from sampletable @@ -124,11 +124,11 @@ STAGE PLANS: Processor Tree: TableScan alias: sampletable1 - Statistics: Num rows: 1 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: trunc(c, d) (type: float) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select trunc (c,d) from sampletable1 @@ -179,11 +179,11 @@ STAGE PLANS: Processor Tree: TableScan alias: sampletable2 - Statistics: Num rows: 1 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: trunc(c, d) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select trunc (c,d) from sampletable2 @@ -234,11 +234,11 @@ STAGE PLANS: Processor Tree: TableScan alias: sampletable3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: trunc(c, d) (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select trunc (c,d) from sampletable3 @@ -289,11 +289,11 @@ STAGE PLANS: Processor Tree: TableScan alias: sampletable4 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: trunc(c, d) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select trunc (c,d) from sampletable4 diff --git a/ql/src/test/results/clientpositive/udf_union.q.out b/ql/src/test/results/clientpositive/udf_union.q.out index d67c2a21df..a33e7a5257 100644 --- a/ql/src/test/results/clientpositive/udf_union.q.out +++ b/ql/src/test/results/clientpositive/udf_union.q.out @@ -34,11 +34,11 @@ STAGE PLANS: TableScan alias: src Row Limit Per Split: 2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: create_union(0,key) (type: uniontype), create_union(if((key < 100), 0, 1),2,value) (type: uniontype), create_union(1,'a',const struct(2,'b')) (type: uniontype>) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 409000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT create_union(0, key), create_union(if(key<100, 0, 1), 2.0, value), diff --git a/ql/src/test/results/clientpositive/udtf_json_tuple.q.out b/ql/src/test/results/clientpositive/udtf_json_tuple.q.out index d500c14c64..f8d5563145 100644 --- a/ql/src/test/results/clientpositive/udtf_json_tuple.q.out +++ b/ql/src/test/results/clientpositive/udtf_json_tuple.q.out @@ -58,52 +58,52 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3179 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 6364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) Select Operator expressions: jstring (type: string), 'f1' (type: string), 'f2' (type: string), 'f3' (type: string), 'f4' (type: string), 'f5' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3185 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3185 Basic stats: COMPLETE Column stats: COMPLETE function name: json_tuple Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 6364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -145,31 +145,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: jstring (type: string), 'f1' (type: string), 'f2' (type: string), 'f3' (type: string), 'f4' (type: string), 'f5' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3306 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3306 Basic stats: COMPLETE Column stats: COMPLETE function name: json_tuple Select Operator expressions: c0 (type: string), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string), _col4 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -211,52 +211,52 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1236 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3179 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 6364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col6 (type: string), _col9 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Select Operator expressions: jstring (type: string), 'f1' (type: string), 'f2' (type: string), 'f3' (type: string), 'f4' (type: string), 'f5' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3185 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3185 Basic stats: COMPLETE Column stats: COMPLETE function name: json_tuple Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 6364 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col6 (type: string), _col9 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -299,58 +299,58 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2669 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 5854 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col6 (type: string) outputColumnNames: _col6 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 5854 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col6 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: jstring (type: string), 'f1' (type: string), 'f2' (type: string), 'f3' (type: string), 'f4' (type: string), 'f5' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3185 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3185 Basic stats: COMPLETE Column stats: COMPLETE function name: json_tuple Filter Operator predicate: c0 is not null (type: boolean) - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3185 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 5854 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col6 (type: string) outputColumnNames: _col6 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 5854 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col6 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -358,7 +358,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -373,17 +373,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 236 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out b/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out index 51e23e53ca..2652499db0 100644 --- a/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out +++ b/ql/src/test/results/clientpositive/udtf_parse_url_tuple.q.out @@ -77,52 +77,52 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3159 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8598 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) Select Operator expressions: fullurl (type: string), 'HOST' (type: string), 'PATH' (type: string), 'QUERY' (type: string), 'REF' (type: string), 'PROTOCOL' (type: string), 'FILE' (type: string), 'AUTHORITY' (type: string), 'USERINFO' (type: string), 'QUERY:k1' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 5439 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 5439 Basic stats: COMPLETE Column stats: COMPLETE function name: parse_url_tuple Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8598 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -164,31 +164,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: fullurl (type: string), 'HOST' (type: string), 'PATH' (type: string), 'QUERY' (type: string), 'REF' (type: string), 'PROTOCOL' (type: string), 'FILE' (type: string), 'AUTHORITY' (type: string), 'USERINFO' (type: string), 'QUERY:k1' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 5556 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 5556 Basic stats: COMPLETE Column stats: COMPLETE function name: parse_url_tuple Select Operator expressions: c0 (type: string), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: string), c6 (type: string), c7 (type: string), c8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -230,52 +230,52 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 3159 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 10266 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col7 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) Select Operator expressions: fullurl (type: string), 'HOST' (type: string), 'PATH' (type: string), 'QUERY' (type: string), 'REF' (type: string), 'PROTOCOL' (type: string), 'FILE' (type: string), 'AUTHORITY' (type: string), 'USERINFO' (type: string), 'QUERY:k1' (type: string), 'host' (type: string), 'query' (type: string), 'QUERY:nonExistCol' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 7107 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 7107 Basic stats: COMPLETE Column stats: COMPLETE function name: parse_url_tuple Lateral View Join Operator outputColumnNames: _col0, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 10266 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col5 (type: string), _col7 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -317,58 +317,58 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 2649 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: string) outputColumnNames: _col5 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col5 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: fullurl (type: string), 'HOST' (type: string), 'PATH' (type: string), 'QUERY' (type: string), 'REF' (type: string), 'PROTOCOL' (type: string), 'FILE' (type: string), 'AUTHORITY' (type: string), 'USERINFO' (type: string), 'QUERY:k1' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 5439 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 5439 Basic stats: COMPLETE Column stats: COMPLETE function name: parse_url_tuple Filter Operator predicate: c8 is not null (type: boolean) - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 5439 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8088 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: string) outputColumnNames: _col5 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 8088 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col5 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 426 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -376,10 +376,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6 Data size: 213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union.q.out b/ql/src/test/results/clientpositive/union.q.out index 64b9c683cc..3dfc85ec0c 100644 --- a/ql/src/test/results/clientpositive/union.q.out +++ b/ql/src/test/results/clientpositive/union.q.out @@ -30,19 +30,19 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -50,19 +50,19 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 332 Data size: 3526 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union11.q.out b/ql/src/test/results/clientpositive/union11.q.out index 19b85ae504..7d8d426d9f 100644 --- a/ql/src/test/results/clientpositive/union11.q.out +++ b/ql/src/test/results/clientpositive/union11.q.out @@ -25,19 +25,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -45,11 +45,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -62,48 +62,48 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -111,10 +111,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -125,19 +125,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -145,11 +145,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -162,19 +162,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -182,11 +182,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst3' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union13.q.out b/ql/src/test/results/clientpositive/union13.q.out index 31219d43bf..ad79df2499 100644 --- a/ql/src/test/results/clientpositive/union13.q.out +++ b/ql/src/test/results/clientpositive/union13.q.out @@ -16,32 +16,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union14.q.out b/ql/src/test/results/clientpositive/union14.q.out index c7a7798a38..bde4d02b1e 100644 --- a/ql/src/test/results/clientpositive/union14.q.out +++ b/ql/src/test/results/clientpositive/union14.q.out @@ -21,19 +21,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -41,11 +41,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -58,39 +58,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2238 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2238 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -98,10 +98,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union15.q.out b/ql/src/test/results/clientpositive/union15.q.out index feb53d0cf3..6f304501d7 100644 --- a/ql/src/test/results/clientpositive/union15.q.out +++ b/ql/src/test/results/clientpositive/union15.q.out @@ -23,19 +23,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -43,11 +43,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -60,60 +60,60 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 4388 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 4388 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: s3 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 4388 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -121,10 +121,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 16 Data size: 1536 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union17.q.out b/ql/src/test/results/clientpositive/union17.q.out index 8f1a2d9c07..523b041da5 100644 --- a/ql/src/test/results/clientpositive/union17.q.out +++ b/ql/src/test/results/clientpositive/union17.q.out @@ -80,24 +80,24 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(_col1, 5)) keys: _col0 (type: string), substr(_col1, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(_col1, 5)) keys: _col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 464 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 232464 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -106,30 +106,30 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(_col1, 5)) keys: _col0 (type: string), substr(_col1, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 70000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT substr(_col1, 5)) keys: _col0 (type: string), _col1 (type: string), substr(_col1, 5) (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 464 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 232464 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -142,14 +142,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 68000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 68000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -158,12 +158,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 68000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -195,7 +195,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -203,10 +203,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -228,7 +228,7 @@ STAGE PLANS: key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 464 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 232464 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -236,14 +236,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 140280 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), CAST( _col2 AS STRING) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -252,12 +252,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -281,7 +281,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -289,10 +289,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union18.q.out b/ql/src/test/results/clientpositive/union18.q.out index 5e456ddae2..ed1ed97f1f 100644 --- a/ql/src/test/results/clientpositive/union18.q.out +++ b/ql/src/test/results/clientpositive/union18.q.out @@ -83,10 +83,10 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -95,23 +95,23 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -120,12 +120,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -134,16 +134,16 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -152,23 +152,23 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 136272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -177,12 +177,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -194,10 +194,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -284,7 +284,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -292,10 +292,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union19.q.out b/ql/src/test/results/clientpositive/union19.q.out index e5c898d8cd..336aa0cc7d 100644 --- a/ql/src/test/results/clientpositive/union19.q.out +++ b/ql/src/test/results/clientpositive/union19.q.out @@ -79,26 +79,26 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -107,12 +107,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -121,32 +121,32 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 501 Data size: 5584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 89272 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Select Operator expressions: _col0 (type: string), _col1 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -155,12 +155,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, val1, val2 - Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 501 Data size: 228456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -173,14 +173,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 24000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 68000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 68000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -189,12 +189,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 250 Data size: 68000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -226,7 +226,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -234,10 +234,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -267,7 +267,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -275,10 +275,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union20.q.out b/ql/src/test/results/clientpositive/union20.q.out index 030dc7fcb4..344c781ce8 100644 --- a/ql/src/test/results/clientpositive/union20.q.out +++ b/ql/src/test/results/clientpositive/union20.q.out @@ -67,59 +67,59 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: s2 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan Union - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: s4 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 167 Data size: 2035 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 167 Data size: 29820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -129,10 +129,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 168 Data size: 91392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27889 Data size: 15171616 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 168 Data size: 91392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union21.q.out b/ql/src/test/results/clientpositive/union21.q.out index 062816e8e1..0f6771d3a1 100644 --- a/ql/src/test/results/clientpositive/union21.q.out +++ b/ql/src/test/results/clientpositive/union21.q.out @@ -44,102 +44,102 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1522 Data size: 114524 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1522 Data size: 201144 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: reverse(key) (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1522 Data size: 114524 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1522 Data size: 201144 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1522 Data size: 114524 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1522 Data size: 201144 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: astring (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 1522 Data size: 114524 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1522 Data size: 201144 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) TableScan alias: src_thrift - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 21120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: lstring[0] (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 30700 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 21120 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 1522 Data size: 114524 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1522 Data size: 201144 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -147,10 +147,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 60672 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union22.q.out b/ql/src/test/results/clientpositive/union22.q.out index d18fe68412..df5df74172 100644 --- a/ql/src/test/results/clientpositive/union22.q.out +++ b/ql/src/test/results/clientpositive/union22.q.out @@ -153,16 +153,16 @@ STAGE PLANS: TableScan alias: dst_union22_delta filterExpr: ((UDFToDouble(k0) > 50.0D) and (UDFToDouble(k1) > 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 16936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 176000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(k0) > 50.0D) and (UDFToDouble(k1) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 1862 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k3 (type: string), k4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 1862 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter mappings: 0 [1, 1] @@ -180,16 +180,16 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(k1) > 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 11124 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(k1) > 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 3693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k2 (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 3693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -203,11 +203,11 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 - Statistics: Num rows: 182 Data size: 4062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 39516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 4062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 39516 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 @@ -337,25 +337,25 @@ STAGE PLANS: TableScan alias: dst_union22_delta filterExpr: ((ds = '1') and (UDFToDouble(k0) <= 50.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 16936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 221500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(k0) <= 50.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 5622 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 73538 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k2 (type: string), k3 (type: string), k4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 5622 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 59096 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2/ - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -383,33 +383,33 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), '2' (type: string) outputColumnNames: k1, k2, k3, k4, ds - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 126832 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll'), compute_stats(k3, 'hll'), compute_stats(k4, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1845 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1845 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) auto parallelism: false TableScan GatherStats: false Union - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Static Partition Specification: ds=2/ - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 98612 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -437,19 +437,19 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), '2' (type: string) outputColumnNames: k1, k2, k3, k4, ds - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 332 Data size: 126832 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll'), compute_stats(k3, 'hll'), compute_stats(k4, 'hll') keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1845 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348 Data size: 9684 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1845 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 value expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) auto parallelism: false @@ -536,17 +536,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174 Data size: 4842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1845 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 174 Data size: 4842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1845 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 174 Data size: 4842 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1845 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -608,44 +608,44 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(k1) > 20.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 11124 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(k1) > 20.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 3693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k2 (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 3693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 3693 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string), _col2 (type: string) auto parallelism: false TableScan alias: dst_union22_delta filterExpr: ((UDFToDouble(k0) > 50.0D) and (UDFToDouble(k1) > 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 16936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 176000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: ((UDFToDouble(k0) > 50.0D) and (UDFToDouble(k1) > 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 1862 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 19360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: k1 (type: string), k3 (type: string), k4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 1862 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 1862 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col1 (type: string), _col2 (type: string) auto parallelism: false @@ -765,11 +765,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col4, _col5 - Statistics: Num rows: 182 Data size: 4062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 39516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 182 Data size: 4062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 39516 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 diff --git a/ql/src/test/results/clientpositive/union23.q.out b/ql/src/test/results/clientpositive/union23.q.out index e40b88cfbe..13ffef04a4 100644 --- a/ql/src/test/results/clientpositive/union23.q.out +++ b/ql/src/test/results/clientpositive/union23.q.out @@ -26,45 +26,45 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Transform Operator command: cat output info: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union24.q.out b/ql/src/test/results/clientpositive/union24.q.out index 6305260b5e..8335024490 100644 --- a/ql/src/test/results/clientpositive/union24.q.out +++ b/ql/src/test/results/clientpositive/union24.q.out @@ -96,24 +96,24 @@ STAGE PLANS: TableScan alias: src5_n3 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -178,7 +178,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 51 Data size: 244 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 8958 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -204,24 +204,24 @@ STAGE PLANS: TableScan alias: src2_n6 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -241,24 +241,24 @@ STAGE PLANS: TableScan alias: src3_n2 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -278,24 +278,24 @@ STAGE PLANS: TableScan alias: src4_n0 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -315,13 +315,13 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 360 Data size: 1726 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 360 Data size: 65598 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -618,43 +618,43 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan alias: b filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -769,11 +769,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -799,24 +799,24 @@ STAGE PLANS: TableScan alias: src2_n6 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 319 Data size: 57662 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 319 Data size: 57662 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -836,24 +836,24 @@ STAGE PLANS: TableScan alias: src3_n2 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 319 Data size: 57662 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 319 Data size: 57662 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -873,13 +873,13 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 319 Data size: 57662 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 319 Data size: 1531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 319 Data size: 57662 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1119,43 +1119,43 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan alias: b filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: @@ -1269,13 +1269,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -1305,7 +1305,7 @@ STAGE PLANS: null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: false @@ -1344,7 +1344,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 56 Data size: 269 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 9862 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 @@ -1370,24 +1370,24 @@ STAGE PLANS: TableScan alias: src2_n6 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 47622 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 47622 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1407,24 +1407,24 @@ STAGE PLANS: TableScan alias: src3_n2 filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), count (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 47622 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 47622 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -1444,13 +1444,13 @@ STAGE PLANS: TableScan GatherStats: false Union - Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 47622 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 262 Data size: 1257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 262 Data size: 47622 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/union25.q.out b/ql/src/test/results/clientpositive/union25.q.out index f4108826d9..4e975371e1 100644 --- a/ql/src/test/results/clientpositive/union25.q.out +++ b/ql/src/test/results/clientpositive/union25.q.out @@ -70,53 +70,53 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316 Data size: 54984 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -130,39 +130,39 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 816 Data size: 143984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 816 Data size: 143984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -170,14 +170,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union26.q.out b/ql/src/test/results/clientpositive/union26.q.out index 83bfc25e0e..f78907bf25 100644 --- a/ql/src/test/results/clientpositive/union26.q.out +++ b/ql/src/test/results/clientpositive/union26.q.out @@ -54,28 +54,28 @@ STAGE PLANS: TableScan alias: a filterExpr: ((ds = '2008-04-08') and (hr = '11') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: value (type: string) TableScan alias: b filterExpr: ((ds = '2008-04-08') and (hr = '12') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -84,7 +84,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,77 +97,77 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1791 Data size: 318798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 351000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col1, _col7 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 379000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1791 Data size: 318798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Select Operator expressions: array(1,2,3) (type: array) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 28000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col7 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 379000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1791 Data size: 318798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1550 Data size: 16467 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -175,14 +175,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 775 Data size: 8233 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 775 Data size: 8233 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 775 Data size: 8233 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 895 Data size: 166470 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union27.q.out b/ql/src/test/results/clientpositive/union27.q.out index a7bc5f404a..b1ee326ed5 100644 --- a/ql/src/test/results/clientpositive/union27.q.out +++ b/ql/src/test/results/clientpositive/union27.q.out @@ -49,56 +49,56 @@ STAGE PLANS: TableScan alias: a filterExpr: (UDFToDouble(key) = 97.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 97.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE TableScan alias: dim_pho_n0 filterExpr: (UDFToDouble(key) = 97.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 97.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: jackson_sev_add_n0 filterExpr: (UDFToDouble(key) = 97.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 97.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -108,14 +108,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 192684 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 192684 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 192684 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union28.q.out b/ql/src/test/results/clientpositive/union28.q.out index 16a8eb503b..6580e00049 100644 --- a/ql/src/test/results/clientpositive/union28.q.out +++ b/ql/src/test/results/clientpositive/union28.q.out @@ -50,28 +50,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -84,20 +84,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -106,26 +106,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -134,26 +134,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -162,25 +162,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -248,28 +248,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union29.q.out b/ql/src/test/results/clientpositive/union29.q.out index 68a28fb5f4..37a3c34367 100644 --- a/ql/src/test/results/clientpositive/union29.q.out +++ b/ql/src/test/results/clientpositive/union29.q.out @@ -48,20 +48,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -70,32 +70,32 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,32 +104,32 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -138,25 +138,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union30.q.out b/ql/src/test/results/clientpositive/union30.q.out index 271cbdf7f6..5530c1aa32 100644 --- a/ql/src/test/results/clientpositive/union30.q.out +++ b/ql/src/test/results/clientpositive/union30.q.out @@ -64,28 +64,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -98,20 +98,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -120,32 +120,32 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -154,26 +154,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -182,26 +182,26 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -210,25 +210,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 142500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -296,28 +296,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union31.q.out b/ql/src/test/results/clientpositive/union31.q.out index bd95e90055..88e17c7691 100644 --- a/ql/src/test/results/clientpositive/union31.q.out +++ b/ql/src/test/results/clientpositive/union31.q.out @@ -84,39 +84,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n28 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Select Operator expressions: _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -125,39 +125,39 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TableScan alias: t2_n19 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Select Operator expressions: _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -170,14 +170,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -186,12 +186,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: key, cnt - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -223,7 +223,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -231,10 +231,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -256,7 +256,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -265,14 +265,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -281,12 +281,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: value, cnt - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(value, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -310,7 +310,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -318,10 +318,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -444,22 +444,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n28 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -468,7 +468,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -481,38 +481,38 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Forward - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -521,12 +521,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: c1, cnt - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -538,14 +538,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -554,12 +554,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: c1, cnt - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -591,7 +591,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -599,10 +599,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -632,7 +632,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -640,10 +640,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -654,22 +654,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n19 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -678,7 +678,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -844,22 +844,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n28 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -868,11 +868,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -885,50 +885,50 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE TableScan alias: t2_n19 - Statistics: Num rows: 6 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Forward - Statistics: Num rows: 11 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -937,12 +937,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: c1, cnt - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -954,14 +954,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -970,12 +970,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: c1, cnt - Statistics: Num rows: 5 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: compute_stats(c1, 'hll'), compute_stats(cnt, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1007,7 +1007,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1015,10 +1015,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1048,7 +1048,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1048 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct), _col1 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -1056,10 +1056,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union32.q.out b/ql/src/test/results/clientpositive/union32.q.out index 72b2cd0fe1..4996f69adc 100644 --- a/ql/src/test/results/clientpositive/union32.q.out +++ b/ql/src/test/results/clientpositive/union32.q.out @@ -44,32 +44,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1_n70 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: t2_n43 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(UDFToLong(key)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -141,35 +141,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -178,11 +178,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -195,26 +195,26 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: t2_n43 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -298,35 +298,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -335,11 +335,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -352,26 +352,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n43 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(key) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -455,35 +455,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -492,11 +492,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double), CAST( CAST( _col1 AS CHAR(20)) AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -509,26 +509,26 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: t2_n43 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(key) (type: double), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -612,35 +612,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -649,11 +649,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double), CAST( CAST( _col1 AS CHAR(20)) AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -666,26 +666,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2_n43 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(key) (type: double), key (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 21 Data size: 147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 21 Data size: 3864 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union33.q.out b/ql/src/test/results/clientpositive/union33.q.out index 57c53089b9..fb637ee46d 100644 --- a/ql/src/test/results/clientpositive/union33.q.out +++ b/ql/src/test/results/clientpositive/union33.q.out @@ -42,22 +42,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -66,7 +66,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -82,7 +82,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -91,11 +91,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -109,19 +109,19 @@ STAGE PLANS: TableScan alias: src filterExpr: (UDFToDouble(key) = 0.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 0.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -130,22 +130,22 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -154,25 +154,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,22 +304,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -328,7 +328,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -344,7 +344,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -353,11 +353,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -370,10 +370,10 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -382,32 +382,32 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan alias: src filterExpr: (UDFToDouble(key) = 0.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(key) = 0.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 112250 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -416,25 +416,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 135500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union34.q.out b/ql/src/test/results/clientpositive/union34.q.out index 715d20a41e..2315fdec98 100644 --- a/ql/src/test/results/clientpositive/union34.q.out +++ b/ql/src/test/results/clientpositive/union34.q.out @@ -91,14 +91,14 @@ STAGE PLANS: TableScan alias: src10_1_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -109,32 +109,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src10_3_n0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: src10_4_n0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -142,14 +142,14 @@ STAGE PLANS: TableScan alias: src10_2_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -157,12 +157,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -254,36 +254,36 @@ STAGE PLANS: TableScan alias: src10_1_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) TableScan alias: src10_2_n0 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -292,7 +292,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -305,42 +305,42 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: src10_3_n0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: src10_4_n0 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 31 Data size: 322 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union37.q.out b/ql/src/test/results/clientpositive/union37.q.out index 9f3e350ab3..abc0ed0e48 100644 --- a/ql/src/test/results/clientpositive/union37.q.out +++ b/ql/src/test/results/clientpositive/union37.q.out @@ -72,32 +72,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: l_test1 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), 'table_1' (type: string), trans_date (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: l_test2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), val (type: string), trans_date (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -181,40 +181,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: l_test1 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), 'table_1' (type: string), trans_date (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), 999 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 394 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 394 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: l_test2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), val (type: string), trans_date (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), 999 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 394 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 394 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -306,40 +306,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: l_test1 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), 'table_1' (type: string), trans_date (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), 999 (type: int), 666 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 402 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 402 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: l_test2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), val (type: string), trans_date (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), 999 (type: int), 666 (type: int), _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 402 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 402 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -435,40 +435,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: l_test1 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), 'table_1' (type: string), trans_date (type: string), '2016-11-11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 287 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 574 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), 999 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: l_test2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: bigint), val (type: string), trans_date (type: string), trans_date (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 287 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 574 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), 999 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union5.q.out b/ql/src/test/results/clientpositive/union5.q.out index 94a74ec51f..92120084fd 100644 --- a/ql/src/test/results/clientpositive/union5.q.out +++ b/ql/src/test/results/clientpositive/union5.q.out @@ -20,19 +20,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -40,11 +40,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -57,33 +57,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan Union - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -91,10 +91,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -105,19 +105,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -125,11 +125,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union6.q.out b/ql/src/test/results/clientpositive/union6.q.out index 48224370b5..88a9b28972 100644 --- a/ql/src/test/results/clientpositive/union6.q.out +++ b/ql/src/test/results/clientpositive/union6.q.out @@ -70,10 +70,10 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -82,28 +82,28 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) TableScan alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 463 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -112,25 +112,25 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union7.q.out b/ql/src/test/results/clientpositive/union7.q.out index 28caa459a7..ae861aa9a3 100644 --- a/ql/src/test/results/clientpositive/union7.q.out +++ b/ql/src/test/results/clientpositive/union7.q.out @@ -19,19 +19,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -39,11 +39,11 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -56,39 +56,39 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2238 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) TableScan alias: s2 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2238 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -96,10 +96,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union8.q.out b/ql/src/test/results/clientpositive/union8.q.out index f58d54a788..b64b8c3c35 100644 --- a/ql/src/test/results/clientpositive/union8.q.out +++ b/ql/src/test/results/clientpositive/union8.q.out @@ -18,48 +18,48 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: s2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: s3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1500 Data size: 267000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_lateralview.q.out b/ql/src/test/results/clientpositive/union_lateralview.q.out index 421ba66b0e..7e3fc7e2c2 100644 --- a/ql/src/test/results/clientpositive/union_lateralview.q.out +++ b/ql/src/test/results/clientpositive/union_lateralview.q.out @@ -56,109 +56,109 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), array(1,2,3) (type: array) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 117000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 234000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 234000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 290000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 346000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Select Operator expressions: _col2 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 56000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 56000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 346000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: srcpart filterExpr: ((ds = '2008-04-08') and (hr = '12')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), array(1,2,3) (type: array) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 117000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 234000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Forward - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 234000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 290000 Basic stats: COMPLETE Column stats: COMPLETE Lateral View Join Operator outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 346000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) Select Operator expressions: _col2 (type: array) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 56000 Basic stats: COMPLETE Column stats: COMPLETE UDTF Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 56000 Basic stats: COMPLETE Column stats: COMPLETE function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 346000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 462000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: string) TableScan alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: key (type: string) sort order: + Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: @@ -167,14 +167,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 key (type: string) outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 364000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col3) (type: int), _col0 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 190000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 190000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -183,12 +183,12 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) outputColumnNames: key, arr_ele, value - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 190000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(arr_ele, 'hll'), compute_stats(value, 'hll') mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -220,7 +220,7 @@ STAGE PLANS: TableScan Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) Execution mode: vectorized Reduce Operator Tree: @@ -228,10 +228,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_offcbo.q.out b/ql/src/test/results/clientpositive/union_offcbo.q.out index 94d197f952..97d1c21aaa 100644 --- a/ql/src/test/results/clientpositive/union_offcbo.q.out +++ b/ql/src/test/results/clientpositive/union_offcbo.q.out @@ -247,36 +247,36 @@ STAGE PLANS: TableScan alias: ttest1 filterExpr: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE value expressions: _col9 (type: string) TableScan alias: ttest2 filterExpr: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), dt1 (type: string), dt2 (type: string), sts (type: string), at1 (type: bigint), khash (type: string), rhash (type: string) outputColumnNames: _col0, _col2, _col3, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: bigint), _col9 (type: string) Reduce Operator Tree: Join Operator @@ -286,14 +286,14 @@ STAGE PLANS: 0 _col8 (type: string) 1 _col8 (type: string) outputColumnNames: _col8, _col9, _col10, _col12, _col13, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col8,-1) <> NVL(_col18,-1)) or (NVL(_col9,-1) <> NVL(_col19,-1))) and (CASE WHEN ((_col18 is not null and _col8 is null and (_col12 >= '2016-02-05'))) THEN ('DEL') WHEN ((_col18 is not null and _col8 is null and (_col12 <= '2016-02-05'))) THEN ('RET') WHEN (((_col18 = _col8) and (_col19 <> _col9))) THEN ('A_INS') ELSE ('NA') END <> 'RET') and _col18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: bigint), _col16 (type: string), _col17 (type: bigint), _col13 (type: string), _col18 (type: string), _col19 (type: string), CASE WHEN ((_col18 is not null and _col8 is null and (_col12 >= '2016-02-05'))) THEN ('DEL') WHEN ((_col18 is not null and _col8 is null and (_col12 <= '2016-02-05'))) THEN ('RET') WHEN (((_col18 = _col8) and (_col19 <> _col9))) THEN ('A_INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -306,28 +306,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col7 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col7 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -339,36 +339,36 @@ STAGE PLANS: TableScan alias: ttest1 filterExpr: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), '2015-11-20' (type: string), sts (type: string), at1 (type: bigint), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col0, _col1, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: string), _col6 (type: string), _col7 (type: bigint), _col9 (type: string) TableScan alias: ttest2 filterExpr: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts1 (type: string), khash (type: string), rhash (type: string) outputColumnNames: _col1, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col9 (type: string) Reduce Operator Tree: Join Operator @@ -378,14 +378,14 @@ STAGE PLANS: 0 _col8 (type: string) 1 _col8 (type: string) outputColumnNames: _col0, _col1, _col6, _col7, _col8, _col9, _col11, _col18, _col19 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col8,-1) <> NVL(_col18,-1)) or (NVL(_col9,-1) <> NVL(_col19,-1))) and (CASE WHEN ((_col18 is not null and _col8 is null and (_col11 <= _col1))) THEN ('DEL') WHEN (((_col18 is null and _col8 is not null) or ((_col18 = _col8) and (_col19 <> _col9)))) THEN ('INS') ELSE ('NA') END <> 'RET') and _col8 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col6 (type: string), _col7 (type: bigint), '2099-12-31' (type: string), _col8 (type: string), _col9 (type: string), CASE WHEN ((_col18 is not null and _col8 is null and (_col11 <= _col1))) THEN ('DEL') WHEN (((_col18 is null and _col8 is not null) or ((_col18 = _col8) and (_col19 <> _col9)))) THEN ('INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -588,39 +588,39 @@ STAGE PLANS: TableScan alias: ttest1 filterExpr: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: ttest2 filterExpr: ('2015-11-20' BETWEEN dt1 AND dt2 and khash is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ('2015-11-20' BETWEEN dt1 AND dt2 and khash is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), dt1 (type: string), dt2 (type: string), sts (type: string), at1 (type: bigint), khash (type: string), rhash (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: string) sort order: + Map-reduce partition columns: _col5 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint), _col6 (type: string) Reduce Operator Tree: Join Operator @@ -630,14 +630,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col0,-1) <> NVL(_col7,-1)) or (NVL(_col1,-1) <> NVL(_col8,-1))) and CASE WHEN ((_col0 is null and (_col3 >= '2016-02-05'))) THEN (true) WHEN ((_col0 is null and (_col3 <= '2016-02-05'))) THEN (false) WHEN (((_col7 = _col0) and (_col8 <> _col1))) THEN (true) ELSE (true) END) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: bigint), _col5 (type: string), _col6 (type: bigint), _col4 (type: string), _col7 (type: string), _col8 (type: string), CASE WHEN ((_col0 is null and (_col3 >= '2016-02-05'))) THEN ('DEL') WHEN ((_col0 is null and (_col3 <= '2016-02-05'))) THEN ('RET') WHEN (((_col7 = _col0) and (_col8 <> _col1))) THEN ('A_INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -650,28 +650,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col6 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col6 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -683,39 +683,39 @@ STAGE PLANS: TableScan alias: ttest1 filterExpr: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), sts (type: string), at1 (type: bigint), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), _col4 (type: string) TableScan alias: ttest2 filterExpr: ('2015-11-20' BETWEEN dt1 AND dt2 and khash is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ('2015-11-20' BETWEEN dt1 AND dt2 and khash is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: khash (type: string), rhash (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -725,14 +725,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 422 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((NVL(_col3,-1) <> NVL(_col5,-1)) or (NVL(_col4,-1) <> NVL(_col6,-1))) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 422 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), '2099-12-31' (type: string), _col3 (type: string), _col4 (type: string), CASE WHEN ((_col5 is null or ((_col5 = _col3) and (_col6 <> _col4)))) THEN ('INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 422 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -935,36 +935,36 @@ STAGE PLANS: TableScan alias: ttest1 filterExpr: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE value expressions: _col9 (type: string) TableScan alias: ttest2 filterExpr: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), dt1 (type: string), dt2 (type: string), sts (type: string), at1 (type: bigint), khash (type: string), rhash (type: string) outputColumnNames: _col0, _col2, _col3, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: bigint), _col9 (type: string) Reduce Operator Tree: Join Operator @@ -974,14 +974,14 @@ STAGE PLANS: 0 _col8 (type: string) 1 _col8 (type: string) outputColumnNames: _col8, _col9, _col10, _col12, _col13, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col8,-1) <> NVL(_col18,-1)) or (NVL(_col9,-1) <> NVL(_col19,-1))) and _col18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: bigint), _col16 (type: string), _col17 (type: bigint), _col13 (type: string), _col18 (type: string), _col19 (type: string), CASE WHEN ((_col18 is not null and _col8 is null and (_col12 >= '2016-02-05'))) THEN ('DEL') WHEN ((_col18 is not null and _col8 is null and (_col12 <= '2016-02-05'))) THEN ('RET') WHEN (((_col18 = _col8) and (_col19 <> _col9))) THEN ('A_INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -994,42 +994,42 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col7 <> 'RET') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col7 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col7 <> 'RET') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col7 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1041,36 +1041,36 @@ STAGE PLANS: TableScan alias: ttest1 filterExpr: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), '2015-11-20' (type: string), sts (type: string), at1 (type: bigint), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col0, _col1, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: string), _col6 (type: string), _col7 (type: bigint), _col9 (type: string) TableScan alias: ttest2 filterExpr: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts1 (type: string), khash (type: string), rhash (type: string) outputColumnNames: _col1, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col9 (type: string) Reduce Operator Tree: Join Operator @@ -1080,14 +1080,14 @@ STAGE PLANS: 0 _col8 (type: string) 1 _col8 (type: string) outputColumnNames: _col0, _col1, _col6, _col7, _col8, _col9, _col11, _col18, _col19 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col8,-1) <> NVL(_col18,-1)) or (NVL(_col9,-1) <> NVL(_col19,-1))) and _col8 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col6 (type: string), _col7 (type: bigint), '2099-12-31' (type: string), _col8 (type: string), _col9 (type: string), CASE WHEN ((_col18 is not null and _col8 is null and (_col11 <= _col1))) THEN ('DEL') WHEN (((_col18 is null and _col8 is not null) or ((_col18 = _col8) and (_col19 <> _col9)))) THEN ('INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1289,35 +1289,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ttest1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE value expressions: _col9 (type: string) TableScan alias: ttest2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), dt1 (type: string), dt2 (type: string), sts (type: string), at1 (type: bigint), khash (type: string), rhash (type: string) outputColumnNames: _col0, _col2, _col3, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: bigint), _col9 (type: string) Reduce Operator Tree: Join Operator @@ -1327,14 +1327,14 @@ STAGE PLANS: 0 _col8 (type: string) 1 _col8 (type: string) outputColumnNames: _col8, _col9, _col10, _col12, _col13, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col8,-1) <> NVL(_col18,-1)) or (NVL(_col9,-1) <> NVL(_col19,-1))) and _col18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: bigint), _col16 (type: string), _col17 (type: bigint), _col13 (type: string), _col18 (type: string), _col19 (type: string), CASE WHEN ((_col18 is not null and _col8 is null and (_col12 >= '2016-02-05'))) THEN ('DEL') WHEN ((_col18 is not null and _col8 is null and (_col12 <= '2016-02-05'))) THEN ('RET') WHEN (((_col18 = _col8) and (_col19 <> _col9))) THEN ('A_INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1347,42 +1347,42 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col7 <> 'RET') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col7 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col7 <> 'RET') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col7 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1393,35 +1393,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ttest1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), '2015-11-20' (type: string), sts (type: string), at1 (type: bigint), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col0, _col1, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 294 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: string), _col6 (type: string), _col7 (type: bigint), _col9 (type: string) TableScan alias: ttest2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: '2015-11-20' BETWEEN dt1 AND dt2 (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts1 (type: string), khash (type: string), rhash (type: string) outputColumnNames: _col1, _col8, _col9 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col8 (type: string) sort order: + Map-reduce partition columns: _col8 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 920 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col9 (type: string) Reduce Operator Tree: Join Operator @@ -1431,14 +1431,14 @@ STAGE PLANS: 0 _col8 (type: string) 1 _col8 (type: string) outputColumnNames: _col0, _col1, _col6, _col7, _col8, _col9, _col11, _col18, _col19 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col8,-1) <> NVL(_col18,-1)) or (NVL(_col9,-1) <> NVL(_col19,-1))) and _col8 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col6 (type: string), _col7 (type: bigint), '2099-12-31' (type: string), _col8 (type: string), _col9 (type: string), CASE WHEN ((_col18 is not null and _col8 is null and (_col11 <= _col1))) THEN ('DEL') WHEN (((_col18 is null and _col8 is not null) or ((_col18 = _col8) and (_col19 <> _col9)))) THEN ('INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 323 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1640,38 +1640,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ttest1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: ttest2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ('2015-11-20' BETWEEN dt1 AND dt2 and khash is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), dt1 (type: string), dt2 (type: string), sts (type: string), at1 (type: bigint), khash (type: string), rhash (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: string) sort order: + Map-reduce partition columns: _col5 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint), _col6 (type: string) Reduce Operator Tree: Join Operator @@ -1681,14 +1681,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((NVL(_col0,-1) <> NVL(_col7,-1)) or (NVL(_col1,-1) <> NVL(_col8,-1))) and CASE WHEN ((_col0 is null and (_col3 >= '2016-02-05'))) THEN (true) WHEN ((_col0 is null and (_col3 <= '2016-02-05'))) THEN (false) WHEN (((_col7 = _col0) and (_col8 <> _col1))) THEN (true) ELSE (true) END) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: bigint), _col5 (type: string), _col6 (type: bigint), _col4 (type: string), _col7 (type: string), _col8 (type: string), CASE WHEN ((_col0 is null and (_col3 >= '2016-02-05'))) THEN ('DEL') WHEN ((_col0 is null and (_col3 <= '2016-02-05'))) THEN ('RET') WHEN (((_col7 = _col0) and (_col8 <> _col1))) THEN ('A_INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 220 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1701,28 +1701,28 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col6 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan Union - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col6 = 'A_INS')) THEN ('2015-11-21') ELSE ('2015-11-20') END (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 2 Data size: 642 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1733,38 +1733,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ttest1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (ts1 = '2015-11-20') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: id1 (type: bigint), sts (type: string), at1 (type: bigint), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( id1 AS STRING))) (type: string), reflect('org.apache.commons.codec.digest.DigestUtils','sha256Hex',concat(CAST( at1 AS STRING))) (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col3 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col3 (type: string) sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 384 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), _col4 (type: string) TableScan alias: ttest2 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ('2015-11-20' BETWEEN dt1 AND dt2 and khash is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: khash (type: string), rhash (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator @@ -1774,14 +1774,14 @@ STAGE PLANS: 0 _col3 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 422 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((NVL(_col3,-1) <> NVL(_col5,-1)) or (NVL(_col4,-1) <> NVL(_col6,-1))) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 422 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: bigint), '2099-12-31' (type: string), _col3 (type: string), _col4 (type: string), CASE WHEN ((_col5 is null or ((_col5 = _col3) and (_col6 <> _col4)))) THEN ('INS') ELSE ('NA') END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 422 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union_paren.q.out b/ql/src/test/results/clientpositive/union_paren.q.out index 36b70eb177..079c8c0b25 100644 --- a/ql/src/test/results/clientpositive/union_paren.q.out +++ b/ql/src/test/results/clientpositive/union_paren.q.out @@ -12,32 +12,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_pos_alias.q.out b/ql/src/test/results/clientpositive/union_pos_alias.q.out index 31a1ceafe6..41d71171d1 100644 --- a/ql/src/test/results/clientpositive/union_pos_alias.q.out +++ b/ql/src/test/results/clientpositive/union_pos_alias.q.out @@ -224,38 +224,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src_10 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5520 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string) sort order: +- - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5520 Basic stats: COMPLETE Column stats: NONE TableScan alias: s3 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'test' (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5520 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string), _col0 (type: string) sort order: +- - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5520 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5520 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 5520 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -383,19 +383,19 @@ STAGE PLANS: TableScan alias: masking_test_n9 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -403,19 +403,19 @@ STAGE PLANS: TableScan alias: masking_test_n9 filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10)) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -466,25 +466,25 @@ STAGE PLANS: TableScan alias: masking_test_n9 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -493,7 +493,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 137 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22372 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -506,33 +506,33 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 26 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(_col2), count(_col2) keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 26 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint), _col3 (type: bigint) TableScan Union - Statistics: Num rows: 26 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(_col2), count(_col2) keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 26 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -540,24 +540,24 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 13 Data size: 137 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22372 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col3 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: bigint), _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: NONE UDTF Operator - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: NONE function name: UDTFReplicateRows Select Operator expressions: col1 (type: int), col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -569,25 +569,25 @@ STAGE PLANS: TableScan alias: masking_test_n9 filterExpr: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((key % 2) = 0) and (key < 10) and (key > 0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), reverse(value) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 44744 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -596,7 +596,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 137 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 22372 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union_ppr.q.out b/ql/src/test/results/clientpositive/union_ppr.q.out index 2d24bc9e09..4d0f81e42f 100644 --- a/ql/src/test/results/clientpositive/union_ppr.q.out +++ b/ql/src/test/results/clientpositive/union_ppr.q.out @@ -27,53 +27,53 @@ STAGE PLANS: TableScan alias: x filterExpr: ((key < 100) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key < 100) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false TableScan alias: y filterExpr: ((key < 100) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false predicate: (key < 100) (type: boolean) - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: false Path -> Alias: @@ -185,13 +185,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 7074 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_1.q.out b/ql/src/test/results/clientpositive/union_remove_1.q.out index 6eae9dd009..f7163c0462 100644 --- a/ql/src/test/results/clientpositive/union_remove_1.q.out +++ b/ql/src/test/results/clientpositive/union_remove_1.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,10 +75,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -100,22 +100,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -124,10 +124,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_10.q.out b/ql/src/test/results/clientpositive/union_remove_10.q.out index 8efe7c52d5..a1c19c4897 100644 --- a/ql/src/test/results/clientpositive/union_remove_10.q.out +++ b/ql/src/test/results/clientpositive/union_remove_10.q.out @@ -65,14 +65,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n7 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -124,22 +124,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n7 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -148,10 +148,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -163,14 +163,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n7 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_11.q.out b/ql/src/test/results/clientpositive/union_remove_11.q.out index 37f6fb5103..5ae9961f01 100644 --- a/ql/src/test/results/clientpositive/union_remove_11.q.out +++ b/ql/src/test/results/clientpositive/union_remove_11.q.out @@ -63,20 +63,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n14 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -84,20 +84,20 @@ STAGE PLANS: name: default.outputtbl1_n21 TableScan alias: inputtbl1_n14 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -105,20 +105,20 @@ STAGE PLANS: name: default.outputtbl1_n21 TableScan alias: inputtbl1_n14 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_12.q.out b/ql/src/test/results/clientpositive/union_remove_12.q.out index d5120b1ddf..8170bbe921 100644 --- a/ql/src/test/results/clientpositive/union_remove_12.q.out +++ b/ql/src/test/results/clientpositive/union_remove_12.q.out @@ -59,14 +59,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n21 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -124,14 +124,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -143,14 +143,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -158,14 +158,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col2) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_13.q.out b/ql/src/test/results/clientpositive/union_remove_13.q.out index 4f2469fb2a..e529281bc7 100644 --- a/ql/src/test/results/clientpositive/union_remove_13.q.out +++ b/ql/src/test/results/clientpositive/union_remove_13.q.out @@ -59,22 +59,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -83,10 +83,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -143,14 +143,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -162,14 +162,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -177,14 +177,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col2) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_14.q.out b/ql/src/test/results/clientpositive/union_remove_14.q.out index c1e019e912..c2823c0316 100644 --- a/ql/src/test/results/clientpositive/union_remove_14.q.out +++ b/ql/src/test/results/clientpositive/union_remove_14.q.out @@ -59,14 +59,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n11 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -124,14 +124,14 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -143,14 +143,14 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -158,14 +158,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col2) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_15.q.out b/ql/src/test/results/clientpositive/union_remove_15.q.out index 1517534d8e..b142312fbb 100644 --- a/ql/src/test/results/clientpositive/union_remove_15.q.out +++ b/ql/src/test/results/clientpositive/union_remove_15.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n18 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -106,22 +106,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n18 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -130,14 +130,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), '2' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_16.q.out b/ql/src/test/results/clientpositive/union_remove_16.q.out index 0d25a7859a..f01d648d42 100644 --- a/ql/src/test/results/clientpositive/union_remove_16.q.out +++ b/ql/src/test/results/clientpositive/union_remove_16.q.out @@ -56,22 +56,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n23 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -80,14 +80,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -140,22 +140,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n23 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -164,14 +164,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), '2' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_17.q.out b/ql/src/test/results/clientpositive/union_remove_17.q.out index 38dfd74d64..02249b791c 100644 --- a/ql/src/test/results/clientpositive/union_remove_17.q.out +++ b/ql/src/test/results/clientpositive/union_remove_17.q.out @@ -50,20 +50,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -71,20 +71,20 @@ STAGE PLANS: name: default.outputtbl1_n4 TableScan alias: inputtbl1_n3 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int), '2' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_18.q.out b/ql/src/test/results/clientpositive/union_remove_18.q.out index 62d6787b6b..c3a29d1deb 100644 --- a/ql/src/test/results/clientpositive/union_remove_18.q.out +++ b/ql/src/test/results/clientpositive/union_remove_18.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n22 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), ds (type: string) outputColumnNames: key, ds - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: bigint), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -106,22 +106,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n22 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), ds (type: string) outputColumnNames: key, ds - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string), ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -130,14 +130,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: bigint), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_19.q.out b/ql/src/test/results/clientpositive/union_remove_19.q.out index 4e48312ee7..ba1b53dddd 100644 --- a/ql/src/test/results/clientpositive/union_remove_19.q.out +++ b/ql/src/test/results/clientpositive/union_remove_19.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,10 +75,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -100,22 +100,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -124,10 +124,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -236,21 +236,21 @@ STAGE PLANS: TableScan alias: inputtbl1_n1 filterExpr: (UDFToDouble(key) = 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -259,10 +259,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -285,21 +285,21 @@ STAGE PLANS: TableScan alias: inputtbl1_n1 filterExpr: (UDFToDouble(key) = 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -308,10 +308,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -386,21 +386,21 @@ STAGE PLANS: TableScan alias: inputtbl1_n1 filterExpr: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -409,14 +409,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( (UDFToDouble(_col0) + UDFToDouble(_col0)) AS STRING) (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -439,21 +439,21 @@ STAGE PLANS: TableScan alias: inputtbl1_n1 filterExpr: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -462,14 +462,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CAST( (UDFToDouble(_col0) + UDFToDouble(_col0)) AS STRING) (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_2.q.out b/ql/src/test/results/clientpositive/union_remove_2.q.out index 761005963a..71482637ea 100644 --- a/ql/src/test/results/clientpositive/union_remove_2.q.out +++ b/ql/src/test/results/clientpositive/union_remove_2.q.out @@ -56,22 +56,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n8 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -80,10 +80,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -105,14 +105,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n8 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -125,14 +125,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n8 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_20.q.out b/ql/src/test/results/clientpositive/union_remove_20.q.out index e4b7729da0..f51872c75d 100644 --- a/ql/src/test/results/clientpositive/union_remove_20.q.out +++ b/ql/src/test/results/clientpositive/union_remove_20.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n19 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,22 +104,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n19 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -128,14 +128,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_21.q.out b/ql/src/test/results/clientpositive/union_remove_21.q.out index 4bf7c6a9d7..37d1789701 100644 --- a/ql/src/test/results/clientpositive/union_remove_21.q.out +++ b/ql/src/test/results/clientpositive/union_remove_21.q.out @@ -51,31 +51,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n12 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -97,31 +97,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n12 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_22.q.out b/ql/src/test/results/clientpositive/union_remove_22.q.out index 89b3f71275..ed2b9c89e3 100644 --- a/ql/src/test/results/clientpositive/union_remove_22.q.out +++ b/ql/src/test/results/clientpositive/union_remove_22.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n5 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,22 +104,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n5 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -128,14 +128,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -245,22 +245,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n5 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -269,14 +269,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(concat(CAST( _col1 AS STRING), _col1)) (type: bigint), UDFToLong(concat(CAST( _col1 AS STRING), _col1)) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -298,22 +298,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n5 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -322,14 +322,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(concat(CAST( _col1 AS STRING), _col1)) (type: bigint), UDFToLong(concat(CAST( _col1 AS STRING), _col1)) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_23.q.out b/ql/src/test/results/clientpositive/union_remove_23.q.out index a4d941cac4..74022ea33d 100644 --- a/ql/src/test/results/clientpositive/union_remove_23.q.out +++ b/ql/src/test/results/clientpositive/union_remove_23.q.out @@ -55,35 +55,35 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: @@ -92,13 +92,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -114,7 +114,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -123,10 +123,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -148,22 +148,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n25 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -172,10 +172,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_24.q.out b/ql/src/test/results/clientpositive/union_remove_24.q.out index bac7d48b6f..9dbd836460 100644 --- a/ql/src/test/results/clientpositive/union_remove_24.q.out +++ b/ql/src/test/results/clientpositive/union_remove_24.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n20 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,14 +75,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(_col0) (type: double), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -104,22 +104,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n20 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -128,14 +128,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToDouble(UDFToLong(_col0)) (type: double), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_25.q.out b/ql/src/test/results/clientpositive/union_remove_25.q.out index 57daa4177e..4ef37fcefc 100644 --- a/ql/src/test/results/clientpositive/union_remove_25.q.out +++ b/ql/src/test/results/clientpositive/union_remove_25.q.out @@ -67,22 +67,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n13 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -91,10 +91,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -118,22 +118,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n13 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -142,10 +142,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -258,17 +258,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 500 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -276,17 +276,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 500 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -311,17 +311,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 500 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized @@ -329,17 +329,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 500 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -441,17 +441,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1000 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Execution mode: vectorized @@ -459,17 +459,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1000 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 373000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 373000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -495,17 +495,17 @@ STAGE PLANS: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1000 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Execution mode: vectorized @@ -513,17 +513,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1000 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint), '2008-04-08' (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 373000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 373000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_3.q.out b/ql/src/test/results/clientpositive/union_remove_3.q.out index 67b534efa7..37a7503dd1 100644 --- a/ql/src/test/results/clientpositive/union_remove_3.q.out +++ b/ql/src/test/results/clientpositive/union_remove_3.q.out @@ -54,20 +54,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n16 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -75,20 +75,20 @@ STAGE PLANS: name: default.outputtbl1_n23 TableScan alias: inputtbl1_n16 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -96,20 +96,20 @@ STAGE PLANS: name: default.outputtbl1_n23 TableScan alias: inputtbl1_n16 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_4.q.out b/ql/src/test/results/clientpositive/union_remove_4.q.out index 49272aabaa..d915573f0f 100644 --- a/ql/src/test/results/clientpositive/union_remove_4.q.out +++ b/ql/src/test/results/clientpositive/union_remove_4.q.out @@ -56,22 +56,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n24 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -80,10 +80,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -144,22 +144,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n24 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -168,10 +168,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_5.q.out b/ql/src/test/results/clientpositive/union_remove_5.q.out index 5fb29a8a4e..6f862344a0 100644 --- a/ql/src/test/results/clientpositive/union_remove_5.q.out +++ b/ql/src/test/results/clientpositive/union_remove_5.q.out @@ -61,22 +61,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n4 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -85,10 +85,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -149,14 +149,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n4 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -169,14 +169,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n4 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_6.q.out b/ql/src/test/results/clientpositive/union_remove_6.q.out index 08a68b77ad..a90a3713cc 100644 --- a/ql/src/test/results/clientpositive/union_remove_6.q.out +++ b/ql/src/test/results/clientpositive/union_remove_6.q.out @@ -61,22 +61,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n10 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -85,7 +85,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -98,10 +98,10 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -109,7 +109,7 @@ STAGE PLANS: name: default.outputtbl1_n14 File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -117,10 +117,10 @@ STAGE PLANS: name: default.outputtbl2_n4 TableScan Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -128,7 +128,7 @@ STAGE PLANS: name: default.outputtbl1_n14 File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -160,22 +160,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n10 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -184,7 +184,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union_remove_6_subq.q.out b/ql/src/test/results/clientpositive/union_remove_6_subq.q.out index daf05f225a..d0a373844e 100644 --- a/ql/src/test/results/clientpositive/union_remove_6_subq.q.out +++ b/ql/src/test/results/clientpositive/union_remove_6_subq.q.out @@ -65,22 +65,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -89,7 +89,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -102,10 +102,10 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -113,7 +113,7 @@ STAGE PLANS: name: default.outputtbl1_n0 File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -121,10 +121,10 @@ STAGE PLANS: name: default.outputtbl2 TableScan Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -132,7 +132,7 @@ STAGE PLANS: name: default.outputtbl1_n0 File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -164,22 +164,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n0 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -188,7 +188,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -445,22 +445,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -469,11 +469,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), (_col1 * 2L) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -486,36 +486,36 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -535,14 +535,14 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDouble window frame: ROWS PRECEDING(MAX)~CURRENT - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), avg_window_0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -553,22 +553,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -577,7 +577,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/union_remove_7.q.out b/ql/src/test/results/clientpositive/union_remove_7.q.out index 3ef0787acb..85078787ba 100644 --- a/ql/src/test/results/clientpositive/union_remove_7.q.out +++ b/ql/src/test/results/clientpositive/union_remove_7.q.out @@ -51,22 +51,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n17 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -75,10 +75,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -100,22 +100,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n17 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -124,10 +124,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_8.q.out b/ql/src/test/results/clientpositive/union_remove_8.q.out index b6c474f9f5..d21f128c09 100644 --- a/ql/src/test/results/clientpositive/union_remove_8.q.out +++ b/ql/src/test/results/clientpositive/union_remove_8.q.out @@ -56,22 +56,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n9 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -80,10 +80,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -105,14 +105,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n9 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -125,14 +125,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n9 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2L (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_remove_9.q.out b/ql/src/test/results/clientpositive/union_remove_9.q.out index 5ab05209cd..902e689332 100644 --- a/ql/src/test/results/clientpositive/union_remove_9.q.out +++ b/ql/src/test/results/clientpositive/union_remove_9.q.out @@ -64,22 +64,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n15 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -88,10 +88,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -142,20 +142,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1_n15 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat @@ -163,20 +163,20 @@ STAGE PLANS: name: default.outputtbl1_n22 TableScan alias: inputtbl1_n15 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), 2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToLong(_col1) (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/union_view.q.out b/ql/src/test/results/clientpositive/union_view.q.out index 8d844b8682..5e1a5c900b 100644 --- a/ql/src/test/results/clientpositive/union_view.q.out +++ b/ql/src/test/results/clientpositive/union_view.q.out @@ -33,17 +33,17 @@ STAGE PLANS: TableScan alias: src_union_1_n0 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), value (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -67,17 +67,17 @@ STAGE PLANS: TableScan alias: src_union_2_n0 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), value (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -101,17 +101,17 @@ STAGE PLANS: TableScan alias: src_union_3_n0 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), value (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -175,23 +175,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '1')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 550 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -201,23 +201,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '1')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '1') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 550 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -227,23 +227,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '1')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '1') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 550 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -268,23 +268,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '2')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -294,23 +294,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '2')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -320,23 +320,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '2')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '2') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -361,23 +361,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '3')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '3') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -387,23 +387,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '3')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '3') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -413,23 +413,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '3')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 5 Data size: 1365 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -454,23 +454,23 @@ STAGE PLANS: filterExpr: ((key = 86) and ds is not null) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 550 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -480,23 +480,23 @@ STAGE PLANS: filterExpr: ((key = 86) and ds is not null) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 279000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 837 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -506,23 +506,23 @@ STAGE PLANS: filterExpr: ((key = 86) and ds is not null) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 279000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 837 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -557,79 +557,79 @@ STAGE PLANS: filterExpr: (ds = '1') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_2_n0 filterExpr: (ds = '1') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_3_n0 filterExpr: (ds = '1') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -654,79 +654,79 @@ STAGE PLANS: filterExpr: (ds = '2') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '2') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_2_n0 filterExpr: (ds = '2') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_3_n0 filterExpr: (ds = '2') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '2') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -751,79 +751,79 @@ STAGE PLANS: filterExpr: (ds = '3') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '3') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_2_n0 filterExpr: (ds = '3') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '3') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_3_n0 filterExpr: (ds = '3') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1002 Data size: 10624 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1002 Data size: 8016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -851,23 +851,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '4')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '4') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 550 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -877,23 +877,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '4')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: ((ds = '4') and (key = 86)) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: PARTIAL Union - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 550 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -903,23 +903,23 @@ STAGE PLANS: filterExpr: ((key = 86) and (ds = '4')) (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = 86) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 550 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: 86 (type: int), _col0 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 252 Data size: 2656 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4 Data size: 1092 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -945,79 +945,79 @@ STAGE PLANS: filterExpr: (ds = '4') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '4') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_2_n0 filterExpr: (ds = '4') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ds = '4') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) TableScan alias: src_union_3_n0 filterExpr: (ds = '4') (type: boolean) properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 502 Data size: 5312 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 502 Data size: 4016 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out b/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out index b107eb7674..c7696d5e09 100644 --- a/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out +++ b/ql/src/test/results/clientpositive/unionall_unbalancedppd.q.out @@ -81,17 +81,17 @@ STAGE PLANS: TableScan alias: union_all_bug_test_1 filterExpr: (if(true, f1, f2) = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (if(true, f1, f2) = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: f1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -359,21 +359,21 @@ STAGE PLANS: TableScan alias: union_all_bug_test_1 filterExpr: (f1 = 1) (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (f1 = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -381,21 +381,21 @@ STAGE PLANS: TableScan alias: union_all_bug_test_2 filterExpr: (f1 = 1) (type: boolean) - Statistics: Num rows: 2 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (f1 = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 1 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/updateBasicStats.q.out b/ql/src/test/results/clientpositive/updateBasicStats.q.out index 8016b500fb..e3feef30a9 100644 --- a/ql/src/test/results/clientpositive/updateBasicStats.q.out +++ b/ql/src/test/results/clientpositive/updateBasicStats.q.out @@ -24,11 +24,11 @@ STAGE PLANS: Processor Tree: TableScan alias: s_n5 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: alter table s_n5 update statistics set('numRows'='12') @@ -53,11 +53,11 @@ STAGE PLANS: Processor Tree: TableScan alias: s_n5 - Statistics: Num rows: 12 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: analyze table s_n5 compute statistics @@ -82,11 +82,11 @@ STAGE PLANS: Processor Tree: TableScan alias: s_n5 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: alter table s_n5 update statistics set('numRows'='1212', 'rawDataSize'='500500') @@ -111,11 +111,11 @@ STAGE PLANS: Processor Tree: TableScan alias: s_n5 - Statistics: Num rows: 1212 Data size: 500500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1212 Data size: 424304 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1212 Data size: 500500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1212 Data size: 424304 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: CREATE TABLE calendarp_n0 (`year` int) partitioned by (p int) @@ -150,11 +150,11 @@ STAGE PLANS: TableScan alias: calendarp_n0 filterExpr: (p = 1) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: alter table calendarp_n0 partition (p=1) update statistics set('numRows'='1000020000', 'rawDataSize'='300040000') @@ -181,11 +181,11 @@ STAGE PLANS: TableScan alias: calendarp_n0 filterExpr: (p = 1) (type: boolean) - Statistics: Num rows: 1000020000 Data size: 300040000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020000 Data size: 4000080000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: year (type: int), 1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000020000 Data size: 300040000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020000 Data size: 8000160000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: create table src_stat_part_two_n0(key string, value string) partitioned by (px int, py string) @@ -247,11 +247,11 @@ STAGE PLANS: TableScan alias: src_stat_part_two_n0 filterExpr: ((px = 1) and (py = 'a')) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), 1 (type: int), 'a' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from src_stat_part_two_n0 where px=1 @@ -269,11 +269,11 @@ STAGE PLANS: TableScan alias: src_stat_part_two_n0 filterExpr: (px = 1) (type: boolean) - Statistics: Num rows: 11 Data size: 115 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 3982 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), 1 (type: int), py (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 11 Data size: 115 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 4026 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: alter table src_stat_part_two_n0 partition (px=1, py='a') update statistics set('numRows'='1000020000', 'rawDataSize'='300040000') @@ -300,11 +300,11 @@ STAGE PLANS: TableScan alias: src_stat_part_two_n0 filterExpr: ((px = 1) and (py = 'a')) (type: boolean) - Statistics: Num rows: 1000020000 Data size: 300040000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020000 Data size: 178003560000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), 1 (type: int), 'a' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000020000 Data size: 300040000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020000 Data size: 267005340000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from src_stat_part_two_n0 where px=1 @@ -322,11 +322,11 @@ STAGE PLANS: TableScan alias: src_stat_part_two_n0 filterExpr: (px = 1) (type: boolean) - Statistics: Num rows: 1000020010 Data size: 300040104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020010 Data size: 362007243620 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), 1 (type: int), py (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000020010 Data size: 300040104 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020010 Data size: 366007323660 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: alter table src_stat_part_two_n0 partition (px=1) update statistics set('numRows'='1000020000', 'rawDataSize'='300040000') @@ -356,11 +356,11 @@ STAGE PLANS: TableScan alias: src_stat_part_two_n0 filterExpr: ((px = 1) and (py = 'a')) (type: boolean) - Statistics: Num rows: 1000020000 Data size: 300040000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020000 Data size: 178003560000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), 1 (type: int), 'a' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000020000 Data size: 300040000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000020000 Data size: 267005340000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from src_stat_part_two_n0 where px=1 @@ -378,10 +378,10 @@ STAGE PLANS: TableScan alias: src_stat_part_two_n0 filterExpr: (px = 1) (type: boolean) - Statistics: Num rows: 2000040000 Data size: 600080000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000040000 Data size: 724014480000 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), 1 (type: int), py (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000040000 Data size: 600080000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000040000 Data size: 732014640000 Basic stats: COMPLETE Column stats: PARTIAL ListSink diff --git a/ql/src/test/results/clientpositive/vector_aggregate_9.q.out b/ql/src/test/results/clientpositive/vector_aggregate_9.q.out index 198f688c17..b0737e7b45 100644 --- a/ql/src/test/results/clientpositive/vector_aggregate_9.q.out +++ b/ql/src/test/results/clientpositive/vector_aggregate_9.q.out @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n4 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 212912 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:tinyint, 1:si:smallint, 2:i:int, 3:b:bigint, 4:f:float, 5:d:double, 6:dc:decimal(38,18), 7:bo:boolean, 8:s:string, 9:s2:string, 10:ts:timestamp, 11:ts2:timestamp, 12:dt:date, 13:ROW__ID:struct] @@ -132,7 +132,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [6] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 212912 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(dc), max(dc), sum(dc), count(dc) Group By Vectorization: @@ -144,7 +144,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -152,7 +152,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -179,14 +179,14 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), sum(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), (_col2 / _col3) (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -227,7 +227,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n4 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:tinyint, 1:si:smallint, 2:i:int, 3:b:bigint, 4:f:float, 5:d:double, 6:dc:decimal(38,18), 7:bo:boolean, 8:s:string, 9:s2:string, 10:ts:timestamp, 11:ts2:timestamp, 12:dt:date, 13:ROW__ID:struct] @@ -238,7 +238,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [5] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(d), max(d), sum(d), count(d) Group By Vectorization: @@ -250,7 +250,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -258,7 +258,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -285,14 +285,14 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), sum(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -333,7 +333,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n4 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 76040 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:tinyint, 1:si:smallint, 2:i:int, 3:b:bigint, 4:f:float, 5:d:double, 6:dc:decimal(38,18), 7:bo:boolean, 8:s:string, 9:s2:string, 10:ts:timestamp, 11:ts2:timestamp, 12:dt:date, 13:ROW__ID:struct] @@ -344,7 +344,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [10] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 76040 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(ts), max(ts), sum(ts), count(ts) Group By Vectorization: @@ -356,7 +356,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -364,7 +364,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: timestamp), _col1 (type: timestamp), _col2 (type: double), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -391,14 +391,14 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), sum(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: timestamp), _col1 (type: timestamp), _col2 (type: double), (_col2 / _col3) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out b/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out index d2456807dd..75c75d697f 100644 --- a/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out +++ b/ql/src/test/results/clientpositive/vector_aggregate_without_gby.q.out @@ -54,7 +54,7 @@ STAGE PLANS: TableScan alias: testvec filterExpr: (id = 5) (type: boolean) - Statistics: Num rows: 7 Data size: 714 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 714 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:id:int, 1:dt:int, 2:greg_dt:string, 3:ROW__ID:struct] @@ -64,7 +64,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColEqualLongScalar(col 0:int, val 5) predicate: (id = 5) (type: boolean) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: dt (type: int), greg_dt (type: string) outputColumnNames: dt, greg_dt @@ -72,7 +72,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1, 2] - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(dt), max(greg_dt) Group By Vectorization: @@ -84,7 +84,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -92,7 +92,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: string) Execution mode: vectorized Map Vectorization: @@ -119,10 +119,10 @@ STAGE PLANS: aggregations: max(VALUE._col0), max(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_between_columns.q.out b/ql/src/test/results/clientpositive/vector_between_columns.q.out index f5e095b632..8c55977a49 100644 --- a/ql/src/test/results/clientpositive/vector_between_columns.q.out +++ b/ql/src/test/results/clientpositive/vector_between_columns.q.out @@ -110,11 +110,11 @@ STAGE PLANS: $hdt$_0:tint TableScan alias: tint - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rnum (type: int), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -125,7 +125,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tsint - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -135,7 +135,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -149,7 +149,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 36 Data size: 468 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3)) THEN ('Ok') ELSE ('NoOk') END (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4 @@ -158,13 +158,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 2, 1, 3, 5] selectExpressions: IfExprStringScalarStringScalar(col 4:boolean, val Ok, val NoOk)(children: VectorUDFAdaptor(_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3))(children: col 3:smallint, col 3:smallint) -> 4:boolean) -> 5:string - Statistics: Num rows: 36 Data size: 468 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 36 Data size: 468 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -264,11 +264,11 @@ STAGE PLANS: $hdt$_0:tint TableScan alias: tint - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rnum (type: int), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -279,7 +279,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tsint - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -289,7 +289,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 6 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -303,14 +303,14 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 36 Data size: 468 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE Filter Operator Filter Vectorization: className: VectorFilterOperator native: true predicateExpression: SelectColumnIsTrue(col 4:boolean)(children: VectorUDFAdaptor(_col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3))(children: col 3:smallint, col 3:smallint) -> 4:boolean) predicate: _col1 BETWEEN UDFToInteger(_col3) AND UDFToInteger(_col3) (type: boolean) - Statistics: Num rows: 4 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint) outputColumnNames: _col0, _col1, _col2, _col3 @@ -318,13 +318,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 2, 1, 3] - Statistics: Num rows: 4 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 52 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out b/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out index 7c550bacae..447a3b06a2 100644 --- a/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out +++ b/ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out @@ -127,14 +127,14 @@ STAGE PLANS: TableScan alias: t1 filterExpr: bin is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 34084 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: bin is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 34084 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 34084 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col10 (type: binary) @@ -146,7 +146,7 @@ STAGE PLANS: TableScan alias: t2 filterExpr: bin is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 34084 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -155,7 +155,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 10:binary) predicate: bin is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 34084 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 @@ -163,7 +163,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10] - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 34084 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -178,7 +178,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 110 Data size: 32601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10000 Data size: 6819968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11,_col12,_col13,_col14,_col15,_col16,_col17,_col18,_col19,_col20,_col21) (type: int) outputColumnNames: _col0 @@ -187,7 +187,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [22] selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11,_col12,_col13,_col14,_col15,_col16,_col17,_col18,_col19,_col20,_col21)) -> 22:int - Statistics: Num rows: 110 Data size: 32601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10000 Data size: 6819968 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) Group By Vectorization: @@ -199,7 +199,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -207,7 +207,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -230,7 +230,7 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -252,7 +252,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -271,10 +271,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -326,7 +326,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: hundredorc - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -336,7 +336,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [10] - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -350,7 +350,7 @@ STAGE PLANS: keys: bin (type: binary) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 3200 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: binary) sort order: + @@ -360,7 +360,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 3200 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -382,11 +382,11 @@ STAGE PLANS: keys: KEY._col0 (type: binary) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 14819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), _col0 (type: binary) outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 14819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -408,7 +408,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 50 Data size: 14819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -428,10 +428,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: binary) outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 14819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 14819 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -512,14 +512,14 @@ STAGE PLANS: TableScan alias: t1 filterExpr: i is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 6000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: i is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 6000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int), bin (type: binary) outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 6000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -531,7 +531,7 @@ STAGE PLANS: TableScan alias: t2 filterExpr: i is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 6000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -540,7 +540,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 2:int) predicate: i is not null (type: boolean) - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 6000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int), bin (type: binary) outputColumnNames: _col0, _col1 @@ -548,7 +548,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 10] - Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 6000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -563,7 +563,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 110 Data size: 32601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 14500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: binary), _col3 (type: binary) outputColumnNames: _col0, _col1, _col2 @@ -571,13 +571,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 110 Data size: 32601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 14500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 110 Data size: 32601 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 125 Data size: 14500 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_bround.q.out b/ql/src/test/results/clientpositive/vector_bround.q.out index 6dcc0f17ae..660f58a25c 100644 --- a/ql/src/test/results/clientpositive/vector_bround.q.out +++ b/ql/src/test/results/clientpositive/vector_bround.q.out @@ -64,7 +64,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_vector_bround - Statistics: Num rows: 9 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:v0:double, 1:v1:double, 2:ROW__ID:struct] @@ -76,13 +76,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4] selectExpressions: FuncBRoundDoubleToDouble(col 0:double) -> 3:double, BRoundWithNumDigitsDoubleToDouble(col 1, decimalPlaces 1) -> 4:double - Statistics: Num rows: 9 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_case_when_1.q.out b/ql/src/test/results/clientpositive/vector_case_when_1.q.out index 01fc3ce570..8a6143e0a1 100644 --- a/ql/src/test/results/clientpositive/vector_case_when_1.q.out +++ b/ql/src/test/results/clientpositive/vector_case_when_1.q.out @@ -197,14 +197,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lineitem_test - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_quantity (type: int), CASE WHEN ((l_quantity = 1)) THEN ('Single') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN ('Many') ELSE ('Huge number') END (type: string), CASE WHEN ((l_quantity = 1)) THEN ('Single') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN ('Many') ELSE (null) END (type: string), CASE WHEN ((l_quantity = 1)) THEN ('Single') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN (null) ELSE (null) END (type: string), if((l_shipmode = 'SHIP '), date_add(l_shipdate, 10), date_add(l_shipdate, 5)) (type: date), CASE WHEN ((l_returnflag = 'N')) THEN ((l_extendedprice * (1.0D - l_discount))) ELSE (0) END (type: double), CASE WHEN ((l_returnflag = 'N')) THEN ((l_extendedprice * (1.0D - l_discount))) ELSE (0.0D) END (type: double), if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), null, l_tax) (type: decimal(10,2)), if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, null) (type: decimal(10,2)), if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax) (type: decimal(12,2)), if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0) (type: decimal(12,2)), if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax) (type: decimal(10,2)), if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0) (type: decimal(10,2)), if((l_partkey > 30), CAST( l_receiptdate AS TIMESTAMP), CAST( l_commitdate AS TIMESTAMP)) (type: timestamp), if((l_suppkey > 10000), datediff(l_receiptdate, l_commitdate), null) (type: int), if((l_suppkey > 10000), null, datediff(l_receiptdate, l_commitdate)) (type: int), if(((l_suppkey % 500) > 100), DATE'2009-01-01', DATE'2009-12-31') (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -505,7 +505,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lineitem_test - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct] @@ -517,13 +517,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 22, 24, 25, 26, 27, 28, 30, 31, 32, 33, 34, 36, 40, 42, 45, 46] selectExpressions: IfExprStringScalarStringGroupColumn(col 17:boolean, val Singlecol 21:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, IfExprStringScalarStringGroupColumn(col 18:boolean, val Twocol 22:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 18:boolean, IfExprStringScalarStringGroupColumn(col 19:boolean, val Somecol 21:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 19:boolean, IfExprStringScalarStringScalar(col 20:boolean, val Many, val Huge number)(children: LongColLessLongScalar(col 4:int, val 100) -> 20:boolean) -> 21:string) -> 22:string) -> 21:string) -> 22:string, IfExprStringScalarStringGroupColumn(col 17:boolean, val Singlecol 23:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, IfExprStringScalarStringGroupColumn(col 18:boolean, val Twocol 24:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 18:boolean, IfExprStringScalarStringGroupColumn(col 19:boolean, val Somecol 23:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 19:boolean, IfExprColumnNull(col 20:boolean, col 21:string, null)(children: LongColLessLongScalar(col 4:int, val 100) -> 20:boolean, ConstantVectorExpression(val Many) -> 21:string) -> 23:string) -> 24:string) -> 23:string) -> 24:string, IfExprStringScalarStringGroupColumn(col 17:boolean, val Singlecol 23:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, IfExprStringScalarStringGroupColumn(col 18:boolean, val Twocol 25:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 18:boolean, IfExprStringScalarStringGroupColumn(col 19:boolean, val Somecol 23:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 19:boolean, IfExprNullNull(null, null) -> 23:string) -> 25:string) -> 23:string) -> 25:string, IfExprLongColumnLongColumn(col 17:boolean, col 18:date, col 19:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 17:boolean, VectorUDFDateAddColScalar(col 10:date, val 10) -> 18:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 19:date) -> 26:date, IfExprDoubleColumnLongScalar(col 17:boolean, col 28:double, val 0)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 17:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 27:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 27:double) -> 28:double) -> 27:double, IfExprDoubleColumnDoubleScalar(col 17:boolean, col 29:double, val 0.0)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 17:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 28:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 28:double) -> 29:double) -> 28:double, IfExprNullColumn(col 17:boolean, null, col 48)(children: StringGroupColEqualStringScalar(col 23:string, val DELIVER IN PERSON)(children: CastStringGroupToString(col 13:varchar(20)) -> 23:string) -> 17:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 48:decimal(10,2)) -> 30:decimal(10,2), IfExprColumnNull(col 18:boolean, col 49:decimal(10,2), null)(children: StringGroupColEqualStringScalar(col 23:string, val TAKE BACK RETURN)(children: CastStringGroupToString(col 13:varchar(20)) -> 23:string) -> 18:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 49:decimal(10,2)) -> 31:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 23:string, val DELIVER IN PERSON)(children: CastStringGroupToString(col 13:varchar(20)) -> 23:string) -> 19:boolean) -> 32:decimal(12,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 23:string, val TAKE BACK RETURN)(children: CastStringGroupToString(col 13:varchar(20)) -> 23:string) -> 19:boolean) -> 33:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 19:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(1,0)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 23:string, val DELIVER IN PERSON)(children: CastStringGroupToString(col 13:varchar(20)) -> 23:string) -> 19:boolean) -> 34:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 35:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 23:string, val TAKE BACK RETURN)(children: CastStringGroupToString(col 13:varchar(20)) -> 23:string) -> 35:boolean) -> 36:decimal(10,2)/DECIMAL_64, IfExprTimestampColumnColumn(col 37:boolean, col 38:timestampcol 39:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30) -> 37:boolean, CastDateToTimestamp(col 12:date) -> 38:timestamp, CastDateToTimestamp(col 11:date) -> 39:timestamp) -> 40:timestamp, IfExprColumnNull(col 37:boolean, col 41:int, null)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 37:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 41:int) -> 42:int, IfExprNullColumn(col 43:boolean, null, col 44)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 43:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 44:int) -> 45:int, IfExprLongScalarLongScalar(col 47:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 46:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 46:int) -> 47:boolean) -> 46:date - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -834,7 +834,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lineitem_test - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct] @@ -846,13 +846,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 27, 38, 48, 52, 54, 60, 63, 65, 67, 68, 69, 71, 75, 78, 81, 82] selectExpressions: IfExprColumnCondExpr(col 17:boolean, col 18:stringcol 26:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, ConstantVectorExpression(val Single) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 25:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 19:boolean, ConstantVectorExpression(val Two) -> 20:string, IfExprColumnCondExpr(col 21:boolean, col 22:stringcol 24:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 21:boolean, ConstantVectorExpression(val Some) -> 22:string, IfExprStringScalarStringScalar(col 23:boolean, val Many, val Huge number)(children: LongColLessLongScalar(col 4:int, val 100) -> 23:boolean) -> 24:string) -> 25:string) -> 26:string) -> 27:string, IfExprColumnCondExpr(col 23:boolean, col 28:stringcol 37:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 23:boolean, ConstantVectorExpression(val Single) -> 28:string, IfExprColumnCondExpr(col 29:boolean, col 30:stringcol 36:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 29:boolean, ConstantVectorExpression(val Two) -> 30:string, IfExprColumnCondExpr(col 31:boolean, col 32:stringcol 35:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 31:boolean, ConstantVectorExpression(val Some) -> 32:string, IfExprColumnNull(col 33:boolean, col 34:string, null)(children: LongColLessLongScalar(col 4:int, val 100) -> 33:boolean, ConstantVectorExpression(val Many) -> 34:string) -> 35:string) -> 36:string) -> 37:string) -> 38:string, IfExprColumnCondExpr(col 39:boolean, col 40:stringcol 47:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 39:boolean, ConstantVectorExpression(val Single) -> 40:string, IfExprColumnCondExpr(col 41:boolean, col 42:stringcol 46:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 41:boolean, ConstantVectorExpression(val Two) -> 42:string, IfExprColumnCondExpr(col 43:boolean, col 44:stringcol 45:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 43:boolean, ConstantVectorExpression(val Some) -> 44:string, IfExprNullNull(null, null) -> 45:string) -> 46:string) -> 47:string) -> 48:string, IfExprCondExprCondExpr(col 49:boolean, col 50:datecol 51:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 49:boolean, VectorUDFDateAddColScalar(col 10:date, val 10) -> 50:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 51:date) -> 52:date, IfExprDoubleColumnLongScalar(col 57:boolean, col 58:double, val 0)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 57:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 54:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 54:double) -> 58:double) -> 54:double, IfExprCondExprColumn(col 57:boolean, col 59:double, col 58:double)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 57:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 58:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 58:double) -> 59:double, ConstantVectorExpression(val 0.0) -> 58:double) -> 60:double, IfExprNullColumn(col 62:boolean, null, col 84)(children: StringGroupColEqualStringScalar(col 61:string, val DELIVER IN PERSON)(children: CastStringGroupToString(col 13:varchar(20)) -> 61:string) -> 62:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 84:decimal(10,2)) -> 63:decimal(10,2), IfExprColumnNull(col 64:boolean, col 85:decimal(10,2), null)(children: StringGroupColEqualStringScalar(col 61:string, val TAKE BACK RETURN)(children: CastStringGroupToString(col 13:varchar(20)) -> 61:string) -> 64:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 85:decimal(10,2)) -> 65:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 61:string, val DELIVER IN PERSON)(children: CastStringGroupToString(col 13:varchar(20)) -> 61:string) -> 66:boolean) -> 67:decimal(12,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 61:string, val TAKE BACK RETURN)(children: CastStringGroupToString(col 13:varchar(20)) -> 61:string) -> 66:boolean) -> 68:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 66:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(1,0)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 61:string, val DELIVER IN PERSON)(children: CastStringGroupToString(col 13:varchar(20)) -> 61:string) -> 66:boolean) -> 69:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 70:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 61:string, val TAKE BACK RETURN)(children: CastStringGroupToString(col 13:varchar(20)) -> 61:string) -> 70:boolean) -> 71:decimal(10,2)/DECIMAL_64, IfExprCondExprCondExpr(col 72:boolean, col 73:timestampcol 74:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30) -> 72:boolean, CastDateToTimestamp(col 12:date) -> 73:timestamp, CastDateToTimestamp(col 11:date) -> 74:timestamp) -> 75:timestamp, IfExprCondExprNull(col 76:boolean, col 77:int, null)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 76:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 77:int) -> 78:int, IfExprNullCondExpr(col 79:boolean, null, col 80:int)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 79:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 80:int) -> 81:int, IfExprLongScalarLongScalar(col 83:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 82:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 82:int) -> 83:boolean) -> 82:date - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 101 Data size: 78500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_case_when_2.q.out b/ql/src/test/results/clientpositive/vector_case_when_2.q.out index b1cb3f26e0..8bbf1b46b2 100644 --- a/ql/src/test/results/clientpositive/vector_case_when_2.q.out +++ b/ql/src/test/results/clientpositive/vector_case_when_2.q.out @@ -129,15 +129,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: timestamps - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), CASE WHEN ((ctimestamp2 <= TIMESTAMP'1800-12-31 00:00:00')) THEN ('1800s or Earlier') WHEN ((ctimestamp2 < TIMESTAMP'1900-01-01 00:00:00')) THEN ('1900s') WHEN (ctimestamp2 BETWEEN TIMESTAMP'2006-01-01 00:00:00' AND TIMESTAMP'2010-12-31 23:59:59.999999999') THEN ('Late 2000s') WHEN ((ctimestamp2 <= TIMESTAMP'2015-12-31 23:59:59.999999999')) THEN ('Early 2010s') ELSE ('Unknown') END (type: string), CASE WHEN ((ctimestamp2 <= TIMESTAMP'2000-12-31 23:59:59.999999999')) THEN ('Old') WHEN ((ctimestamp2 < TIMESTAMP'2006-01-01 00:00:00')) THEN ('Early 2000s') WHEN (ctimestamp2 BETWEEN TIMESTAMP'2006-01-01 00:00:00' AND TIMESTAMP'2010-12-31 23:59:59.999999999') THEN ('Late 2000s') WHEN ((ctimestamp2 <= TIMESTAMP'2015-12-31 23:59:59.999999999')) THEN ('Early 2010s') ELSE (null) END (type: string), CASE WHEN ((ctimestamp2 <= TIMESTAMP'2000-12-31 23:59:59.999999999')) THEN ('Old') WHEN ((ctimestamp2 < TIMESTAMP'2006-01-01 00:00:00')) THEN ('Early 2000s') WHEN (ctimestamp2 BETWEEN TIMESTAMP'2006-01-01 00:00:00' AND TIMESTAMP'2010-12-31 23:59:59.999999999') THEN ('Late 2000s') WHEN ((ctimestamp2 <= TIMESTAMP'2015-12-31 23:59:59.999999999')) THEN (null) ELSE (null) END (type: string), if((ctimestamp1 < TIMESTAMP'1974-10-04 17:21:03.989'), year(ctimestamp1), year(ctimestamp2)) (type: int), CASE WHEN ((stimestamp1 like '%19%')) THEN (stimestamp1) ELSE (TIMESTAMP'2018-03-08 23:04:59') END (type: string), if((ctimestamp1 = TIMESTAMP'2021-09-24 03:18:32.413655165'), null, minute(ctimestamp1)) (type: int), if(((ctimestamp2 >= TIMESTAMP'5344-10-04 18:40:08.165') and (ctimestamp2 < TIMESTAMP'6631-11-13 16:31:29.702202248')), minute(ctimestamp1), null) (type: int), if(((UDFToDouble(ctimestamp1) % 500.0D) > 100.0D), date_add(cdate, 1), date_add(cdate, 365)) (type: date), stimestamp1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col10 (type: string), _col1 (type: timestamp) sort order: +++ - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: date) Map Vectorization: enabled: true @@ -153,10 +153,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey2 (type: timestamp), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -365,7 +365,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: timestamps - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdate:date, 1:ctimestamp1:timestamp, 2:stimestamp1:string, 3:ctimestamp2:timestamp, 4:ROW__ID:struct] @@ -377,7 +377,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3, 10, 12, 13, 14, 11, 7, 16, 23, 2] selectExpressions: IfExprStringScalarStringGroupColumn(col 5:boolean, val 1800s or Earliercol 9:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 1800-12-31 00:00:00) -> 5:boolean, IfExprStringScalarStringGroupColumn(col 6:boolean, val 1900scol 10:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 1900-01-01 00:00:00) -> 6:boolean, IfExprStringScalarStringGroupColumn(col 7:boolean, val Late 2000scol 9:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 7:boolean, IfExprStringScalarStringScalar(col 8:boolean, val Early 2010s, val Unknown)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 8:boolean) -> 9:string) -> 10:string) -> 9:string) -> 10:string, IfExprStringScalarStringGroupColumn(col 5:boolean, val Oldcol 11:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2000-12-31 23:59:59.999999999) -> 5:boolean, IfExprStringScalarStringGroupColumn(col 6:boolean, val Early 2000scol 12:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 6:boolean, IfExprStringScalarStringGroupColumn(col 7:boolean, val Late 2000scol 11:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 7:boolean, IfExprColumnNull(col 8:boolean, col 9:string, null)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 8:boolean, ConstantVectorExpression(val Early 2010s) -> 9:string) -> 11:string) -> 12:string) -> 11:string) -> 12:string, IfExprStringScalarStringGroupColumn(col 5:boolean, val Oldcol 11:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2000-12-31 23:59:59.999999999) -> 5:boolean, IfExprStringScalarStringGroupColumn(col 6:boolean, val Early 2000scol 13:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 6:boolean, IfExprStringScalarStringGroupColumn(col 7:boolean, val Late 2000scol 11:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 7:boolean, IfExprNullNull(null, null) -> 11:string) -> 13:string) -> 11:string) -> 13:string, IfExprLongColumnLongColumn(col 5:boolean, col 6:int, col 7:int)(children: TimestampColLessTimestampScalar(col 1:timestamp, val 1974-10-04 17:21:03.989) -> 5:boolean, VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 6:int, VectorUDFYearTimestamp(col 3:timestamp, field YEAR) -> 7:int) -> 14:int, VectorUDFAdaptor(CASE WHEN ((stimestamp1 like '%19%')) THEN (stimestamp1) ELSE (TIMESTAMP'2018-03-08 23:04:59') END)(children: SelectStringColLikeStringScalar(col 2:string) -> 5:boolean) -> 11:string, IfExprNullColumn(col 5:boolean, null, col 6)(children: TimestampColEqualTimestampScalar(col 1:timestamp, val 2021-09-24 03:18:32.413655165) -> 5:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 6:int) -> 7:int, IfExprColumnNull(col 17:boolean, col 15:int, null)(children: ColAndCol(col 15:boolean, col 16:boolean)(children: TimestampColGreaterEqualTimestampScalar(col 3:timestamp, val 5344-10-04 18:40:08.165) -> 15:boolean, TimestampColLessTimestampScalar(col 3:timestamp, val 6631-11-13 16:31:29.702202248) -> 16:boolean) -> 17:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 15:int) -> 16:int, IfExprLongColumnLongColumn(col 20:boolean, col 21:date, col 22:date)(children: DoubleColGreaterDoubleScalar(col 19:double, val 100.0)(children: DoubleColModuloDoubleScalar(col 18:double, val 500.0)(children: CastTimestampToDouble(col 1:timestamp) -> 18:double) -> 19:double) -> 20:boolean, VectorUDFDateAddColScalar(col 0:date, val 1) -> 21:date, VectorUDFDateAddColScalar(col 0:date, val 365) -> 22:date) -> 23:date - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col10 (type: string), _col1 (type: timestamp) sort order: +++ @@ -386,7 +386,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: date) Execution mode: vectorized Map Vectorization: @@ -412,10 +412,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey2 (type: timestamp), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -624,7 +624,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: timestamps - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdate:date, 1:ctimestamp1:timestamp, 2:stimestamp1:string, 3:ctimestamp2:timestamp, 4:ROW__ID:struct] @@ -636,7 +636,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3, 15, 26, 36, 40, 42, 44, 46, 53, 2] selectExpressions: IfExprColumnCondExpr(col 5:boolean, col 6:stringcol 14:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 1800-12-31 00:00:00) -> 5:boolean, ConstantVectorExpression(val 1800s or Earlier) -> 6:string, IfExprColumnCondExpr(col 7:boolean, col 8:stringcol 13:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 1900-01-01 00:00:00) -> 7:boolean, ConstantVectorExpression(val 1900s) -> 8:string, IfExprColumnCondExpr(col 9:boolean, col 10:stringcol 12:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 9:boolean, ConstantVectorExpression(val Late 2000s) -> 10:string, IfExprStringScalarStringScalar(col 11:boolean, val Early 2010s, val Unknown)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 11:boolean) -> 12:string) -> 13:string) -> 14:string) -> 15:string, IfExprColumnCondExpr(col 11:boolean, col 16:stringcol 25:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2000-12-31 23:59:59.999999999) -> 11:boolean, ConstantVectorExpression(val Old) -> 16:string, IfExprColumnCondExpr(col 17:boolean, col 18:stringcol 24:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 17:boolean, ConstantVectorExpression(val Early 2000s) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 23:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 19:boolean, ConstantVectorExpression(val Late 2000s) -> 20:string, IfExprColumnNull(col 21:boolean, col 22:string, null)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 21:boolean, ConstantVectorExpression(val Early 2010s) -> 22:string) -> 23:string) -> 24:string) -> 25:string) -> 26:string, IfExprColumnCondExpr(col 27:boolean, col 28:stringcol 35:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2000-12-31 23:59:59.999999999) -> 27:boolean, ConstantVectorExpression(val Old) -> 28:string, IfExprColumnCondExpr(col 29:boolean, col 30:stringcol 34:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 29:boolean, ConstantVectorExpression(val Early 2000s) -> 30:string, IfExprColumnCondExpr(col 31:boolean, col 32:stringcol 33:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 31:boolean, ConstantVectorExpression(val Late 2000s) -> 32:string, IfExprNullNull(null, null) -> 33:string) -> 34:string) -> 35:string) -> 36:string, IfExprCondExprCondExpr(col 37:boolean, col 38:intcol 39:int)(children: TimestampColLessTimestampScalar(col 1:timestamp, val 1974-10-04 17:21:03.989) -> 37:boolean, VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 38:int, VectorUDFYearTimestamp(col 3:timestamp, field YEAR) -> 39:int) -> 40:int, VectorUDFAdaptor(CASE WHEN ((stimestamp1 like '%19%')) THEN (stimestamp1) ELSE (TIMESTAMP'2018-03-08 23:04:59') END)(children: SelectStringColLikeStringScalar(col 2:string) -> 41:boolean) -> 42:string, IfExprNullCondExpr(col 41:boolean, null, col 43:int)(children: TimestampColEqualTimestampScalar(col 1:timestamp, val 2021-09-24 03:18:32.413655165) -> 41:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 43:int) -> 44:int, IfExprCondExprNull(col 47:boolean, col 45:int, null)(children: ColAndCol(col 45:boolean, col 46:boolean)(children: TimestampColGreaterEqualTimestampScalar(col 3:timestamp, val 5344-10-04 18:40:08.165) -> 45:boolean, TimestampColLessTimestampScalar(col 3:timestamp, val 6631-11-13 16:31:29.702202248) -> 46:boolean) -> 47:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 45:int) -> 46:int, IfExprCondExprCondExpr(col 50:boolean, col 51:datecol 52:date)(children: DoubleColGreaterDoubleScalar(col 49:double, val 100.0)(children: DoubleColModuloDoubleScalar(col 48:double, val 500.0)(children: CastTimestampToDouble(col 1:timestamp) -> 48:double) -> 49:double) -> 50:boolean, VectorUDFDateAddColScalar(col 0:date, val 1) -> 51:date, VectorUDFDateAddColScalar(col 0:date, val 365) -> 52:date) -> 53:date - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp), _col10 (type: string), _col1 (type: timestamp) sort order: +++ @@ -645,7 +645,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: date) Execution mode: vectorized Map Vectorization: @@ -671,10 +671,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey2 (type: timestamp), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 51 Data size: 12300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/vector_cast_constant.q.out index 68a1aeae5e..95496025c0 100644 --- a/ql/src/test/results/clientpositive/vector_cast_constant.q.out +++ b/ql/src/test/results/clientpositive/vector_cast_constant.q.out @@ -124,7 +124,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1korc_n0 - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4196 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -134,7 +134,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2] - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4196 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(50), count(), sum(50.0D), count(50.0D), sum(50), count(50) Group By Vectorization: @@ -148,7 +148,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 257 Data size: 40092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -158,7 +158,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 257 Data size: 40092 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: double), _col4 (type: bigint), _col5 (type: decimal(12,0)), _col6 (type: bigint) Execution mode: vectorized @@ -181,11 +181,11 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 257 Data size: 40092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), (UDFToDouble(_col1) / _col2) (type: double), (_col3 / _col4) (type: double), CAST( (_col5 / _col6) AS decimal(6,4)) (type: decimal(6,4)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 257 Data size: 33924 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -207,7 +207,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 257 Data size: 33924 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(6,4)) Execution mode: vectorized @@ -228,13 +228,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(6,4)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 257 Data size: 33924 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_char_2.q.out b/ql/src/test/results/clientpositive/vector_char_2.q.out index dc2c1e41ea..ff4344ba3e 100644 --- a/ql/src/test/results/clientpositive/vector_char_2.q.out +++ b/ql/src/test/results/clientpositive/vector_char_2.q.out @@ -84,7 +84,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: char_2_n0 - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 89178 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -95,7 +95,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3] selectExpressions: CastStringToLong(col 0:char(10)) -> 3:int - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 89178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count() Group By Vectorization: @@ -109,7 +109,7 @@ STAGE PLANS: keys: _col0 (type: char(20)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: char(20)) sort order: + @@ -119,7 +119,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized @@ -142,7 +142,7 @@ STAGE PLANS: keys: KEY._col0 (type: char(20)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 49401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -164,7 +164,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 250 Data size: 49401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized @@ -185,13 +185,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: char(20)), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 49401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 985 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 535 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 985 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 535 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -272,7 +272,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: char_2_n0 - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 89178 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -283,7 +283,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3] selectExpressions: CastStringToLong(col 0:char(10)) -> 3:int - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 501 Data size: 89178 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count() Group By Vectorization: @@ -297,7 +297,7 @@ STAGE PLANS: keys: _col0 (type: char(20)) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: char(20)) sort order: - @@ -307,7 +307,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 501 Data size: 99000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized @@ -330,7 +330,7 @@ STAGE PLANS: keys: KEY._col0 (type: char(20)) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 49401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -352,7 +352,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 250 Data size: 49401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized @@ -373,13 +373,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: char(20)), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 49401 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 985 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 535 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 985 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 535 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_char_4.q.out b/ql/src/test/results/clientpositive/vector_char_4.q.out index 8d275372db..6e7ec7173b 100644 --- a/ql/src/test/results/clientpositive/vector_char_4.q.out +++ b/ql/src/test/results/clientpositive/vector_char_4.q.out @@ -147,7 +147,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -158,13 +158,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [14, 15, 16, 17, 18, 19, 20] selectExpressions: CastLongToChar(col 0:tinyint, maxLength 10) -> 14:char(10), CastLongToChar(col 1:smallint, maxLength 10) -> 15:char(10), CastLongToChar(col 2:int, maxLength 20) -> 16:char(20), CastLongToChar(col 3:bigint, maxLength 30) -> 17:char(30), CastFloatToChar(col 4:float, maxLength 20) -> 18:char(20), CastDoubleToChar(col 5:double, maxLength 20) -> 19:char(20), CastStringGroupToChar(col 8:string, maxLength 50) -> 20:char(50) - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out b/ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out index 260c1596d5..a5bfa88657 100644 --- a/ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out +++ b/ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out @@ -421,14 +421,14 @@ STAGE PLANS: TableScan alias: b filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 CAST( _col1 AS STRING) (type: string) diff --git a/ql/src/test/results/clientpositive/vector_coalesce_2.q.out b/ql/src/test/results/clientpositive/vector_coalesce_2.q.out index 918ac59c99..bcba118087 100644 --- a/ql/src/test/results/clientpositive/vector_coalesce_2.q.out +++ b/ql/src/test/results/clientpositive/vector_coalesce_2.q.out @@ -52,7 +52,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: str_str_orc - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -63,7 +63,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 5] selectExpressions: CastStringToLong(col 4:string)(children: VectorCoalesce(columns [0, 3])(children: col 0:string, ConstantVectorExpression(val 0) -> 3:string) -> 4:string) -> 5:int - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) Group By Vectorization: @@ -77,7 +77,7 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -87,7 +87,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -109,14 +109,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), round((UDFToDouble(_col1) / 60.0D), 2) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -167,7 +167,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: str_str_orc - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -178,13 +178,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4] selectExpressions: VectorCoalesce(columns [0, 3])(children: col 0:string, ConstantVectorExpression(val 0) -> 3:string) -> 4:string - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -247,7 +247,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: str_str_orc - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -258,7 +258,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 5] selectExpressions: CastStringToLong(col 4:string)(children: VectorCoalesce(columns [0, 3])(children: col 0:string, ConstantVectorExpression(val 0) -> 3:string) -> 4:string) -> 5:int - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) Group By Vectorization: @@ -272,7 +272,7 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -282,7 +282,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -304,14 +304,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), round((UDFToDouble(_col1) / 60.0D), 2) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -362,7 +362,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: str_str_orc - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -373,13 +373,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4] selectExpressions: VectorCoalesce(columns [0, 3])(children: col 0:string, ConstantVectorExpression(val 0) -> 3:string) -> 4:string - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 510 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_coalesce_3.q.out b/ql/src/test/results/clientpositive/vector_coalesce_3.q.out index 884078d734..a4418db94c 100644 --- a/ql/src/test/results/clientpositive/vector_coalesce_3.q.out +++ b/ql/src/test/results/clientpositive/vector_coalesce_3.q.out @@ -80,11 +80,11 @@ STAGE PLANS: $hdt$_1:n TableScan alias: n - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: member (type: bigint), attr (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: bigint) @@ -95,7 +95,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: m - Statistics: Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:member:bigint, 1:ROW__ID:struct] @@ -106,7 +106,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -121,7 +121,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col2 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), CASE WHEN ((COALESCE(_col2,5) > 1)) THEN (_col2) ELSE (null) END (type: bigint) outputColumnNames: _col0, _col1 @@ -130,13 +130,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3] selectExpressions: IfExprColumnNull(col 2:boolean, col 1:bigint, null)(children: LongColGreaterLongScalar(col 3:bigint, val 1)(children: VectorCoalesce(columns [1, 2])(children: col 1:bigint, ConstantVectorExpression(val 5) -> 2:bigint) -> 3:bigint) -> 2:boolean, col 1:bigint) -> 3:bigint - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_coalesce_4.q.out b/ql/src/test/results/clientpositive/vector_coalesce_4.q.out index c7c0da62aa..a3e03b94bc 100644 --- a/ql/src/test/results/clientpositive/vector_coalesce_4.q.out +++ b/ql/src/test/results/clientpositive/vector_coalesce_4.q.out @@ -46,7 +46,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: coalesce_test - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct] @@ -58,7 +58,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 0, 1] selectExpressions: VectorCoalesce(columns [0, 1])(children: col 0:int, col 1:int) -> 3:int - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int) sort order: ++ @@ -67,7 +67,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Map Vectorization: @@ -93,10 +93,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_count.q.out b/ql/src/test/results/clientpositive/vector_count.q.out index 10a144aaa1..b541b72ffd 100644 --- a/ql/src/test/results/clientpositive/vector_count.q.out +++ b/ql/src/test/results/clientpositive/vector_count.q.out @@ -61,22 +61,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: abcd - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) outputColumnNames: a, b, c, d - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) keys: a (type: int), b (type: int), c (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: bigint) Map Vectorization: enabled: true @@ -94,10 +94,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -139,21 +139,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: abcd - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) outputColumnNames: a, b, c, d - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint) Map Vectorization: enabled: true @@ -170,14 +170,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -216,7 +216,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: abcd - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -226,7 +226,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3] - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: a (type: int), b (type: int), c (type: int) sort order: +++ @@ -236,7 +236,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, No DISTINCT columns IS false - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE value expressions: d (type: int) Execution mode: vectorized Map Vectorization: @@ -258,10 +258,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 42 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -303,7 +303,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: abcd - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -313,7 +313,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3] - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ @@ -322,7 +322,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, No DISTINCT columns IS false - Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -342,14 +342,14 @@ STAGE PLANS: aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_custom_udf_configure.q.out b/ql/src/test/results/clientpositive/vector_custom_udf_configure.q.out index 98e69a7709..f8382b2add 100644 --- a/ql/src/test/results/clientpositive/vector_custom_udf_configure.q.out +++ b/ql/src/test/results/clientpositive/vector_custom_udf_configure.q.out @@ -38,14 +38,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: testorc1 - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int), Hello... (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_data_types.q.out b/ql/src/test/results/clientpositive/vector_data_types.q.out index b9d8ac85fb..d412af9eb0 100644 --- a/ql/src/test/results/clientpositive/vector_data_types.q.out +++ b/ql/src/test/results/clientpositive/vector_data_types.q.out @@ -128,28 +128,28 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1korc_n1 - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: boolean), _col7 (type: string), _col8 (type: timestamp), _col9 (type: decimal(4,2)), _col10 (type: binary) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: boolean), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: decimal(4,2)), VALUE._col7 (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -218,7 +218,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1korc_n1 - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -228,7 +228,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10] - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int) sort order: +++ @@ -237,7 +237,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: boolean), _col7 (type: string), _col8 (type: timestamp), _col9 (type: decimal(4,2)), _col10 (type: binary) Execution mode: vectorized @@ -258,13 +258,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: boolean), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: decimal(4,2)), VALUE._col7 (type: binary) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -326,7 +326,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1korc_n1 - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -337,7 +337,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [12] selectExpressions: VectorUDFAdaptor(hash(t,si,i,b,f,d,bo,s,ts,dec,bin)) -> 12:int - Statistics: Num rows: 1050 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1050 Data size: 358026 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) Group By Vectorization: @@ -349,7 +349,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -357,7 +357,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -378,10 +378,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_date_1.q.out b/ql/src/test/results/clientpositive/vector_date_1.q.out index 6e997bc2b8..859ecc9c6a 100644 --- a/ql/src/test/results/clientpositive/vector_date_1.q.out +++ b/ql/src/test/results/clientpositive/vector_date_1.q.out @@ -104,7 +104,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_date_1 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct] @@ -116,7 +116,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 3, 4, 5, 6, 7, 8, 9, 10] selectExpressions: LongColEqualLongColumn(col 0:date, col 0:date) -> 3:boolean, LongColNotEqualLongColumn(col 0:date, col 1:date) -> 4:boolean, LongColLessEqualLongColumn(col 0:date, col 0:date) -> 5:boolean, LongColLessEqualLongColumn(col 0:date, col 1:date) -> 6:boolean, LongColLessLongColumn(col 0:date, col 1:date) -> 7:boolean, LongColGreaterEqualLongColumn(col 1:date, col 1:date) -> 8:boolean, LongColGreaterEqualLongColumn(col 1:date, col 0:date) -> 9:boolean, LongColGreaterLongColumn(col 1:date, col 0:date) -> 10:boolean - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -125,7 +125,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean) Execution mode: vectorized Map Vectorization: @@ -151,10 +151,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -243,7 +243,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_date_1 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct] @@ -255,7 +255,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 3, 4, 5, 6, 7, 8, 9, 10] selectExpressions: LongColNotEqualLongColumn(col 0:date, col 0:date) -> 3:boolean, LongColEqualLongColumn(col 0:date, col 1:date) -> 4:boolean, LongColLessLongColumn(col 0:date, col 0:date) -> 5:boolean, LongColGreaterEqualLongColumn(col 0:date, col 1:date) -> 6:boolean, LongColGreaterLongColumn(col 0:date, col 1:date) -> 7:boolean, LongColGreaterLongColumn(col 1:date, col 1:date) -> 8:boolean, LongColLessEqualLongColumn(col 1:date, col 0:date) -> 9:boolean, LongColLessLongColumn(col 1:date, col 0:date) -> 10:boolean - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -264,7 +264,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean) Execution mode: vectorized Map Vectorization: @@ -290,10 +290,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -382,7 +382,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_date_1 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct] @@ -394,7 +394,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3, 4, 5, 6, 7] selectExpressions: DateColNotEqualDateScalar(col 0:date, date 1970-01-01) -> 3:boolean, DateColGreaterEqualDateScalar(col 0:date, date 1970-01-01) -> 4:boolean, DateColGreaterDateScalar(col 0:date, date 1970-01-01) -> 5:boolean, DateColLessEqualDateScalar(col 0:date, date 2100-01-01) -> 6:boolean, DateColLessDateScalar(col 0:date, date 2100-01-01) -> 7:boolean - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -403,7 +403,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean) Execution mode: vectorized Map Vectorization: @@ -429,10 +429,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -521,7 +521,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_date_1 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct] @@ -533,7 +533,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3, 4, 5, 6, 7] selectExpressions: DateColEqualDateScalar(col 0:date, date 1970-01-01) -> 3:boolean, DateColLessEqualDateScalar(col 0:date, date 1970-01-01) -> 4:boolean, DateColLessDateScalar(col 0:date, date 1970-01-01) -> 5:boolean, DateColGreaterEqualDateScalar(col 0:date, date 2100-01-01) -> 6:boolean, DateColGreaterDateScalar(col 0:date, date 2100-01-01) -> 7:boolean - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -542,7 +542,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean) Execution mode: vectorized Map Vectorization: @@ -568,10 +568,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -659,7 +659,7 @@ STAGE PLANS: TableScan alias: vector_date_1 filterExpr: ((dt1 = dt1) and (dt1 <> dt2) and (dt1 < dt2) and (dt1 <= dt2) and (dt2 > dt1) and (dt2 >= dt1)) (type: boolean) - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct] @@ -669,7 +669,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongColumn(col 0:date, col 0:date), FilterLongColNotEqualLongColumn(col 0:date, col 1:date), FilterLongColLessLongColumn(col 0:date, col 1:date), FilterLongColLessEqualLongColumn(col 0:date, col 1:date), FilterLongColGreaterLongColumn(col 1:date, col 0:date), FilterLongColGreaterEqualLongColumn(col 1:date, col 0:date)) predicate: ((dt1 < dt2) and (dt1 <= dt2) and (dt1 <> dt2) and (dt1 = dt1) and (dt2 > dt1) and (dt2 >= dt1)) (type: boolean) - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt1 (type: date), dt2 (type: date) outputColumnNames: _col0, _col1 @@ -677,7 +677,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -686,7 +686,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: date) Execution mode: vectorized Map Vectorization: @@ -712,10 +712,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -804,7 +804,7 @@ STAGE PLANS: TableScan alias: vector_date_1 filterExpr: ((dt1 = DATE'2001-01-01') and (dt1 <> DATE'1970-01-01')) (type: boolean) - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct] @@ -814,7 +814,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDateColEqualDateScalar(col 0:date, val 11323), FilterDateColNotEqualDateScalar(col 0:date, val 0)) predicate: ((dt1 <> DATE'1970-01-01') and (dt1 = DATE'2001-01-01')) (type: boolean) - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: DATE'2001-01-01' (type: date), dt2 (type: date) outputColumnNames: _col0, _col1 @@ -823,13 +823,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 1] selectExpressions: ConstantVectorExpression(val 11323) -> 3:date - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -913,7 +913,7 @@ STAGE PLANS: TableScan alias: vector_date_1 filterExpr: (dt1) IN (DATE'1970-01-01', DATE'2001-01-01') (type: boolean) - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct] @@ -923,7 +923,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColumnInList(col 0:date, values [0, 11323]) predicate: (dt1) IN (DATE'1970-01-01', DATE'2001-01-01') (type: boolean) - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dt1 (type: date) outputColumnNames: _col0 @@ -931,13 +931,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_1.q.out b/ql/src/test/results/clientpositive/vector_decimal_1.q.out index 253ccdd56d..1ab46b18a1 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_1.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_1.q.out @@ -63,7 +63,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -75,7 +75,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToBoolean(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:boolean - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -84,7 +84,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -109,10 +109,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -154,7 +154,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -166,7 +166,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToLong(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:tinyint - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -175,7 +175,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -200,10 +200,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -245,7 +245,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -257,7 +257,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToLong(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:smallint - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + @@ -266,7 +266,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -291,10 +291,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: smallint) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -336,7 +336,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -348,7 +348,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToLong(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:int - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -357,7 +357,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -382,10 +382,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -427,7 +427,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -439,7 +439,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToLong(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:bigint - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + @@ -448,7 +448,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -473,10 +473,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -518,7 +518,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -530,7 +530,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToFloat(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:float - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: float) sort order: + @@ -539,7 +539,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -564,10 +564,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -609,7 +609,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -621,7 +621,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToDouble(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:double - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -630,7 +630,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -655,10 +655,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -700,7 +700,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -712,7 +712,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToString(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:string - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -721,7 +721,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -746,10 +746,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -791,7 +791,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_1 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:t:decimal(4,2)/DECIMAL_64, 1:u:decimal(5,0)/DECIMAL_64, 2:v:decimal(10,0)/DECIMAL_64, 3:ROW__ID:struct] @@ -803,7 +803,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: CastDecimalToTimestamp(col 4:decimal(4,2))(children: ConvertDecimal64ToDecimal(col 0:decimal(4,2)/DECIMAL_64) -> 4:decimal(4,2)) -> 5:timestamp - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp) sort order: + @@ -812,7 +812,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -837,10 +837,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out b/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out index 6526abe576..b272684189 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_10_0.q.out @@ -53,7 +53,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal - Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct] @@ -64,7 +64,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + @@ -73,7 +73,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -98,10 +98,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -143,7 +143,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_txt - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct] @@ -154,7 +154,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + @@ -163,7 +163,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -188,10 +188,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_5.q.out b/ql/src/test/results/clientpositive/vector_decimal_5.q.out index a2e114b410..ccb459bc0b 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_5.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_5.q.out @@ -143,14 +143,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_5 - Statistics: Num rows: 38 Data size: 4072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38 Data size: 4032 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( key AS decimal(10,0)) (type: decimal(10,0)) outputColumnNames: _col0 - Statistics: Num rows: 38 Data size: 4072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38 Data size: 4032 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 38 Data size: 4072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 38 Data size: 4032 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_6.q.out b/ql/src/test/results/clientpositive/vector_decimal_6.q.out index 445896b145..2c9423a35e 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_6.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_6.q.out @@ -126,7 +126,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_6_1 - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2684 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:decimal(10,5)/DECIMAL_64, 1:value:int, 2:ROW__ID:struct] @@ -137,7 +137,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2684 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(10,5)), _col1 (type: int) sort order: ++ @@ -146,7 +146,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2684 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -171,10 +171,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,5)), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2684 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2684 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -241,7 +241,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_6_2 - Statistics: Num rows: 27 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:decimal(17,4)/DECIMAL_64, 1:value:int, 2:ROW__ID:struct] @@ -252,7 +252,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 27 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(17,4)), _col1 (type: int) sort order: ++ @@ -261,7 +261,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 27 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -286,10 +286,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(17,4)), KEY.reducesinkkey1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -364,30 +364,30 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_6_1 - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2576 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( key AS decimal(18,5)) (type: decimal(18,5)) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2576 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 54 Data size: 5592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(18,5)) sort order: + - Statistics: Num rows: 54 Data size: 5592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: decimal_6_2 - Statistics: Num rows: 27 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( key AS decimal(18,5)) (type: decimal(18,5)) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 3020 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: COMPLETE Union - Statistics: Num rows: 54 Data size: 5592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(18,5)) sort order: + - Statistics: Num rows: 54 Data size: 5592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5600 Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -399,10 +399,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(18,5)) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 5592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 4928 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 5592 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 4928 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -508,7 +508,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_6_1 - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 2684 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:decimal(10,5)/DECIMAL_64, 1:value:int, 2:ROW__ID:struct] @@ -520,7 +520,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4] selectExpressions: Decimal64ColAddDecimal64Scalar(col 0:decimal(10,5)/DECIMAL_64, decimal64Val 550000, decimalVal 5.5) -> 3:decimal(11,5)/DECIMAL_64, LongColMultiplyLongScalar(col 1:int, val 11) -> 4:int - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -529,7 +529,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(11,5)) Execution mode: vectorized Map Vectorization: @@ -555,10 +555,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: decimal(11,5)), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out index b9f4444b18..7a5d8c8c0f 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_aggregate.q.out @@ -62,7 +62,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_vgby - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(20,10), 2:cdecimal2:decimal(23,14), 3:cint:int, 4:ROW__ID:struct] @@ -73,7 +73,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1, 2, 3] - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() Group By Vectorization: @@ -87,7 +87,7 @@ STAGE PLANS: keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -97,7 +97,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: bigint), _col6 (type: decimal(23,14)), _col7 (type: decimal(23,14)), _col8 (type: decimal(33,14)), _col9 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -125,17 +125,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 6144 Data size: 1082441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col9 > 1L) (type: boolean) - Statistics: Num rows: 2048 Data size: 360813 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: bigint), _col6 (type: decimal(23,14)), _col7 (type: decimal(23,14)), _col8 (type: decimal(33,14)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2048 Data size: 360813 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 360813 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -203,7 +203,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_vgby - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(20,10), 2:cdecimal2:decimal(23,14), 3:cint:int, 4:ROW__ID:struct] @@ -215,7 +215,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 1, 2, 5, 8, 6, 10] selectExpressions: CastDecimalToDouble(col 1:decimal(20,10)) -> 5:double, DoubleColMultiplyDoubleColumn(col 6:double, col 7:double)(children: CastDecimalToDouble(col 1:decimal(20,10)) -> 6:double, CastDecimalToDouble(col 1:decimal(20,10)) -> 7:double) -> 8:double, CastDecimalToDouble(col 2:decimal(23,14)) -> 6:double, DoubleColMultiplyDoubleColumn(col 7:double, col 9:double)(children: CastDecimalToDouble(col 2:decimal(23,14)) -> 7:double, CastDecimalToDouble(col 2:decimal(23,14)) -> 9:double) -> 10:double - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), sum(_col4), sum(_col3), count(_col2), max(_col2), min(_col2), sum(_col2), sum(_col6), sum(_col5), count() Group By Vectorization: @@ -229,7 +229,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -239,7 +239,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12289 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: decimal(23,14)), _col9 (type: decimal(23,14)), _col10 (type: decimal(33,14)), _col11 (type: double), _col12 (type: double), _col13 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -267,17 +267,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 6144 Data size: 1082441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col13 > 1L) (type: boolean) - Statistics: Num rows: 2048 Data size: 360813 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), (CAST( _col4 AS decimal(24,14)) / _col1) (type: decimal(38,28)), power(((_col5 - ((_col6 * _col6) / _col1)) / _col1), 0.5) (type: double), power(((_col5 - ((_col6 * _col6) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), _col7 (type: bigint), _col8 (type: decimal(23,14)), _col9 (type: decimal(23,14)), _col10 (type: decimal(33,14)), (CAST( _col10 AS decimal(27,18)) / _col7) (type: decimal(38,29)), power(((_col11 - ((_col12 * _col12) / _col7)) / _col7), 0.5) (type: double), power(((_col11 - ((_col12 * _col12) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2048 Data size: 360813 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 360813 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -379,7 +379,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_vgby_small - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(11,5)/DECIMAL_64, 2:cdecimal2:decimal(16,0)/DECIMAL_64, 3:cint:int, 4:ROW__ID:struct] @@ -390,7 +390,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1, 2, 3] - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() Group By Vectorization: @@ -404,7 +404,7 @@ STAGE PLANS: keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -414,7 +414,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), _col5 (type: bigint), _col6 (type: decimal(16,0)), _col7 (type: decimal(16,0)), _col8 (type: decimal(26,0)), _col9 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -442,17 +442,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 6144 Data size: 173216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col9 > 1L) (type: boolean) - Statistics: Num rows: 2048 Data size: 57738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), _col5 (type: bigint), _col6 (type: decimal(16,0)), _col7 (type: decimal(16,0)), _col8 (type: decimal(26,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 2048 Data size: 57738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 57738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -539,7 +539,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_vgby_small - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(11,5)/DECIMAL_64, 2:cdecimal2:decimal(16,0)/DECIMAL_64, 3:cint:int, 4:ROW__ID:struct] @@ -551,7 +551,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 1, 2, 6, 9, 7, 12] selectExpressions: CastDecimalToDouble(col 5:decimal(11,5))(children: ConvertDecimal64ToDecimal(col 1:decimal(11,5)/DECIMAL_64) -> 5:decimal(11,5)) -> 6:double, DoubleColMultiplyDoubleColumn(col 7:double, col 8:double)(children: CastDecimalToDouble(col 5:decimal(11,5))(children: ConvertDecimal64ToDecimal(col 1:decimal(11,5)/DECIMAL_64) -> 5:decimal(11,5)) -> 7:double, CastDecimalToDouble(col 5:decimal(11,5))(children: ConvertDecimal64ToDecimal(col 1:decimal(11,5)/DECIMAL_64) -> 5:decimal(11,5)) -> 8:double) -> 9:double, CastDecimalToDouble(col 10:decimal(16,0))(children: ConvertDecimal64ToDecimal(col 2:decimal(16,0)/DECIMAL_64) -> 10:decimal(16,0)) -> 7:double, DoubleColMultiplyDoubleColumn(col 8:double, col 11:double)(children: CastDecimalToDouble(col 10:decimal(16,0))(children: ConvertDecimal64ToDecimal(col 2:decimal(16,0)/DECIMAL_64) -> 10:decimal(16,0)) -> 8:double, CastDecimalToDouble(col 10:decimal(16,0))(children: ConvertDecimal64ToDecimal(col 2:decimal(16,0)/DECIMAL_64) -> 10:decimal(16,0)) -> 11:double) -> 12:double - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), sum(_col4), sum(_col3), count(_col2), max(_col2), min(_col2), sum(_col2), sum(_col6), sum(_col5), count() Group By Vectorization: @@ -565,7 +565,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -575,7 +575,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12289 Data size: 346462 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: decimal(16,0)), _col9 (type: decimal(16,0)), _col10 (type: decimal(26,0)), _col11 (type: double), _col12 (type: double), _col13 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -603,17 +603,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 6144 Data size: 173216 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col13 > 1L) (type: boolean) - Statistics: Num rows: 2048 Data size: 57738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), (CAST( _col4 AS decimal(15,9)) / _col1) (type: decimal(35,29)), power(((_col5 - ((_col6 * _col6) / _col1)) / _col1), 0.5) (type: double), power(((_col5 - ((_col6 * _col6) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), _col7 (type: bigint), _col8 (type: decimal(16,0)), _col9 (type: decimal(16,0)), _col10 (type: decimal(26,0)), CAST( (CAST( _col10 AS decimal(20,4)) / _col7) AS decimal(20,4)) (type: decimal(20,4)), power(((_col11 - ((_col12 * _col12) / _col7)) / _col7), 0.5) (type: double), power(((_col11 - ((_col12 * _col12) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2048 Data size: 57738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 57738 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_cast.q.out b/ql/src/test/results/clientpositive/vector_decimal_cast.q.out index 8fcd217e8c..a422eecb19 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_cast.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_cast.q.out @@ -17,7 +17,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (cdouble is not null and cint is not null and cboolean1 is not null and ctimestamp1 is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 638316 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -27,7 +27,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 5:double), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 10:boolean), SelectColumnIsNotNull(col 8:timestamp)) predicate: (cboolean1 is not null and cdouble is not null and cint is not null and ctimestamp1 is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5112 Data size: 265564 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 @@ -36,19 +36,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 2, 10, 8, 13, 14, 15, 16] selectExpressions: CastDoubleToDecimal(col 5:double) -> 13:decimal(20,10), CastLongToDecimal(col 2:int) -> 14:decimal(23,14), CastLongToDecimal(col 10:boolean) -> 15:decimal(5,2), CastTimestampToDecimal(col 8:timestamp) -> 16:decimal(15,0) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5112 Data size: 2410700 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4784 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 4784 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -137,7 +137,7 @@ STAGE PLANS: TableScan alias: alltypes_small filterExpr: (cdouble is not null and cint is not null and cboolean1 is not null and ctimestamp1 is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 1333293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -147,7 +147,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 5:double), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 10:boolean), SelectColumnIsNotNull(col 8:timestamp)) predicate: (cboolean1 is not null and cdouble is not null and cint is not null and ctimestamp1 is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 1333293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9832 Data size: 523125 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 @@ -156,19 +156,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 2, 10, 8, 13, 14, 15, 16] selectExpressions: CastDoubleToDecimal(col 5:double) -> 13:decimal(20,10), CastLongToDecimal(col 2:int) -> 14:decimal(23,14), CastLongToDecimal(col 10:boolean) -> 15:decimal(5,2), CastTimestampToDecimal(col 8:timestamp) -> 16:decimal(15,0) - Statistics: Num rows: 12288 Data size: 1333293 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9832 Data size: 523125 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 1080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out b/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out index c131dc0942..25e164cf50 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_expressions.q.out @@ -53,7 +53,7 @@ STAGE PLANS: TableScan alias: decimal_test_n1 filterExpr: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 <> 0) and (cdecimal2 > 1000) and cdouble is not null) (type: boolean) - Statistics: Num rows: 12289 Data size: 2128368 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 2708832 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(20,10), 2:cdecimal2:decimal(23,14), 3:ROW__ID:struct] @@ -63,7 +63,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDecimalColGreaterDecimalScalar(col 1:decimal(20,10), val 0), FilterDecimalColLessDecimalScalar(col 1:decimal(20,10), val 12345.5678), FilterDecimalColNotEqualDecimalScalar(col 2:decimal(23,14), val 0), FilterDecimalColGreaterDecimalScalar(col 2:decimal(23,14), val 1000), SelectColumnIsNotNull(col 0:double)) predicate: ((cdecimal1 < 12345.5678) and (cdecimal1 > 0) and (cdecimal2 <> 0) and (cdecimal2 > 1000) and cdouble is not null) (type: boolean) - Statistics: Num rows: 455 Data size: 78802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(25,14)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(26,14)), ((cdecimal1 + 2.34) / cdecimal2) (type: decimal(38,13)), (cdecimal1 * (cdecimal2 / 3.4)) (type: decimal(38,17)), (cdecimal1 % 10) (type: decimal(12,10)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), CAST( cdecimal2 AS STRING) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -72,7 +72,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] selectExpressions: DecimalColAddDecimalColumn(col 1:decimal(20,10), col 2:decimal(23,14)) -> 4:decimal(25,14), DecimalColSubtractDecimalColumn(col 1:decimal(20,10), col 5:decimal(25,14))(children: DecimalScalarMultiplyDecimalColumn(val 2, col 2:decimal(23,14)) -> 5:decimal(25,14)) -> 6:decimal(26,14), DecimalColDivideDecimalColumn(col 7:decimal(21,10), col 2:decimal(23,14))(children: DecimalColAddDecimalScalar(col 1:decimal(20,10), val 2.34) -> 7:decimal(21,10)) -> 8:decimal(38,13), DecimalColMultiplyDecimalColumn(col 1:decimal(20,10), col 9:decimal(27,17))(children: DecimalColDivideDecimalScalar(col 2:decimal(23,14), val 3.4) -> 9:decimal(27,17)) -> 10:decimal(38,17), DecimalColModuloDecimalScalar(col 1:decimal(20,10), val 10) -> 11:decimal(12,10), CastDecimalToLong(col 1:decimal(20,10)) -> 12:int, CastDecimalToLong(col 2:decimal(23,14)) -> 13:smallint, CastDecimalToLong(col 2:decimal(23,14)) -> 14:tinyint, CastDecimalToLong(col 1:decimal(20,10)) -> 15:bigint, CastDecimalToBoolean(col 1:decimal(20,10)) -> 16:boolean, CastDecimalToDouble(col 2:decimal(23,14)) -> 17:double, CastDecimalToFloat(col 1:decimal(20,10)) -> 18:float, CastDecimalToString(col 2:decimal(23,14)) -> 19:string, CastDecimalToTimestamp(col 1:decimal(20,10)) -> 20:timestamp - Statistics: Num rows: 455 Data size: 78802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(25,14)), _col1 (type: decimal(26,14)), _col2 (type: decimal(38,13)), _col3 (type: decimal(38,17)), _col4 (type: decimal(12,10)), _col5 (type: int), _col6 (type: smallint), _col7 (type: tinyint), _col8 (type: bigint), _col9 (type: boolean), _col10 (type: double), _col11 (type: float), _col12 (type: string), _col13 (type: timestamp) sort order: ++++++++++++++ @@ -81,7 +81,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 455 Data size: 78802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -107,13 +107,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(25,14)), KEY.reducesinkkey1 (type: decimal(26,14)), KEY.reducesinkkey2 (type: decimal(38,13)), KEY.reducesinkkey3 (type: decimal(38,17)), KEY.reducesinkkey4 (type: decimal(12,10)), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: smallint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey9 (type: boolean), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: string), KEY.reducesinkkey13 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 455 Data size: 78802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -198,7 +198,7 @@ STAGE PLANS: TableScan alias: decimal_test_small_n0 filterExpr: ((cdecimal1 > 0) and (cdecimal1 < 12345.5678) and (cdecimal2 <> 0) and (cdecimal2 > 1000) and cdouble is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 2127808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2708600 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(10,3)/DECIMAL_64, 2:cdecimal2:decimal(7,2)/DECIMAL_64, 3:ROW__ID:struct] @@ -208,7 +208,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterDecimal64ColGreaterDecimal64Scalar(col 1:decimal(10,3)/DECIMAL_64, val 0), FilterDecimalColLessDecimalScalar(col 4:decimal(10,3), val 12345.5678)(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)), FilterDecimal64ColNotEqualDecimal64Scalar(col 2:decimal(7,2)/DECIMAL_64, val 0), FilterDecimal64ColGreaterDecimal64Scalar(col 2:decimal(7,2)/DECIMAL_64, val 100000), SelectColumnIsNotNull(col 0:double)) predicate: ((cdecimal1 < 12345.5678) and (cdecimal1 > 0) and (cdecimal2 <> 0) and (cdecimal2 > 1000) and cdouble is not null) (type: boolean) - Statistics: Num rows: 455 Data size: 78788 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (cdecimal1 + cdecimal2) (type: decimal(11,3)), (cdecimal1 - (2 * cdecimal2)) (type: decimal(11,3)), ((cdecimal1 + 2.34) / cdecimal2) (type: decimal(21,11)), (cdecimal1 * (cdecimal2 / 3.4)) (type: decimal(23,9)), (cdecimal1 % 10) (type: decimal(5,3)), UDFToInteger(cdecimal1) (type: int), UDFToShort(cdecimal2) (type: smallint), UDFToByte(cdecimal2) (type: tinyint), UDFToLong(cdecimal1) (type: bigint), UDFToBoolean(cdecimal1) (type: boolean), UDFToDouble(cdecimal2) (type: double), UDFToFloat(cdecimal1) (type: float), CAST( cdecimal2 AS STRING) (type: string), CAST( cdecimal1 AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -217,7 +217,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 8, 10, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] selectExpressions: DecimalColAddDecimalColumn(col 4:decimal(10,3), col 5:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3), ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 6:decimal(11,3), DecimalColSubtractDecimalColumn(col 4:decimal(10,3), col 7:decimal(9,2))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3), DecimalScalarMultiplyDecimalColumn(val 2, col 5:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 7:decimal(9,2)) -> 8:decimal(11,3), DecimalColDivideDecimalColumn(col 23:decimal(11,3), col 5:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 9:decimal(11,3)/DECIMAL_64)(children: Decimal64ColAddDecimal64Scalar(col 1:decimal(10,3)/DECIMAL_64, decimal64Val 2340, decimalVal 2.34) -> 9:decimal(11,3)/DECIMAL_64) -> 23:decimal(11,3), ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 10:decimal(21,11), DecimalColMultiplyDecimalColumn(col 4:decimal(10,3), col 11:decimal(12,6))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3), DecimalColDivideDecimalScalar(col 5:decimal(7,2), val 3.4)(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 11:decimal(12,6)) -> 12:decimal(23,9), DecimalColModuloDecimalScalar(col 4:decimal(10,3), val 10)(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)) -> 13:decimal(5,3), CastDecimalToLong(col 4:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)) -> 14:int, CastDecimalToLong(col 5:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 15:smallint, CastDecimalToLong(col 5:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 16:tinyint, CastDecimalToLong(col 4:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)) -> 17:bigint, CastDecimalToBoolean(col 4:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)) -> 18:boolean, CastDecimalToDouble(col 5:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 19:double, CastDecimalToFloat(col 4:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)) -> 20:float, CastDecimalToString(col 5:decimal(7,2))(children: ConvertDecimal64ToDecimal(col 2:decimal(7,2)/DECIMAL_64) -> 5:decimal(7,2)) -> 21:string, CastDecimalToTimestamp(col 4:decimal(10,3))(children: ConvertDecimal64ToDecimal(col 1:decimal(10,3)/DECIMAL_64) -> 4:decimal(10,3)) -> 22:timestamp - Statistics: Num rows: 455 Data size: 78788 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: decimal(11,3)), _col1 (type: decimal(11,3)), _col2 (type: decimal(21,11)), _col3 (type: decimal(23,9)), _col4 (type: decimal(5,3)), _col5 (type: int), _col6 (type: smallint), _col7 (type: tinyint), _col8 (type: bigint), _col9 (type: boolean), _col10 (type: double), _col11 (type: float), _col12 (type: string), _col13 (type: timestamp) sort order: ++++++++++++++ @@ -226,7 +226,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 455 Data size: 78788 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -252,13 +252,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(11,3)), KEY.reducesinkkey1 (type: decimal(11,3)), KEY.reducesinkkey2 (type: decimal(21,11)), KEY.reducesinkkey3 (type: decimal(23,9)), KEY.reducesinkkey4 (type: decimal(5,3)), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: smallint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: bigint), KEY.reducesinkkey9 (type: boolean), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: string), KEY.reducesinkkey13 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 455 Data size: 78788 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 455 Data size: 100294 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1730 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_decimal_mapjoin.q.out index aa9f54b5b3..5a9ff28585 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_mapjoin.q.out @@ -101,14 +101,14 @@ STAGE PLANS: TableScan alias: t2_n29 filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 111776 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(24,0)) outputColumnNames: _col0 - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: decimal(26,2)) @@ -120,7 +120,7 @@ STAGE PLANS: TableScan alias: t1_n48 filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 111776 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(22,2), 1:value_dec:decimal(22,2), 2:ROW__ID:struct] @@ -130,7 +130,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:decimal(22,2)) predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(22,2)) outputColumnNames: _col0 @@ -138,7 +138,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -154,13 +154,13 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, Optimized Table and Supports Key Types IS false nativeNotSupportedKeyTypes: DECIMAL outputColumnNames: _col0, _col1 - Statistics: Num rows: 1153 Data size: 258473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 116858 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1153 Data size: 258473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 116858 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -344,14 +344,14 @@ STAGE PLANS: TableScan alias: t2_n29 filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 223552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(24,0)), value_dec (type: decimal(24,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: decimal(26,2)) @@ -363,7 +363,7 @@ STAGE PLANS: TableScan alias: t1_n48 filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 223552 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(22,2), 1:value_dec:decimal(22,2), 2:ROW__ID:struct] @@ -373,7 +373,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:decimal(22,2)) predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(22,2)), value_dec (type: decimal(22,2)) outputColumnNames: _col0, _col1 @@ -381,7 +381,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1049 Data size: 234976 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -397,13 +397,13 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, Optimized Table and Supports Key Types IS false nativeNotSupportedKeyTypes: DECIMAL outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1153 Data size: 258473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 233717 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1153 Data size: 258473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 233717 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -663,14 +663,14 @@ STAGE PLANS: TableScan alias: t2_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 111776 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,0)) outputColumnNames: _col0 - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: decimal(16,2)) @@ -682,7 +682,7 @@ STAGE PLANS: TableScan alias: t1_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 111776 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(14,2)/DECIMAL_64, 1:value_dec:decimal(14,2)/DECIMAL_64, 2:ROW__ID:struct] @@ -692,7 +692,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:decimal(14,2)/DECIMAL_64) predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,2)) outputColumnNames: _col0 @@ -700,7 +700,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -716,13 +716,13 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, Optimized Table and Supports Key Types IS false nativeNotSupportedKeyTypes: DECIMAL outputColumnNames: _col0, _col1 - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 116858 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 116858 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -906,14 +906,14 @@ STAGE PLANS: TableScan alias: t2_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 223552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,0)), value_dec (type: decimal(14,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: decimal(16,2)) @@ -925,7 +925,7 @@ STAGE PLANS: TableScan alias: t1_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 223552 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(14,2)/DECIMAL_64, 1:value_dec:decimal(14,2)/DECIMAL_64, 2:ROW__ID:struct] @@ -935,7 +935,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:decimal(14,2)/DECIMAL_64) predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,2)), value_dec (type: decimal(14,2)) outputColumnNames: _col0, _col1 @@ -943,7 +943,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -959,13 +959,13 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, Optimized Table and Supports Key Types IS false nativeNotSupportedKeyTypes: DECIMAL outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 233717 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 233717 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1149,14 +1149,14 @@ STAGE PLANS: TableScan alias: t2_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 111776 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,0)) outputColumnNames: _col0 - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: decimal(16,2)) @@ -1168,7 +1168,7 @@ STAGE PLANS: TableScan alias: t1_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 111776 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(14,2), 1:value_dec:decimal(14,2), 2:ROW__ID:struct] @@ -1178,7 +1178,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:decimal(14,2)) predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,2)) outputColumnNames: _col0 @@ -1186,7 +1186,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 106235 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -1202,13 +1202,13 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, Optimized Table and Supports Key Types IS false nativeNotSupportedKeyTypes: DECIMAL outputColumnNames: _col0, _col1 - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 116858 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 116858 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1393,14 +1393,14 @@ STAGE PLANS: TableScan alias: t2_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 223552 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,0)), value_dec (type: decimal(14,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1049 Data size: 4966 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: decimal(16,2)) @@ -1412,7 +1412,7 @@ STAGE PLANS: TableScan alias: t1_small filterExpr: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 223552 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(14,2), 1:value_dec:decimal(14,2), 2:ROW__ID:struct] @@ -1422,7 +1422,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:decimal(14,2)) predicate: dec is not null (type: boolean) - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(14,2)), value_dec (type: decimal(14,2)) outputColumnNames: _col0, _col1 @@ -1430,7 +1430,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1049 Data size: 11234 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 997 Data size: 212470 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -1446,13 +1446,13 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, Optimized Table and Supports Key Types IS false nativeNotSupportedKeyTypes: DECIMAL outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 233717 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1153 Data size: 12357 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1096 Data size: 233717 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out b/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out index cee3efba6e..300c5c084d 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_math_funcs.q.out @@ -113,7 +113,7 @@ STAGE PLANS: TableScan alias: decimal_test_n0 filterExpr: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean) - Statistics: Num rows: 12289 Data size: 2201752 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12289 Data size: 1401120 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cbigint:bigint, 1:cdouble:double, 2:cdecimal1:decimal(20,10), 3:cdecimal2:decimal(23,14), 4:ROW__ID:struct] @@ -123,7 +123,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 5:bigint, val 0)(children: LongColModuloLongScalar(col 0:bigint, val 500) -> 5:bigint), FilterDoubleColGreaterEqualDoubleScalar(col 7:double, val -1.0)(children: FuncSinDoubleToDouble(col 6:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 6:double) -> 7:double)) predicate: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean) - Statistics: Num rows: 2048 Data size: 366928 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdecimal1 (type: decimal(20,10)), round(cdecimal1, 2) (type: decimal(13,2)), round(cdecimal1) (type: decimal(11,0)), floor(cdecimal1) (type: decimal(11,0)), ceil(cdecimal1) (type: decimal(11,0)), round(exp(cdecimal1), 58) (type: double), ln(cdecimal1) (type: double), log10(cdecimal1) (type: double), log2(cdecimal1) (type: double), log2((cdecimal1 - 15601)) (type: double), log(2, cdecimal1) (type: double), power(log2(cdecimal1), 2) (type: double), power(log2(cdecimal1), 2) (type: double), sqrt(cdecimal1) (type: double), abs(cdecimal1) (type: decimal(20,10)), sin(cdecimal1) (type: double), asin(cdecimal1) (type: double), cos(cdecimal1) (type: double), acos(cdecimal1) (type: double), atan(cdecimal1) (type: double), degrees(cdecimal1) (type: double), radians(cdecimal1) (type: double), cdecimal1 (type: decimal(20,10)), (- cdecimal1) (type: decimal(20,10)), sign(cdecimal1) (type: int), cos(((- sin(log(cdecimal1))) + 3.14159D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25 @@ -132,13 +132,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 8, 9, 10, 11, 6, 12, 13, 14, 16, 17, 7, 18, 20, 21, 22, 23, 24, 25, 26, 27, 28, 2, 29, 5, 30] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 2:decimal(20,10), decimalPlaces 2) -> 8:decimal(13,2), FuncRoundDecimalToDecimal(col 2:decimal(20,10)) -> 9:decimal(11,0), FuncFloorDecimalToDecimal(col 2:decimal(20,10)) -> 10:decimal(11,0), FuncCeilDecimalToDecimal(col 2:decimal(20,10)) -> 11:decimal(11,0), RoundWithNumDigitsDoubleToDouble(col 7, decimalPlaces 58)(children: FuncExpDoubleToDouble(col 6:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 6:double) -> 7:double) -> 6:double, FuncLnDoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 7:double) -> 12:double, FuncLog10DoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 7:double) -> 13:double, FuncLog2DoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 7:double) -> 14:double, FuncLog2DoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 15:decimal(21,10))(children: DecimalColSubtractDecimalScalar(col 2:decimal(20,10), val 15601) -> 15:decimal(21,10)) -> 7:double) -> 16:double, FuncLogWithBaseDoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 7:double) -> 17:double, FuncPowerDoubleToDouble(col 18:double)(children: FuncLog2DoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 7:double) -> 18:double) -> 7:double, FuncPowerDoubleToDouble(col 19:double)(children: FuncLog2DoubleToDouble(col 18:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 18:double) -> 19:double) -> 18:double, FuncSqrtDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 20:double, FuncAbsDecimalToDecimal(col 2:decimal(20,10)) -> 21:decimal(20,10), FuncSinDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 22:double, FuncASinDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 23:double, FuncCosDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 24:double, FuncACosDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 25:double, FuncATanDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 26:double, FuncDegreesDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 27:double, FuncRadiansDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 28:double, FuncNegateDecimalToDecimal(col 2:decimal(20,10)) -> 29:decimal(20,10), FuncSignDecimalToLong(col 2:decimal(20,10)) -> 5:int, FuncCosDoubleToDouble(col 19:double)(children: DoubleColAddDoubleScalar(col 30:double, val 3.14159)(children: DoubleColUnaryMinus(col 19:double)(children: FuncSinDoubleToDouble(col 30:double)(children: FuncLnDoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 30:double) -> 19:double) -> 30:double) -> 19:double) -> 30:double - Statistics: Num rows: 2048 Data size: 366928 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2048 Data size: 366928 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -356,7 +356,7 @@ STAGE PLANS: TableScan alias: decimal_test_small filterExpr: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2201192 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1401000 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:cbigint:bigint, 1:cdouble:double, 2:cdecimal1:decimal(12,4)/DECIMAL_64, 3:cdecimal2:decimal(14,8)/DECIMAL_64, 4:ROW__ID:struct] @@ -366,7 +366,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 5:bigint, val 0)(children: LongColModuloLongScalar(col 0:bigint, val 500) -> 5:bigint), FilterDoubleColGreaterEqualDoubleScalar(col 8:double, val -1.0)(children: FuncSinDoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 7:double) -> 8:double)) predicate: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean) - Statistics: Num rows: 2048 Data size: 366865 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdecimal1 (type: decimal(12,4)), round(cdecimal1, 2) (type: decimal(11,2)), round(cdecimal1) (type: decimal(9,0)), floor(cdecimal1) (type: decimal(9,0)), ceil(cdecimal1) (type: decimal(9,0)), round(exp(cdecimal1), 58) (type: double), ln(cdecimal1) (type: double), log10(cdecimal1) (type: double), log2(cdecimal1) (type: double), log2((cdecimal1 - 15601)) (type: double), log(2, cdecimal1) (type: double), power(log2(cdecimal1), 2) (type: double), power(log2(cdecimal1), 2) (type: double), sqrt(cdecimal1) (type: double), abs(cdecimal1) (type: decimal(12,4)), sin(cdecimal1) (type: double), asin(cdecimal1) (type: double), cos(cdecimal1) (type: double), acos(cdecimal1) (type: double), atan(cdecimal1) (type: double), degrees(cdecimal1) (type: double), radians(cdecimal1) (type: double), cdecimal1 (type: decimal(12,4)), (- cdecimal1) (type: decimal(12,4)), sign(cdecimal1) (type: int), cos(((- sin(log(cdecimal1))) + 3.14159D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25 @@ -375,13 +375,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 9, 10, 11, 12, 7, 13, 14, 15, 17, 18, 8, 19, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2, 30, 5, 31] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 6:decimal(12,4), decimalPlaces 2)(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 9:decimal(11,2), FuncRoundDecimalToDecimal(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 10:decimal(9,0), FuncFloorDecimalToDecimal(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 11:decimal(9,0), FuncCeilDecimalToDecimal(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 12:decimal(9,0), RoundWithNumDigitsDoubleToDouble(col 8, decimalPlaces 58)(children: FuncExpDoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 7:double) -> 8:double) -> 7:double, FuncLnDoubleToDouble(col 8:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 8:double) -> 13:double, FuncLog10DoubleToDouble(col 8:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 8:double) -> 14:double, FuncLog2DoubleToDouble(col 8:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 8:double) -> 15:double, FuncLog2DoubleToDouble(col 8:double)(children: CastDecimalToDouble(col 32:decimal(13,4))(children: ConvertDecimal64ToDecimal(col 16:decimal(13,4)/DECIMAL_64)(children: Decimal64ColSubtractDecimal64Scalar(col 2:decimal(12,4)/DECIMAL_64, decimal64Val 156010000, decimalVal 15601) -> 16:decimal(13,4)/DECIMAL_64) -> 32:decimal(13,4)) -> 8:double) -> 17:double, FuncLogWithBaseDoubleToDouble(col 8:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 8:double) -> 18:double, FuncPowerDoubleToDouble(col 19:double)(children: FuncLog2DoubleToDouble(col 8:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 8:double) -> 19:double) -> 8:double, FuncPowerDoubleToDouble(col 20:double)(children: FuncLog2DoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 19:double) -> 20:double) -> 19:double, FuncSqrtDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 21:double, FuncAbsDecimalToDecimal(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 22:decimal(12,4), FuncSinDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 23:double, FuncASinDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 24:double, FuncCosDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 25:double, FuncACosDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 26:double, FuncATanDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 27:double, FuncDegreesDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 28:double, FuncRadiansDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 29:double, FuncNegateDecimalToDecimal(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 30:decimal(12,4), FuncSignDecimalToLong(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 5:int, FuncCosDoubleToDouble(col 20:double)(children: DoubleColAddDoubleScalar(col 31:double, val 3.14159)(children: DoubleColUnaryMinus(col 20:double)(children: FuncSinDoubleToDouble(col 31:double)(children: FuncLnDoubleToDouble(col 20:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 20:double) -> 31:double) -> 20:double) -> 31:double) -> 20:double) -> 31:double - Statistics: Num rows: 2048 Data size: 366865 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2048 Data size: 366865 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_precision.q.out b/ql/src/test/results/clientpositive/vector_decimal_precision.q.out index e3e354f925..33bb6a7a47 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_precision.q.out @@ -567,7 +567,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_precision - Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 3584 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(20,10), 1:ROW__ID:struct] @@ -578,7 +578,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75 Data size: 3584 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(dec), count(dec) Group By Vectorization: @@ -590,7 +590,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -598,7 +598,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(30,10)), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -625,14 +625,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: decimal(38,18)), CAST( _col0 AS decimal(30,10)) (type: decimal(30,10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1152,7 +1152,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_precision_txt_small - Statistics: Num rows: 1 Data size: 26610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(20,10), 1:ROW__ID:struct] @@ -1163,7 +1163,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 1 Data size: 26610 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(dec), count(dec) Group By Vectorization: @@ -1175,7 +1175,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -1183,7 +1183,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(30,10)), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1210,14 +1210,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (_col0 / _col1) (type: decimal(38,18)), CAST( _col0 AS decimal(30,10)) (type: decimal(30,10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_round.q.out b/ql/src/test/results/clientpositive/vector_decimal_round.q.out index d690579de1..e67c5544b3 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_round.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_round.q.out @@ -50,7 +50,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_txt - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct] @@ -62,7 +62,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 2:decimal(10,0), decimalPlaces -1)(children: ConvertDecimal64ToDecimal(col 0:decimal(10,0)/DECIMAL_64) -> 2:decimal(10,0)) -> 3:decimal(11,0) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + @@ -71,7 +71,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(11,0)) Execution mode: vectorized Map Vectorization: @@ -97,10 +97,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -141,7 +141,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_txt - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct] @@ -153,7 +153,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 2:decimal(10,0), decimalPlaces -1)(children: ConvertDecimal64ToDecimal(col 0:decimal(10,0)/DECIMAL_64) -> 2:decimal(10,0)) -> 3:decimal(11,0) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: decimal(11,0)) sort order: + @@ -162,7 +162,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(10,0)) Execution mode: vectorized Map Vectorization: @@ -188,10 +188,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -260,7 +260,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_rc - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0), 1:ROW__ID:struct] @@ -272,7 +272,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 2] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(10,0), decimalPlaces -1) -> 2:decimal(11,0) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + @@ -281,7 +281,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(11,0)) Execution mode: vectorized Map Vectorization: @@ -307,10 +307,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -351,7 +351,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_rc - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0), 1:ROW__ID:struct] @@ -363,7 +363,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 2] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(10,0), decimalPlaces -1) -> 2:decimal(11,0) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: decimal(11,0)) sort order: + @@ -372,7 +372,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(10,0)) Execution mode: vectorized Map Vectorization: @@ -398,10 +398,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -470,7 +470,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_orc - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct] @@ -482,7 +482,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 2:decimal(10,0), decimalPlaces -1)(children: ConvertDecimal64ToDecimal(col 0:decimal(10,0)/DECIMAL_64) -> 2:decimal(10,0)) -> 3:decimal(11,0) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(10,0)) sort order: + @@ -491,7 +491,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(11,0)) Execution mode: vectorized Map Vectorization: @@ -517,10 +517,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -561,7 +561,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_orc - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct] @@ -573,7 +573,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 2:decimal(10,0), decimalPlaces -1)(children: ConvertDecimal64ToDecimal(col 0:decimal(10,0)/DECIMAL_64) -> 2:decimal(10,0)) -> 3:decimal(11,0) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: decimal(11,0)) sort order: + @@ -582,7 +582,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: decimal(10,0)) Execution mode: vectorized Map Vectorization: @@ -608,10 +608,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: decimal(10,0)), KEY.reducesinkkey0 (type: decimal(11,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out b/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out index 446fa3721a..f2402cddfa 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_round_2.q.out @@ -54,7 +54,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_1_orc - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(38,18), 1:ROW__ID:struct] @@ -66,7 +66,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14] selectExpressions: FuncRoundDecimalToDecimal(col 0:decimal(38,18)) -> 2:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 0) -> 3:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 1) -> 4:decimal(22,1), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 2) -> 5:decimal(23,2), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 3) -> 6:decimal(24,3), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -1) -> 7:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -2) -> 8:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -3) -> 9:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -4) -> 10:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -5) -> 11:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -6) -> 12:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -7) -> 13:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -8) -> 14:decimal(21,0) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(21,0)) sort order: + @@ -75,7 +75,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(21,0)), _col2 (type: decimal(22,1)), _col3 (type: decimal(23,2)), _col4 (type: decimal(24,3)), _col5 (type: decimal(21,0)), _col6 (type: decimal(21,0)), _col7 (type: decimal(21,0)), _col8 (type: decimal(21,0)), _col9 (type: decimal(21,0)), _col10 (type: decimal(21,0)), _col11 (type: decimal(21,0)), _col12 (type: decimal(21,0)) Execution mode: vectorized Map Vectorization: @@ -101,10 +101,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._col0 (type: decimal(21,0)), VALUE._col1 (type: decimal(22,1)), VALUE._col2 (type: decimal(23,2)), VALUE._col3 (type: decimal(24,3)), VALUE._col4 (type: decimal(21,0)), VALUE._col5 (type: decimal(21,0)), VALUE._col6 (type: decimal(21,0)), VALUE._col7 (type: decimal(21,0)), VALUE._col8 (type: decimal(21,0)), VALUE._col9 (type: decimal(21,0)), VALUE._col10 (type: decimal(21,0)), VALUE._col11 (type: decimal(21,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -196,7 +196,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_2_orc - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:pos:decimal(38,18), 1:neg:decimal(38,18), 2:ROW__ID:struct] @@ -208,7 +208,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22] selectExpressions: FuncRoundDecimalToDecimal(col 0:decimal(38,18)) -> 3:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 0) -> 4:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 1) -> 5:decimal(22,1), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 2) -> 6:decimal(23,2), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 3) -> 7:decimal(24,3), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 4) -> 8:decimal(25,4), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -1) -> 9:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -2) -> 10:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -3) -> 11:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -4) -> 12:decimal(21,0), FuncRoundDecimalToDecimal(col 1:decimal(38,18)) -> 13:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces 0) -> 14:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces 1) -> 15:decimal(22,1), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces 2) -> 16:decimal(23,2), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces 3) -> 17:decimal(24,3), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces 4) -> 18:decimal(25,4), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces -1) -> 19:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces -2) -> 20:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces -3) -> 21:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces -4) -> 22:decimal(21,0) - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(21,0)) sort order: + @@ -217,7 +217,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(21,0)), _col2 (type: decimal(22,1)), _col3 (type: decimal(23,2)), _col4 (type: decimal(24,3)), _col5 (type: decimal(25,4)), _col6 (type: decimal(21,0)), _col7 (type: decimal(21,0)), _col8 (type: decimal(21,0)), _col9 (type: decimal(21,0)), _col10 (type: decimal(21,0)), _col11 (type: decimal(21,0)), _col12 (type: decimal(22,1)), _col13 (type: decimal(23,2)), _col14 (type: decimal(24,3)), _col15 (type: decimal(25,4)), _col16 (type: decimal(21,0)), _col17 (type: decimal(21,0)), _col18 (type: decimal(21,0)), _col19 (type: decimal(21,0)) Execution mode: vectorized Map Vectorization: @@ -243,10 +243,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._col0 (type: decimal(21,0)), VALUE._col1 (type: decimal(22,1)), VALUE._col2 (type: decimal(23,2)), VALUE._col3 (type: decimal(24,3)), VALUE._col4 (type: decimal(25,4)), VALUE._col5 (type: decimal(21,0)), VALUE._col6 (type: decimal(21,0)), VALUE._col7 (type: decimal(21,0)), VALUE._col8 (type: decimal(21,0)), VALUE._col9 (type: decimal(21,0)), VALUE._col10 (type: decimal(21,0)), VALUE._col11 (type: decimal(22,1)), VALUE._col12 (type: decimal(23,2)), VALUE._col13 (type: decimal(24,3)), VALUE._col14 (type: decimal(25,4)), VALUE._col15 (type: decimal(21,0)), VALUE._col16 (type: decimal(21,0)), VALUE._col17 (type: decimal(21,0)), VALUE._col18 (type: decimal(21,0)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -365,7 +365,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_3_orc - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:dec:decimal(38,18), 1:ROW__ID:struct] @@ -377,7 +377,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -15) -> 2:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -16) -> 3:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -13) -> 4:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -14) -> 5:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -11) -> 6:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -12) -> 7:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -9) -> 8:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -10) -> 9:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -7) -> 10:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -8) -> 11:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -5) -> 12:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -6) -> 13:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -3) -> 14:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -4) -> 15:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -1) -> 16:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces -2) -> 17:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 0) -> 18:decimal(21,0), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 1) -> 19:decimal(22,1), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 2) -> 20:decimal(23,2), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 3) -> 21:decimal(24,3), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 4) -> 22:decimal(25,4), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 5) -> 23:decimal(26,5), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 6) -> 24:decimal(27,6), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 7) -> 25:decimal(28,7), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 8) -> 26:decimal(29,8), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 9) -> 27:decimal(30,9), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 10) -> 28:decimal(31,10), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 11) -> 29:decimal(32,11), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 12) -> 30:decimal(33,12), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 13) -> 31:decimal(34,13), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 14) -> 32:decimal(35,14), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 15) -> 33:decimal(36,15), FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 16) -> 34:decimal(37,16) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3808 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(21,0)) sort order: + @@ -386,7 +386,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3808 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(21,0)), _col2 (type: decimal(21,0)), _col3 (type: decimal(21,0)), _col4 (type: decimal(21,0)), _col5 (type: decimal(21,0)), _col6 (type: decimal(21,0)), _col7 (type: decimal(21,0)), _col8 (type: decimal(21,0)), _col9 (type: decimal(21,0)), _col10 (type: decimal(21,0)), _col11 (type: decimal(21,0)), _col12 (type: decimal(21,0)), _col13 (type: decimal(21,0)), _col14 (type: decimal(21,0)), _col15 (type: decimal(21,0)), _col16 (type: decimal(21,0)), _col17 (type: decimal(22,1)), _col18 (type: decimal(23,2)), _col19 (type: decimal(24,3)), _col20 (type: decimal(25,4)), _col21 (type: decimal(26,5)), _col22 (type: decimal(27,6)), _col23 (type: decimal(28,7)), _col24 (type: decimal(29,8)), _col25 (type: decimal(30,9)), _col26 (type: decimal(31,10)), _col27 (type: decimal(32,11)), _col28 (type: decimal(33,12)), _col29 (type: decimal(34,13)), _col31 (type: decimal(35,14)), _col32 (type: decimal(36,15)), _col33 (type: decimal(37,16)) Execution mode: vectorized Map Vectorization: @@ -412,10 +412,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(21,0)), VALUE._col0 (type: decimal(21,0)), VALUE._col1 (type: decimal(21,0)), VALUE._col2 (type: decimal(21,0)), VALUE._col3 (type: decimal(21,0)), VALUE._col4 (type: decimal(21,0)), VALUE._col5 (type: decimal(21,0)), VALUE._col6 (type: decimal(21,0)), VALUE._col7 (type: decimal(21,0)), VALUE._col8 (type: decimal(21,0)), VALUE._col9 (type: decimal(21,0)), VALUE._col10 (type: decimal(21,0)), VALUE._col11 (type: decimal(21,0)), VALUE._col12 (type: decimal(21,0)), VALUE._col13 (type: decimal(21,0)), VALUE._col14 (type: decimal(21,0)), VALUE._col15 (type: decimal(21,0)), VALUE._col16 (type: decimal(22,1)), VALUE._col17 (type: decimal(23,2)), VALUE._col18 (type: decimal(24,3)), VALUE._col19 (type: decimal(25,4)), VALUE._col20 (type: decimal(26,5)), VALUE._col21 (type: decimal(27,6)), VALUE._col22 (type: decimal(28,7)), VALUE._col23 (type: decimal(29,8)), VALUE._col24 (type: decimal(30,9)), VALUE._col25 (type: decimal(31,10)), VALUE._col26 (type: decimal(32,11)), VALUE._col27 (type: decimal(33,12)), VALUE._col28 (type: decimal(34,13)), VALUE._col28 (type: decimal(34,13)), VALUE._col29 (type: decimal(35,14)), VALUE._col30 (type: decimal(36,15)), VALUE._col31 (type: decimal(37,16)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3808 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 3808 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -523,7 +523,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_tbl_4_orc - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:pos:decimal(38,18), 1:neg:decimal(38,18), 2:ROW__ID:struct] @@ -535,7 +535,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4] selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(38,18), decimalPlaces 9) -> 3:decimal(30,9), FuncRoundWithNumDigitsDecimalToDecimal(col 1:decimal(38,18), decimalPlaces 9) -> 4:decimal(30,9) - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(30,9)) sort order: + @@ -544,7 +544,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(30,9)) Execution mode: vectorized Map Vectorization: @@ -570,10 +570,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(30,9)), VALUE._col0 (type: decimal(30,9)), 1809242.315111134 (type: decimal(17,9)), -1809242.315111134 (type: decimal(17,9)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_trailing.q.out b/ql/src/test/results/clientpositive/vector_decimal_trailing.q.out index f25b0b24c9..f15b455e3b 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_trailing.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_trailing.q.out @@ -85,7 +85,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: decimal_trailing - Statistics: Num rows: 30 Data size: 4712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 4936 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:id:int, 1:a:decimal(10,4)/DECIMAL_64, 2:b:decimal(15,8)/DECIMAL_64, 3:ROW__ID:struct] @@ -96,7 +96,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 30 Data size: 4712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 4936 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -105,7 +105,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 30 Data size: 4712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 4936 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(10,4)), _col2 (type: decimal(15,8)) Execution mode: vectorized Map Vectorization: @@ -131,10 +131,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: decimal(10,4)), VALUE._col1 (type: decimal(15,8)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 4712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 4936 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 30 Data size: 4712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 4936 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out b/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out index f8b7e4ab54..ccce3435f8 100644 --- a/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out +++ b/ql/src/test/results/clientpositive/vector_decimal_udf2.q.out @@ -81,7 +81,7 @@ STAGE PLANS: TableScan alias: decimal_udf2_n0 filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 39 Data size: 4072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 4032 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:decimal(14,5)/DECIMAL_64, 1:value:int, 2:ROW__ID:struct] @@ -91,7 +91,7 @@ STAGE PLANS: native: true predicateExpression: FilterDecimal64ColEqualDecimal64Scalar(col 0:decimal(14,5)/DECIMAL_64, val 1000000) predicate: (key = 10) (type: boolean) - Statistics: Num rows: 19 Data size: 1983 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: double), null (type: double), 1.4711276743037347D (type: double), -0.8390715290764524D (type: double), -0.5440211108893698D (type: double), 0.6483608274590866D (type: double), 0.17453292519943295D (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -100,13 +100,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4, 5, 6, 7, 8, 9] selectExpressions: ConstantVectorExpression(val null) -> 3:double, ConstantVectorExpression(val null) -> 4:double, ConstantVectorExpression(val 1.4711276743037347) -> 5:double, ConstantVectorExpression(val -0.8390715290764524) -> 6:double, ConstantVectorExpression(val -0.5440211108893698) -> 7:double, ConstantVectorExpression(val 0.6483608274590866) -> 8:double, ConstantVectorExpression(val 0.17453292519943295) -> 9:double - Statistics: Num rows: 19 Data size: 1983 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 19 Data size: 1983 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -187,7 +187,7 @@ STAGE PLANS: TableScan alias: decimal_udf2_n0 filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 39 Data size: 4072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:decimal(14,5)/DECIMAL_64, 1:value:int, 2:ROW__ID:struct] @@ -197,7 +197,7 @@ STAGE PLANS: native: true predicateExpression: FilterDecimal64ColEqualDecimal64Scalar(col 0:decimal(14,5)/DECIMAL_64, val 1000000) predicate: (key = 10) (type: boolean) - Statistics: Num rows: 19 Data size: 1983 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 22026.465794806718D (type: double), 2.302585092994046D (type: double), 2.302585092994046D (type: double), 1.0D (type: double), log(10, value) (type: double), log(value, 10) (type: double), 1.0D (type: double), 3.1622776601683795D (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 @@ -206,13 +206,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4, 5, 6, 7, 8, 9, 10] selectExpressions: ConstantVectorExpression(val 22026.465794806718) -> 3:double, ConstantVectorExpression(val 2.302585092994046) -> 4:double, ConstantVectorExpression(val 2.302585092994046) -> 5:double, ConstantVectorExpression(val 1.0) -> 6:double, FuncLogWithBaseLongToDouble(col 1:double) -> 7:double, VectorUDFAdaptor(log(value, 10)) -> 8:double, ConstantVectorExpression(val 1.0) -> 9:double, ConstantVectorExpression(val 3.1622776601683795) -> 10:double - Statistics: Num rows: 19 Data size: 1983 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 19 Data size: 1983 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -299,7 +299,7 @@ STAGE PLANS: TableScan alias: decimal_udf2_txt filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:decimal(14,5)/DECIMAL_64, 1:value:int, 2:ROW__ID:struct] @@ -309,7 +309,7 @@ STAGE PLANS: native: true predicateExpression: FilterDecimal64ColEqualDecimal64Scalar(col 0:decimal(14,5)/DECIMAL_64, val 1000000) predicate: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: double), null (type: double), 1.4711276743037347D (type: double), -0.8390715290764524D (type: double), -0.5440211108893698D (type: double), 0.6483608274590866D (type: double), 0.17453292519943295D (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -318,13 +318,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4, 5, 6, 7, 8, 9] selectExpressions: ConstantVectorExpression(val null) -> 3:double, ConstantVectorExpression(val null) -> 4:double, ConstantVectorExpression(val 1.4711276743037347) -> 5:double, ConstantVectorExpression(val -0.8390715290764524) -> 6:double, ConstantVectorExpression(val -0.5440211108893698) -> 7:double, ConstantVectorExpression(val 0.6483608274590866) -> 8:double, ConstantVectorExpression(val 0.17453292519943295) -> 9:double - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -405,7 +405,7 @@ STAGE PLANS: TableScan alias: decimal_udf2_txt filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:decimal(14,5)/DECIMAL_64, 1:value:int, 2:ROW__ID:struct] @@ -415,7 +415,7 @@ STAGE PLANS: native: true predicateExpression: FilterDecimal64ColEqualDecimal64Scalar(col 0:decimal(14,5)/DECIMAL_64, val 1000000) predicate: (key = 10) (type: boolean) - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 22026.465794806718D (type: double), 2.302585092994046D (type: double), 2.302585092994046D (type: double), 1.0D (type: double), log(10, value) (type: double), log(value, 10) (type: double), 1.0D (type: double), 3.1622776601683795D (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 @@ -424,13 +424,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 4, 5, 6, 7, 8, 9, 10] selectExpressions: ConstantVectorExpression(val 22026.465794806718) -> 3:double, ConstantVectorExpression(val 2.302585092994046) -> 4:double, ConstantVectorExpression(val 2.302585092994046) -> 5:double, ConstantVectorExpression(val 1.0) -> 6:double, FuncLogWithBaseLongToDouble(col 1:double) -> 7:double, VectorUDFAdaptor(log(value, 10)) -> 8:double, ConstantVectorExpression(val 1.0) -> 9:double, ConstantVectorExpression(val 3.1622776601683795) -> 10:double - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 3590 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/vector_distinct_2.q.out index 8eefb3d95a..9f84de5b28 100644 --- a/ql/src/test/results/clientpositive/vector_distinct_2.q.out +++ b/ql/src/test/results/clientpositive/vector_distinct_2.q.out @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n3 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -131,7 +131,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 8] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -143,7 +143,7 @@ STAGE PLANS: keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ @@ -153,7 +153,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -173,14 +173,14 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178694 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178694 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 178694 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_elt.q.out b/ql/src/test/results/clientpositive/vector_elt.q.out index 9d83698e80..a5b001a6b1 100644 --- a/ql/src/test/results/clientpositive/vector_elt.q.out +++ b/ql/src/test/results/clientpositive/vector_elt.q.out @@ -21,7 +21,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (ctinyint > 0Y) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 935842 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -30,7 +30,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:tinyint, val 0) predicate: (ctinyint > 0Y) (type: boolean) - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 312018 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((UDFToInteger(ctinyint) % 2) + 1) (type: int), cstring1 (type: string), cint (type: int), elt(((UDFToInteger(ctinyint) % 2) + 1), cstring1, cint) (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -39,19 +39,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [14, 6, 2, 17] selectExpressions: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 14:int, VectorElt(columns [15, 6, 16])(children: LongColAddLongScalar(col 13:int, val 1)(children: LongColModuloLongScalar(col 0:int, val 2)(children: col 0:tinyint) -> 13:int) -> 15:int, col 6:string, CastLongToString(col 2:int) -> 16:string) -> 17:string - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1069830 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2664 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 2664 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_empty_where.q.out b/ql/src/test/results/clientpositive/vector_empty_where.q.out index 388b775d8a..4b65b60db4 100644 --- a/ql/src/test/results/clientpositive/vector_empty_where.q.out +++ b/ql/src/test/results/clientpositive/vector_empty_where.q.out @@ -19,7 +19,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 899146 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -28,7 +28,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastStringToBoolean(col 6) -> 13:boolean) predicate: cstring1 (type: string) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 449620 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: cint @@ -36,7 +36,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2] - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 449620 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -48,7 +48,7 @@ STAGE PLANS: keys: cint (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -58,7 +58,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -78,12 +78,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -104,7 +104,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -125,10 +125,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -170,7 +170,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -179,7 +179,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastLongToBooleanViaLongToLong(col 2:int) -> 13:boolean) predicate: cint (type: int) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 18348 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -191,7 +191,7 @@ STAGE PLANS: keys: cint (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3053 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -201,7 +201,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3053 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -221,12 +221,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3053 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -247,7 +247,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -268,10 +268,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -313,7 +313,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -322,7 +322,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastDoubleToBooleanViaDoubleToLong(col 4:float) -> 13:boolean) predicate: cfloat (type: float) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: cint @@ -330,7 +330,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2] - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -342,7 +342,7 @@ STAGE PLANS: keys: cint (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -352,7 +352,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -372,12 +372,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -398,7 +398,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -419,10 +419,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -464,7 +464,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 528216 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -473,7 +473,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsTrue(col 13:boolean)(children: CastTimestampToBoolean(col 8:timestamp) -> 13:boolean) predicate: ctimestamp1 (type: timestamp) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 264108 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: cint @@ -481,7 +481,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2] - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 264108 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -493,7 +493,7 @@ STAGE PLANS: keys: cint (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -503,7 +503,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -523,12 +523,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 9176 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) mode: partial2 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -549,7 +549,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -570,10 +570,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_gather_stats.q.out b/ql/src/test/results/clientpositive/vector_gather_stats.q.out index 0c873836e3..77ce7d594f 100644 --- a/ql/src/test/results/clientpositive/vector_gather_stats.q.out +++ b/ql/src/test/results/clientpositive/vector_gather_stats.q.out @@ -77,7 +77,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cd - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE Map Vectorization: enabled: true enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true diff --git a/ql/src/test/results/clientpositive/vector_groupby4.q.out b/ql/src/test/results/clientpositive/vector_groupby4.q.out index 15b0427308..39382a2940 100644 --- a/ql/src/test/results/clientpositive/vector_groupby4.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby4.q.out @@ -44,7 +44,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcorc_n1 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -55,7 +55,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3] selectExpressions: StringSubstrColStartLen(col 0:string, start 0, length 1) -> 3:string - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -65,7 +65,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -85,7 +85,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -108,7 +108,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -128,10 +128,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -140,7 +140,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -180,7 +180,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE value expressions: c1 (type: string) Execution mode: vectorized Map Vectorization: @@ -201,7 +201,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll') mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -222,7 +222,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct) Execution mode: vectorized Map Vectorization: @@ -243,10 +243,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_groupby6.q.out b/ql/src/test/results/clientpositive/vector_groupby6.q.out index 31472a1ea9..0d1f3cc874 100644 --- a/ql/src/test/results/clientpositive/vector_groupby6.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby6.q.out @@ -44,7 +44,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcorc_n0 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -55,7 +55,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3] selectExpressions: StringSubstrColStartLen(col 1:string, start 4, length 1) -> 3:string - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -65,7 +65,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -85,7 +85,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -108,7 +108,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -128,10 +128,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -140,7 +140,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string) outputColumnNames: c1 - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -180,7 +180,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE value expressions: c1 (type: string) Execution mode: vectorized Map Vectorization: @@ -201,7 +201,7 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0, 'hll') mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -222,7 +222,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: struct) Execution mode: vectorized Map Vectorization: @@ -243,10 +243,10 @@ STAGE PLANS: aggregations: compute_stats(VALUE._col0) mode: final outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/vector_groupby_3.q.out index 173f84f43c..5aed984504 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_3.q.out @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n8 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -131,7 +131,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 3, 8] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(b) Group By Vectorization: @@ -145,7 +145,7 @@ STAGE PLANS: keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ @@ -155,7 +155,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -177,14 +177,14 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 186298 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: tinyint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 186298 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 186298 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out index 4be127283b..efad290eb4 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out @@ -35,7 +35,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -45,7 +45,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), count(key) Group By Vectorization: @@ -57,7 +57,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -65,7 +65,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -86,7 +86,7 @@ STAGE PLANS: aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -104,11 +104,11 @@ STAGE PLANS: $hdt$_0:src TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 @@ -133,7 +133,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 13812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: @@ -193,14 +193,14 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator Filter Vectorization: className: VectorFilterOperator native: true predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 2:bigint, val 0), FilterExprAndExpr(children: SelectColumnIsNull(col 4:boolean), SelectColumnIsNotNull(col 0:string), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 2:bigint))) predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -208,7 +208,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: @@ -245,7 +245,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map Vectorization: @@ -265,10 +265,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -282,14 +282,14 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 13812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint), _col3 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean) Reduce Operator Tree: Join Operator @@ -299,14 +299,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -319,7 +319,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -329,7 +329,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -341,7 +341,7 @@ STAGE PLANS: keys: key (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -351,7 +351,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -371,11 +371,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), true (type: boolean) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out index 3e1c5b6e1f..cc61c6fbfe 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out @@ -249,7 +249,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_sales_n3 - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -259,7 +259,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [9] - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -271,7 +271,7 @@ STAGE PLANS: keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -281,7 +281,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -302,7 +302,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -324,7 +324,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -344,13 +344,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4820 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4820 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,7 +441,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_sales_n3 - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -451,7 +451,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [9] - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -463,7 +463,7 @@ STAGE PLANS: keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -473,7 +473,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -493,17 +493,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col0) keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -525,7 +525,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -544,10 +544,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 85 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -709,7 +709,7 @@ STAGE PLANS: TableScan alias: store_sales_n3 filterExpr: (ss_ticket_number = 1) (type: boolean) - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 126616 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -718,7 +718,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColEqualLongScalar(col 9:int, val 1) predicate: (ss_ticket_number = 1) (type: boolean) - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_item_sk (type: int), ss_quantity (type: int), ss_wholesale_cost_decimal (type: decimal(38,18)), ss_net_profit (type: double) outputColumnNames: ss_item_sk, ss_quantity, ss_wholesale_cost_decimal, ss_net_profit @@ -726,7 +726,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 10, 12, 23] - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1584 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(ss_quantity), max(ss_net_profit), max(ss_wholesale_cost_decimal) Group By Vectorization: @@ -740,7 +740,7 @@ STAGE PLANS: keys: ss_item_sk (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -750,7 +750,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: double), _col3 (type: decimal(38,18)) Execution mode: vectorized Map Vectorization: @@ -772,17 +772,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: double), _col3 (type: decimal(38,18)) outputColumnNames: _col1, _col2, _col3, _col4 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 768 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), sum(_col2), count(_col2), sum(_col3), count(_col3), sum(_col4), count(_col4) keys: 1 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -805,7 +805,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: double), _col5 (type: bigint), _col6 (type: decimal(38,18)), _col7 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -827,14 +827,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 125 Data size: 30150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 1 (type: int), _col1 (type: bigint), _col2 (type: bigint), (UDFToDouble(_col2) / _col3) (type: double), _col4 (type: double), (_col4 / _col5) (type: double), _col6 (type: decimal(38,18)), (_col6 / _col7) (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 125 Data size: 30150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 125 Data size: 30150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -914,7 +914,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_sales_n3 - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 126616 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -924,7 +924,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 9, 10, 12, 23] - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 126616 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(ss_quantity), max(ss_net_profit), max(ss_wholesale_cost_decimal) Group By Vectorization: @@ -938,7 +938,7 @@ STAGE PLANS: keys: ss_ticket_number (type: int), ss_item_sk (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 66000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ @@ -948,7 +948,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1000 Data size: 241204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 66000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: int), _col3 (type: double), _col4 (type: decimal(38,18)) Execution mode: vectorized Map Vectorization: @@ -970,21 +970,21 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 66000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), _col2 (type: int), _col3 (type: double), _col4 (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 500 Data size: 120602 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 66000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2), sum(_col3), count(_col3), sum(_col4), count(_col4) keys: _col1 (type: int), _col0 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 80000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), (UDFToDouble(_col2) / _col3) (type: double), _col4 (type: double), (_col4 / _col5) (type: double), _col6 (type: decimal(38,18)), (_col6 / _col7) (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -1006,7 +1006,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: decimal(38,18)), _col7 (type: decimal(38,18)) Execution mode: vectorized Map Vectorization: @@ -1026,10 +1026,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: decimal(38,18)), VALUE._col5 (type: decimal(38,18)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 60301 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 132000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_grouping_sets.q.out b/ql/src/test/results/clientpositive/vector_grouping_sets.q.out index 5113966b8a..5b808615dc 100644 --- a/ql/src/test/results/clientpositive/vector_grouping_sets.q.out +++ b/ql/src/test/results/clientpositive/vector_grouping_sets.q.out @@ -147,7 +147,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_n1 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -157,7 +157,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -169,7 +169,7 @@ STAGE PLANS: keys: s_store_id (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ @@ -179,7 +179,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -199,11 +199,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -258,7 +258,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_n1 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -268,7 +268,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -280,7 +280,7 @@ STAGE PLANS: keys: _col0 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ @@ -290,7 +290,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -310,14 +310,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -368,35 +368,35 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_n1 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) - Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_if_expr.q.out b/ql/src/test/results/clientpositive/vector_if_expr.q.out index 7e7594975a..b9cfc0a49f 100644 --- a/ql/src/test/results/clientpositive/vector_if_expr.q.out +++ b/ql/src/test/results/clientpositive/vector_if_expr.q.out @@ -19,7 +19,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (cboolean1 and cboolean1 is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -28,7 +28,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsTrue(col 10:boolean), SelectColumnIsNotNull(col 10:boolean)) predicate: (cboolean1 and cboolean1 is not null) (type: boolean) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4587 Data size: 13704 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), if(cboolean1, 'first', 'second') (type: string) outputColumnNames: _col0, _col1 @@ -37,7 +37,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 13] selectExpressions: IfExprStringScalarStringScalar(col 10:boolean, val first, val second) -> 13:string - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -46,7 +46,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized Map Vectorization: @@ -66,10 +66,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4587 Data size: 857712 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_include_no_sel.q.out b/ql/src/test/results/clientpositive/vector_include_no_sel.q.out index 0ecc7af27b..9f54006c03 100644 --- a/ql/src/test/results/clientpositive/vector_include_no_sel.q.out +++ b/ql/src/test/results/clientpositive/vector_include_no_sel.q.out @@ -193,7 +193,7 @@ STAGE PLANS: customer_demographics TableScan alias: customer_demographics - Statistics: Num rows: 200 Data size: 74200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 35908 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 @@ -204,7 +204,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: store_sales_n1 - Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 3804 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Map Join Operator @@ -220,20 +220,20 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col2, _col16 - Statistics: Num rows: 200000 Data size: 92055200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200000 Data size: 36868800 Basic stats: COMPLETE Column stats: NONE Filter Operator Filter Vectorization: className: VectorFilterOperator native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColEqualLongColumn(col 0:int, col 2:int), FilterStringGroupColEqualStringScalar(col 1:string, val M)), FilterExprAndExpr(children: FilterLongColEqualLongColumn(col 0:int, col 2:int), FilterStringGroupColEqualStringScalar(col 1:string, val U))) predicate: (((_col0 = _col16) and (_col2 = 'M')) or ((_col0 = _col16) and (_col2 = 'U'))) (type: boolean) - Statistics: Num rows: 100000 Data size: 46027600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100000 Data size: 18434400 Basic stats: COMPLETE Column stats: NONE Select Operator Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumnNums: [] - Statistics: Num rows: 100000 Data size: 46027600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100000 Data size: 18434400 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/vector_interval_1.q.out b/ql/src/test/results/clientpositive/vector_interval_1.q.out index 9a2a18acf4..ea6f210105 100644 --- a/ql/src/test/results/clientpositive/vector_interval_1.q.out +++ b/ql/src/test/results/clientpositive/vector_interval_1.q.out @@ -80,7 +80,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -91,7 +91,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 5, 6] selectExpressions: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month, CastStringToIntervalDayTime(col 3:string) -> 6:interval_day_time - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -100,7 +100,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: interval_year_month), _col2 (type: interval_day_time) Execution mode: vectorized Map Vectorization: @@ -120,10 +120,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), INTERVAL'1-2' (type: interval_year_month), VALUE._col0 (type: interval_year_month), INTERVAL'1 02:03:04.000000000' (type: interval_day_time), VALUE._col1 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -191,7 +191,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -202,7 +202,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 7, 6, 9, 8] selectExpressions: IntervalYearMonthColAddIntervalYearMonthColumn(col 5:interval_year_month, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 7:interval_year_month, IntervalYearMonthScalarAddIntervalYearMonthColumn(val 14, col 5:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month) -> 6:interval_year_month, IntervalYearMonthColSubtractIntervalYearMonthColumn(col 5:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:interval_year_month, IntervalYearMonthScalarSubtractIntervalYearMonthColumn(val 14, col 5:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month) -> 8:interval_year_month - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -211,7 +211,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: interval_year_month), _col2 (type: interval_year_month), _col3 (type: interval_year_month), _col4 (type: interval_year_month) Execution mode: vectorized Map Vectorization: @@ -231,10 +231,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), INTERVAL'2-4' (type: interval_year_month), VALUE._col0 (type: interval_year_month), VALUE._col1 (type: interval_year_month), INTERVAL'0-0' (type: interval_year_month), VALUE._col2 (type: interval_year_month), VALUE._col3 (type: interval_year_month) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -310,7 +310,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -321,7 +321,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 7, 6, 9, 8] selectExpressions: IntervalDayTimeColAddIntervalDayTimeColumn(col 5:interval_day_time, col 6:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time, CastStringToIntervalDayTime(col 3:string) -> 6:interval_day_time) -> 7:interval_day_time, IntervalDayTimeScalarAddIntervalDayTimeColumn(val 1 02:03:04.000000000, col 5:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time) -> 6:interval_day_time, IntervalDayTimeColSubtractIntervalDayTimeColumn(col 5:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time, CastStringToIntervalDayTime(col 3:string) -> 8:interval_day_time) -> 9:interval_day_time, IntervalDayTimeScalarSubtractIntervalDayTimeColumn(val 1 02:03:04.000000000, col 5:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time) -> 8:interval_day_time - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -330,7 +330,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time) Execution mode: vectorized Map Vectorization: @@ -350,10 +350,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), INTERVAL'2 04:06:08.000000000' (type: interval_day_time), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), INTERVAL'0 00:00:00.000000000' (type: interval_day_time), VALUE._col2 (type: interval_day_time), VALUE._col3 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -441,7 +441,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -452,7 +452,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 5, 7, 6, 9, 8, 11, 12, 14, 15, 16, 17, 18] selectExpressions: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 5:date, DateColAddIntervalYearMonthColumn(col 1:date, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 7:date, IntervalYearMonthScalarAddDateColumn(val 1-2, col 1:interval_year_month) -> 6:date, IntervalYearMonthColAddDateColumn(col 8:interval_year_month, col 1:date)(children: CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:date, DateColSubtractIntervalYearMonthScalar(col 1:date, val 1-2) -> 8:date, DateColSubtractIntervalYearMonthColumn(col 1:date, col 10:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 10:interval_year_month) -> 11:date, DateColAddIntervalDayTimeScalar(col 1:date, val 1 02:03:04.000000000) -> 12:timestamp, DateColAddIntervalDayTimeColumn(col 1:date, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 14:timestamp, IntervalDayTimeScalarAddDateColumn(val 1 02:03:04.000000000, col 1:date) -> 15:timestamp, IntervalDayTimeColAddDateColumn(col 13:interval_day_time, col 1:date)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 16:timestamp, DateColSubtractIntervalDayTimeScalar(col 1:date, val 1 02:03:04.000000000) -> 17:timestamp, DateColSubtractIntervalDayTimeColumn(col 1:date, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 18:timestamp - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -461,7 +461,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: date), _col2 (type: date), _col3 (type: date), _col4 (type: date), _col5 (type: date), _col6 (type: date), _col7 (type: timestamp), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: timestamp), _col11 (type: timestamp), _col12 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -481,10 +481,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: date), VALUE._col2 (type: date), VALUE._col3 (type: date), VALUE._col4 (type: date), VALUE._col5 (type: date), VALUE._col6 (type: timestamp), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: timestamp), VALUE._col11 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -584,7 +584,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -595,7 +595,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 5, 7, 8, 9, 10, 11, 12, 14, 15, 16, 17, 18] selectExpressions: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 5:timestamp, TimestampColAddIntervalYearMonthColumn(col 0:timestamp, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 7:timestamp, IntervalYearMonthScalarAddTimestampColumn(val 1-2, col 0:interval_year_month) -> 8:timestamp, IntervalYearMonthColAddTimestampColumn(col 6:interval_year_month, col 0:timestamp)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 9:timestamp, TimestampColSubtractIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 10:timestamp, TimestampColSubtractIntervalYearMonthColumn(col 0:timestamp, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 11:timestamp, TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 02:03:04.000000000) -> 12:timestamp, TimestampColAddIntervalDayTimeColumn(col 0:timestamp, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 14:timestamp, IntervalDayTimeScalarAddTimestampColumn(val 1 02:03:04.000000000, col 0:timestamp) -> 15:timestamp, IntervalDayTimeColAddTimestampColumn(col 13:interval_day_time, col 0:timestamp)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 16:timestamp, TimestampColSubtractIntervalDayTimeScalar(col 0:timestamp, val 1 02:03:04.000000000) -> 17:timestamp, TimestampColSubtractIntervalDayTimeColumn(col 0:timestamp, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 18:timestamp - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp) sort order: + @@ -604,7 +604,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp), _col7 (type: timestamp), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: timestamp), _col11 (type: timestamp), _col12 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -624,10 +624,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: timestamp), VALUE._col11 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -709,7 +709,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -720,7 +720,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 5, 6, 7] selectExpressions: TimestampColSubtractTimestampColumn(col 0:timestamp, col 0:timestamp) -> 5:interval_day_time, TimestampScalarSubtractTimestampColumn(val 2001-01-01 01:02:03, col 0:timestamp) -> 6:interval_day_time, TimestampColSubtractTimestampScalar(col 0:timestamp, val 2001-01-01 01:02:03) -> 7:interval_day_time - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp) sort order: + @@ -729,7 +729,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time) Execution mode: vectorized Map Vectorization: @@ -749,10 +749,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -816,7 +816,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -827,7 +827,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 5, 6, 7] selectExpressions: DateColSubtractDateColumn(col 1:date, col 1:date) -> 5:interval_day_time, DateScalarSubtractDateColumn(val 2001-01-01, col 1:date) -> 6:interval_day_time, DateColSubtractDateScalar(col 1:date, val 2001-01-01) -> 7:interval_day_time - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -836,7 +836,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time) Execution mode: vectorized Map Vectorization: @@ -856,10 +856,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -929,7 +929,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vector_interval_1 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -940,7 +940,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 5, 6, 7, 8, 9, 10] selectExpressions: TimestampColSubtractDateColumn(col 0:timestamp, col 1:date) -> 5:interval_day_time, TimestampScalarSubtractDateColumn(val 2001-01-01 01:02:03, col 1:date) -> 6:interval_day_time, TimestampColSubtractDateScalar(col 0:timestamp, val 2001-01-01) -> 7:interval_day_time, DateColSubtractTimestampColumn(col 1:date, col 0:timestamp) -> 8:interval_day_time, DateColSubtractTimestampScalar(col 1:date, val 2001-01-01 01:02:03) -> 9:interval_day_time, DateScalarSubtractTimestampColumn(val 2001-01-01, col 0:timestamp) -> 10:interval_day_time - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -949,7 +949,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time), _col5 (type: interval_day_time), _col6 (type: interval_day_time) Execution mode: vectorized Map Vectorization: @@ -969,10 +969,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time), VALUE._col3 (type: interval_day_time), VALUE._col4 (type: interval_day_time), VALUE._col5 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 274 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out b/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out index 3b398cb595..7dac2a3cde 100644 --- a/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out +++ b/ql/src/test/results/clientpositive/vector_interval_arithmetic.q.out @@ -74,7 +74,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -85,7 +85,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8] selectExpressions: DateColSubtractIntervalYearMonthScalar(col 0:date, val 2-2) -> 3:date, DateColSubtractIntervalYearMonthScalar(col 0:date, val -2-2) -> 4:date, DateColAddIntervalYearMonthScalar(col 0:date, val 2-2) -> 5:date, DateColAddIntervalYearMonthScalar(col 0:date, val -2-2) -> 6:date, IntervalYearMonthScalarAddDateColumn(val -2-2, col 0:interval_year_month) -> 7:date, IntervalYearMonthScalarAddDateColumn(val 2-2, col 0:interval_year_month) -> 8:date - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -94,7 +94,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: date), _col2 (type: date), _col3 (type: date), _col4 (type: date), _col5 (type: date), _col6 (type: date) Execution mode: vectorized Map Vectorization: @@ -114,10 +114,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: date), VALUE._col2 (type: date), VALUE._col3 (type: date), VALUE._col4 (type: date), VALUE._col5 (type: date) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -239,7 +239,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -250,7 +250,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3, 4, 5] selectExpressions: DateColSubtractDateScalar(col 0:date, val 1999-06-07) -> 3:interval_day_time, DateScalarSubtractDateColumn(val 1999-06-07, col 0:date) -> 4:interval_day_time, DateColSubtractDateColumn(col 0:date, col 0:date) -> 5:interval_day_time - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -259,7 +259,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time) Execution mode: vectorized Map Vectorization: @@ -279,10 +279,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: interval_day_time), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -404,7 +404,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -415,7 +415,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3, 4, 5, 6, 7, 8] selectExpressions: TimestampColSubtractIntervalYearMonthScalar(col 1:timestamp, val 2-2) -> 3:timestamp, TimestampColSubtractIntervalYearMonthScalar(col 1:timestamp, val -2-2) -> 4:timestamp, TimestampColAddIntervalYearMonthScalar(col 1:timestamp, val 2-2) -> 5:timestamp, TimestampColAddIntervalYearMonthScalar(col 1:timestamp, val -2-2) -> 6:timestamp, IntervalYearMonthScalarAddTimestampColumn(val -2-2, col 1:interval_year_month) -> 7:timestamp, IntervalYearMonthScalarAddTimestampColumn(val 2-2, col 1:interval_year_month) -> 8:timestamp - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp) sort order: + @@ -424,7 +424,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -444,10 +444,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -672,7 +672,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -683,7 +683,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8] selectExpressions: DateColSubtractIntervalDayTimeScalar(col 0:date, val 99 11:22:33.123456789) -> 3:timestamp, DateColSubtractIntervalDayTimeScalar(col 0:date, val -99 11:22:33.123456789) -> 4:timestamp, DateColAddIntervalDayTimeScalar(col 0:date, val 99 11:22:33.123456789) -> 5:timestamp, DateColAddIntervalDayTimeScalar(col 0:date, val -99 11:22:33.123456789) -> 6:timestamp, IntervalDayTimeScalarAddDateColumn(val -99 11:22:33.123456789, col 0:date) -> 7:timestamp, IntervalDayTimeScalarAddDateColumn(val 99 11:22:33.123456789, col 0:date) -> 8:timestamp - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -692,7 +692,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -712,10 +712,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -839,7 +839,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -850,7 +850,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 3, 4, 5] selectExpressions: DateColSubtractTimestampColumn(col 0:date, col 1:timestamp) -> 3:interval_day_time, TimestampColSubtractDateColumn(col 1:timestamp, col 0:date) -> 4:interval_day_time, TimestampColSubtractTimestampColumn(col 1:timestamp, col 1:timestamp) -> 5:interval_day_time - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: date) sort order: + @@ -859,7 +859,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: timestamp), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time) Execution mode: vectorized Map Vectorization: @@ -879,10 +879,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: timestamp), VALUE._col1 (type: interval_day_time), VALUE._col2 (type: interval_day_time), VALUE._col3 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1006,7 +1006,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: interval_arithmetic_1 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -1017,7 +1017,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3, 4, 5, 6, 7, 8] selectExpressions: TimestampColSubtractIntervalDayTimeScalar(col 1:timestamp, val 99 11:22:33.123456789) -> 3:timestamp, TimestampColSubtractIntervalDayTimeScalar(col 1:timestamp, val -99 11:22:33.123456789) -> 4:timestamp, TimestampColAddIntervalDayTimeScalar(col 1:timestamp, val 99 11:22:33.123456789) -> 5:timestamp, TimestampColAddIntervalDayTimeScalar(col 1:timestamp, val -99 11:22:33.123456789) -> 6:timestamp, IntervalDayTimeScalarAddTimestampColumn(val -99 11:22:33.123456789, col 1:timestamp) -> 7:timestamp, IntervalDayTimeScalarAddTimestampColumn(val 99 11:22:33.123456789, col 1:timestamp) -> 8:timestamp - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: timestamp) sort order: + @@ -1026,7 +1026,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -1046,10 +1046,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col0 (type: timestamp), VALUE._col1 (type: timestamp), VALUE._col2 (type: timestamp), VALUE._col3 (type: timestamp), VALUE._col4 (type: timestamp), VALUE._col5 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out index 1c4692c603..872b7ba10e 100644 --- a/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out @@ -201,14 +201,14 @@ STAGE PLANS: TableScan alias: vectortab_b_1korc filterExpr: (dt is not null and ts is not null and s is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 266280 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (dt is not null and s is not null and ts is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string), _col1 (type: interval_day_time) @@ -220,7 +220,7 @@ STAGE PLANS: TableScan alias: vectortab_a_1korc filterExpr: (dt is not null and ts is not null and s is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 266280 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -229,7 +229,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 12:date), SelectColumnIsNotNull(col 10:timestamp), SelectColumnIsNotNull(col 8:string)) predicate: (dt is not null and s is not null and ts is not null) (type: boolean) - Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 @@ -238,7 +238,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 15] selectExpressions: DateColSubtractDateColumn(col 12:date, col 14:date)(children: CastTimestampToDate(col 10:timestamp) -> 14:date) -> 15:interval_day_time - Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -253,7 +253,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 935 Data size: 248971 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2 @@ -261,13 +261,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 2, 1] - Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 935 Data size: 248971 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 935 Data size: 248971 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_join_part_col_char.q.out b/ql/src/test/results/clientpositive/vector_join_part_col_char.q.out index 9af387a2b2..07ddaef485 100644 --- a/ql/src/test/results/clientpositive/vector_join_part_col_char.q.out +++ b/ql/src/test/results/clientpositive/vector_join_part_col_char.q.out @@ -116,30 +116,30 @@ STAGE PLANS: TableScan alias: c1 filterExpr: gpa is not null (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 474 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: name (type: string), age (type: int), gpa (type: char(50)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 474 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: char(50)) sort order: + Map-reduce partition columns: _col2 (type: char(50)) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 474 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: int) TableScan alias: c2 filterExpr: gpa is not null (type: boolean) - Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: name (type: string), age (type: int), gpa (type: char(5)) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: char(50)) sort order: + Map-reduce partition columns: _col2 (type: char(50)) - Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: int) Map Vectorization: enabled: false @@ -156,10 +156,10 @@ STAGE PLANS: 0 _col2 (type: char(50)) 1 _col2 (type: char(50)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 858 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 858 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out index 9aa6531d0f..4451517f80 100644 --- a/ql/src/test/results/clientpositive/vector_left_outer_join.q.out +++ b/ql/src/test/results/clientpositive/vector_left_outer_join.q.out @@ -39,11 +39,11 @@ STAGE PLANS: $hdt$_1:cd TableScan alias: cd - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -51,11 +51,11 @@ STAGE PLANS: $hdt$_2:hd TableScan alias: hd - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: tinyint) @@ -66,11 +66,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cint (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -78,22 +78,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 24737 Data size: 86492 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 keys: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) - Statistics: Num rows: 14867 Data size: 3518672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2338217 Data size: 18705736 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -116,10 +116,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_left_outer_join2.q.out b/ql/src/test/results/clientpositive/vector_left_outer_join2.q.out index 7f2f17fe37..aee931d493 100644 --- a/ql/src/test/results/clientpositive/vector_left_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/vector_left_outer_join2.q.out @@ -102,11 +102,11 @@ STAGE PLANS: $hdt$_1:tjoin2 TableScan alias: tjoin2 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c2 (type: char(2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(_col2 > 15)} @@ -120,11 +120,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tjoin1 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rnum (type: int), c1 (type: int), c2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -135,14 +135,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -191,11 +191,11 @@ STAGE PLANS: $hdt$_1:tjoin2 TableScan alias: tjoin2 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c2 (type: char(2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(_col2 > 15)} @@ -209,11 +209,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tjoin1 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rnum (type: int), c1 (type: int), c2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -224,14 +224,14 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -284,11 +284,11 @@ STAGE PLANS: $hdt$_1:tjoin2 TableScan alias: tjoin2 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c2 (type: char(2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(_col2 > 15)} @@ -302,7 +302,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tjoin1 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -312,7 +312,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -330,7 +330,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.vectorized.execution.mapjoin.native.enabled IS false, hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 @@ -338,13 +338,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3] - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -407,11 +407,11 @@ STAGE PLANS: $hdt$_1:tjoin2 TableScan alias: tjoin2 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c2 (type: char(2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(_col2 > 15)} @@ -425,7 +425,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tjoin1 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -435,7 +435,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -453,7 +453,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.vectorized.execution.mapjoin.native.enabled IS false, hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 @@ -461,13 +461,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3] - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -530,11 +530,11 @@ STAGE PLANS: $hdt$_1:tjoin2 TableScan alias: tjoin2 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c2 (type: char(2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(_col2 > 15)} @@ -548,7 +548,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tjoin1 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -558,7 +558,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -576,7 +576,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 @@ -584,13 +584,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3] - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -653,11 +653,11 @@ STAGE PLANS: $hdt$_1:tjoin2 TableScan alias: tjoin2 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c1 (type: int), c2 (type: char(2)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator filter predicates: 0 {(_col2 > 15)} @@ -671,7 +671,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tjoin1 - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -681,7 +681,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -699,7 +699,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 @@ -707,13 +707,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3] - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_map_order.q.out b/ql/src/test/results/clientpositive/vector_map_order.q.out index bfe4b93dd3..624ad487af 100644 --- a/ql/src/test/results/clientpositive/vector_map_order.q.out +++ b/ql/src/test/results/clientpositive/vector_map_order.q.out @@ -44,7 +44,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: map_table_n0 - Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:foo:string, 1:bar:map, 2:ROW__ID:struct] @@ -55,13 +55,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 520 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out b/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out index 0b6a95bea3..999499103e 100644 --- a/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out +++ b/ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out @@ -250,36 +250,36 @@ STAGE PLANS: TableScan alias: store_sales_n2 filterExpr: (ss_store_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_sold_date_sk (type: int), ss_store_sk (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) TableScan alias: date_dim_n0 filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -295,7 +295,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -311,23 +311,23 @@ STAGE PLANS: key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TableScan alias: store_n2 filterExpr: ((s_state) IN ('KS', 'AL', 'MN', 'SC', 'VT') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((s_state) IN ('KS', 'AL', 'MN', 'SC', 'VT') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_sk (type: int), s_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map Vectorization: enabled: false @@ -344,13 +344,13 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col4 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col4 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -366,7 +366,7 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -389,7 +389,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -404,7 +404,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) Execution mode: vectorized @@ -425,13 +425,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_multi_insert.q.out b/ql/src/test/results/clientpositive/vector_multi_insert.q.out index 65e1034d5b..6388cf0ec2 100644 --- a/ql/src/test/results/clientpositive/vector_multi_insert.q.out +++ b/ql/src/test/results/clientpositive/vector_multi_insert.q.out @@ -112,14 +112,14 @@ STAGE PLANS: Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (rn < 100) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: rn (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out b/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out index 7ddfda1bc6..cb67e9617d 100644 --- a/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out +++ b/ql/src/test/results/clientpositive/vector_non_constant_in_expr.q.out @@ -17,17 +17,17 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cint = UDFToInteger(ctinyint)) or (cint = UDFToInteger(cbigint))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((cint = UDFToInteger(cbigint)) or (cint = UDFToInteger(ctinyint))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3093170 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_non_string_partition.q.out b/ql/src/test/results/clientpositive/vector_non_string_partition.q.out index c0dd971639..169c72e0ff 100644 --- a/ql/src/test/results/clientpositive/vector_non_string_partition.q.out +++ b/ql/src/test/results/clientpositive/vector_non_string_partition.q.out @@ -46,7 +46,7 @@ STAGE PLANS: TableScan alias: non_string_part filterExpr: (cint > 0) (type: boolean) - Statistics: Num rows: 3073 Data size: 339150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3073 Data size: 24584 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -55,7 +55,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 0) predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), ctinyint (type: tinyint) outputColumnNames: _col0, _col1 @@ -63,7 +63,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 4] - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -72,7 +72,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: tinyint) Execution mode: vectorized @@ -93,13 +93,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 8192 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -150,7 +150,7 @@ STAGE PLANS: TableScan alias: non_string_part filterExpr: (cint > 0) (type: boolean) - Statistics: Num rows: 3073 Data size: 339150 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3073 Data size: 313446 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -159,7 +159,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 0:int, val 0) predicate: (cint > 0) (type: boolean) - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cstring1 (type: string) outputColumnNames: _col0, _col1 @@ -167,7 +167,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ @@ -176,7 +176,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -196,13 +196,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1024 Data size: 113013 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 104448 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_nvl.q.out b/ql/src/test/results/clientpositive/vector_nvl.q.out index c469a56e97..7525ca4ed2 100644 --- a/ql/src/test/results/clientpositive/vector_nvl.q.out +++ b/ql/src/test/results/clientpositive/vector_nvl.q.out @@ -23,7 +23,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: cdouble is null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -32,7 +32,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNull(col 5:double) predicate: cdouble is null (type: boolean) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3114 Data size: 18608 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: double), 100.0D (type: double) outputColumnNames: _col0, _col1 @@ -41,19 +41,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 14] selectExpressions: ConstantVectorExpression(val null) -> 13:double, ConstantVectorExpression(val 100.0) -> 14:double - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3114 Data size: 24920 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -132,19 +132,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 14] selectExpressions: VectorCoalesce(columns [4, 13])(children: col 4:float, ConstantVectorExpression(val 1.0) -> 13:float) -> 14:float - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 85848 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/vector_orderby_5.q.out index 734c6a98f3..88ed804086 100644 --- a/ql/src/test/results/clientpositive/vector_orderby_5.q.out +++ b/ql/src/test/results/clientpositive/vector_orderby_5.q.out @@ -122,7 +122,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n6 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -132,7 +132,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3, 7] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(b) Group By Vectorization: @@ -146,7 +146,7 @@ STAGE PLANS: keys: bo (type: boolean) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -156,7 +156,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -178,7 +178,7 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -200,7 +200,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -220,10 +220,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_outer_join0.q.out b/ql/src/test/results/clientpositive/vector_outer_join0.q.out index 9bb2fadc4c..6bca549737 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join0.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join0.q.out @@ -88,11 +88,11 @@ STAGE PLANS: $hdt$_1:t2 TableScan alias: t2 - Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: c (type: int), v2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -103,7 +103,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:v1:string, 1:a:int, 2:ROW__ID:struct] @@ -114,7 +114,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -129,13 +129,13 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 598 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 598 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -207,11 +207,11 @@ STAGE PLANS: $hdt$_0:t1 TableScan alias: t1 - Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: v1 (type: string), a (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -222,7 +222,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t2 - Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:c:int, 1:v2:string, 2:ROW__ID:struct] @@ -233,7 +233,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 554 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Right Outer Join 0 to 1 @@ -248,13 +248,13 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 598 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6 Data size: 598 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1666 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_outer_join1.q.out b/ql/src/test/results/clientpositive/vector_outer_join1.q.out index ece32f6aa6..38885f26b4 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join1.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join1.q.out @@ -248,11 +248,11 @@ STAGE PLANS: $hdt$_1:cd TableScan alias: cd - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 3697 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 3697 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col2 (type: int) @@ -263,7 +263,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 3697 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -274,7 +274,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 3697 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -289,13 +289,13 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 15376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 15376 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -390,11 +390,11 @@ STAGE PLANS: $hdt$_1:hd TableScan alias: hd - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: tinyint) @@ -405,7 +405,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -416,7 +416,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -431,13 +431,13 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 225 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 225 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -627,11 +627,11 @@ STAGE PLANS: $hdt$_1:cd TableScan alias: cd - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -639,11 +639,11 @@ STAGE PLANS: $hdt$_2:hd TableScan alias: hd - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: tinyint) @@ -654,7 +654,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -665,7 +665,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 2] - Statistics: Num rows: 15 Data size: 3320 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -680,7 +680,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 3652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 28 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -695,7 +695,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0 - Statistics: Num rows: 17 Data size: 4017 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 420 Data size: 1664 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col0) Group By Vectorization: @@ -707,7 +707,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -715,7 +715,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -744,10 +744,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_outer_join2.q.out b/ql/src/test/results/clientpositive/vector_outer_join2.q.out index 455d09e299..59987e1c8c 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join2.q.out @@ -267,11 +267,11 @@ STAGE PLANS: $hdt$_1:cd TableScan alias: cd - Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -279,11 +279,11 @@ STAGE PLANS: $hdt$_2:hd TableScan alias: hd - Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: bigint) @@ -294,7 +294,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: c - Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 132 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -305,7 +305,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3] - Statistics: Num rows: 20 Data size: 4182 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 132 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -320,7 +320,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col1 - Statistics: Num rows: 22 Data size: 4600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -335,7 +335,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col1 - Statistics: Num rows: 24 Data size: 5060 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 142 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(), sum(_col1) Group By Vectorization: @@ -347,7 +347,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -355,7 +355,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -384,10 +384,10 @@ STAGE PLANS: aggregations: count(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_outer_join3.q.out b/ql/src/test/results/clientpositive/vector_outer_join3.q.out index 1f1c1314fe..7bcbea7801 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join3.q.out @@ -244,7 +244,7 @@ left outer join small_alltypesorc_a_n1 hd on hd.cstring1 = c.cstring1 ) t1 POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cint`, `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cint`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t0` ON `t`.`cint` = `t0`.`cint`\nLEFT JOIN (SELECT `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t1` ON `t`.`cstring1` = `t1`.`cstring1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cint"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cint (type: int)","columnExprMap:":{"_col0":"cint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: int)","1":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"cstring1 (type: string)","columnExprMap:":{"_col0":"cstring1"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cint","cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cint (type: int), cstring1 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cstring1"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[2, 6]"},"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col1":"0:_col1"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: int)","1":"_col0 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 2:int"],"bigTableValueExpressions:":["col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col1"],"Statistics:":"Num rows: 22 Data size: 4840 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[2, 6]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} +{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cint`, `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cint`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t0` ON `t`.`cint` = `t0`.`cint`\nLEFT JOIN (SELECT `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t1` ON `t`.`cstring1` = `t1`.`cstring1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cint"],"database:":"default","Statistics:":"Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cint (type: int)","columnExprMap:":{"_col0":"cint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: int)","1":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"cstring1 (type: string)","columnExprMap:":{"_col0":"cstring1"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cint","cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cint (type: int), cstring1 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cstring1"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[2, 6]"},"Statistics:":"Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col1":"0:_col1"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: int)","1":"_col0 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 2:int"],"bigTableValueExpressions:":["col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col1"],"Statistics:":"Num rows: 40 Data size: 2759 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 80 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[2, 6]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} PREHOOK: query: select count(*) from (select c.cstring1 from small_alltypesorc_a_n1 c left outer join small_alltypesorc_a_n1 cd @@ -284,7 +284,7 @@ left outer join small_alltypesorc_a_n1 hd on hd.cstring1 = c.cstring1 ) t1 POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cstring1`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t0` ON `t`.`cstring2` = `t0`.`cstring2`\nLEFT JOIN (SELECT `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t1` ON `t`.`cstring1` = `t1`.`cstring1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cstring2 (type: string)","columnExprMap:":{"_col0":"cstring2"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"cstring1 (type: string)","columnExprMap:":{"_col0":"cstring1"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: string)","1":"_col0 (type: string)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cstring1","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cstring1 (type: string), cstring2 (type: string)","columnExprMap:":{"_col0":"cstring1","_col1":"cstring2"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[6, 7]"},"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 7:string"],"bigTableValueExpressions:":["col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 22 Data size: 4840 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: string)","1":"_col0 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[6, 7]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} +{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cstring1`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t0` ON `t`.`cstring2` = `t0`.`cstring2`\nLEFT JOIN (SELECT `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t1` ON `t`.`cstring1` = `t1`.`cstring1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 1960 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cstring2 (type: string)","columnExprMap:":{"_col0":"cstring2"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 1960 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"cstring1 (type: string)","columnExprMap:":{"_col0":"cstring1"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: string)","1":"_col0 (type: string)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cstring1","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 2939 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cstring1 (type: string), cstring2 (type: string)","columnExprMap:":{"_col0":"cstring1","_col1":"cstring2"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[6, 7]"},"Statistics:":"Num rows: 20 Data size: 2939 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: string)","1":"_col0 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 7:string"],"bigTableValueExpressions:":["col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 23 Data size: 1246 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: string)","1":"_col0 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 46 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[6, 7]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} PREHOOK: query: select count(*) from (select c.cstring1 from small_alltypesorc_a_n1 c left outer join small_alltypesorc_a_n1 cd @@ -324,7 +324,7 @@ left outer join small_alltypesorc_a_n1 hd on hd.cstring1 = c.cstring1 and hd.cint = c.cint ) t1 POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cint`, `cbigint`, `cstring1`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cbigint`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t0` ON `t`.`cstring2` = `t0`.`cstring2` AND `t`.`cbigint` = `t0`.`cbigint`\nLEFT JOIN (SELECT `cint`, `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t1` ON `t`.`cstring1` = `t1`.`cstring1` AND `t`.`cint` = `t1`.`cint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cbigint","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cbigint (type: bigint), cstring2 (type: string)","columnExprMap:":{"_col0":"cbigint","_col1":"cstring2"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cint","cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"cint (type: int), cstring1 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cstring1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cint","cbigint","cstring1","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cint (type: int), cbigint (type: bigint), cstring1 (type: string), cstring2 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cbigint","_col2":"cstring1","_col3":"cstring2"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[2, 3, 6, 7]"},"Statistics:":"Num rows: 20 Data size: 4400 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"0:_col2"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 3:bigint","col 7:string"],"bigTableValueExpressions:":["col 2:int","col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col2"],"Statistics:":"Num rows: 22 Data size: 4840 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:int","col 1:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 24 Data size: 5324 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[2, 3, 6, 7]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} +{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `cint`, `cbigint`, `cstring1`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t`\nLEFT JOIN (SELECT `cbigint`, `cstring2`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t0` ON `t`.`cstring2` = `t0`.`cstring2` AND `t`.`cbigint` = `t0`.`cbigint`\nLEFT JOIN (SELECT `cint`, `cstring1`\nFROM `default`.`small_alltypesorc_a_n1`) AS `t1` ON `t`.`cstring1` = `t1`.`cstring1` AND `t`.`cint` = `t1`.`cint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cbigint","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cbigint (type: bigint), cstring2 (type: string)","columnExprMap:":{"_col0":"cbigint","_col1":"cstring2"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 20 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["cint","cstring1"],"database:":"default","Statistics:":"Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"cint (type: int), cstring1 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cstring1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["cint","cbigint","cstring1","cstring2"],"database:":"default","Statistics:":"Num rows: 20 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_a_n1","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"cint (type: int), cbigint (type: bigint), cstring1 (type: string), cstring2 (type: string)","columnExprMap:":{"_col0":"cint","_col1":"cbigint","_col2":"cstring1","_col3":"cstring2"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[2, 3, 6, 7]"},"Statistics:":"Num rows: 20 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"0:_col2"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: bigint), _col3 (type: string)","1":"_col0 (type: bigint), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 3:bigint","col 7:string"],"bigTableValueExpressions:":["col 2:int","col 6:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col2"],"Statistics:":"Num rows: 23 Data size: 1302 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: int), _col2 (type: string)","1":"_col0 (type: int), _col1 (type: string)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:int","col 1:string"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 46 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[2, 3, 6, 7]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} PREHOOK: query: select count(*) from (select c.cstring1 from small_alltypesorc_a_n1 c left outer join small_alltypesorc_a_n1 cd diff --git a/ql/src/test/results/clientpositive/vector_outer_join4.q.out b/ql/src/test/results/clientpositive/vector_outer_join4.q.out index 2826698b0c..304708dc53 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join4.q.out @@ -258,7 +258,7 @@ from small_alltypesorc_b c left outer join small_alltypesorc_b cd on cd.cint = c.cint POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT *\nFROM (SELECT `ctinyint`, `csmallint`, `cint`, `cbigint`, `cfloat`, `cdouble`, `cstring1`, `cstring2`, `ctimestamp1`, `ctimestamp2`, `cboolean1`, `cboolean2`\nFROM `default`.`small_alltypesorc_b`) AS `t`\nLEFT JOIN (SELECT `ctinyint`, `csmallint`, `cint`, `cbigint`, `cfloat`, `cdouble`, `cstring1`, `cstring2`, `ctimestamp1`, `ctimestamp2`, `cboolean1`, `cboolean2`\nFROM `default`.`small_alltypesorc_b`) AS `t0` ON `t`.`cint` = `t0`.`cint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-4":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-4"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-4":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"],"database:":"default","Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)","columnExprMap:":{"_col0":"ctinyint","_col1":"csmallint","_col10":"cboolean1","_col11":"cboolean2","_col2":"cint","_col3":"cbigint","_col4":"cfloat","_col5":"cdouble","_col6":"cstring1","_col7":"cstring2","_col8":"ctimestamp1","_col9":"ctimestamp2"},"outputColumnNames:":["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"],"Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col2 (type: int)","1":"_col2 (type: int)"},"OperatorId:":"HASHTABLESINK_10"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"],"database:":"default","Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_b","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)","columnExprMap:":{"_col0":"ctinyint","_col1":"csmallint","_col10":"cboolean1","_col11":"cboolean2","_col2":"cint","_col3":"cbigint","_col4":"cfloat","_col5":"cdouble","_col6":"cstring1","_col7":"cstring2","_col8":"ctimestamp1","_col9":"ctimestamp2"},"outputColumnNames:":["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]"},"Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_12","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col1":"0:_col1","_col10":"0:_col10","_col11":"0:_col11","_col12":"1:_col0","_col13":"1:_col1","_col14":"1:_col2","_col15":"1:_col3","_col16":"1:_col4","_col17":"1:_col5","_col18":"1:_col6","_col19":"1:_col7","_col2":"0:_col2","_col20":"1:_col8","_col21":"1:_col9","_col22":"1:_col10","_col23":"1:_col11","_col3":"0:_col3","_col4":"0:_col4","_col5":"0:_col5","_col6":"0:_col6","_col7":"0:_col7","_col8":"0:_col8","_col9":"0:_col9"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col2 (type: int)","1":"_col2 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 2:int"],"bigTableValueExpressions:":["col 0:tinyint","col 1:smallint","col 2:int","col 3:bigint","col 4:float","col 5:double","col 6:string","col 7:string","col 8:timestamp","col 9:timestamp","col 10:boolean","col 11:boolean"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"],"Statistics:":"Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_13","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_14"}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[bigint, bigint, bigint, bigint, double, double, string, string, timestamp, timestamp, bigint, bigint]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_15"}}}}}} +{"optimizedSQL":"SELECT *\nFROM (SELECT `ctinyint`, `csmallint`, `cint`, `cbigint`, `cfloat`, `cdouble`, `cstring1`, `cstring2`, `ctimestamp1`, `ctimestamp2`, `cboolean1`, `cboolean2`\nFROM `default`.`small_alltypesorc_b`) AS `t`\nLEFT JOIN (SELECT `ctinyint`, `csmallint`, `cint`, `cbigint`, `cfloat`, `cdouble`, `cstring1`, `cstring2`, `ctimestamp1`, `ctimestamp2`, `cboolean1`, `cboolean2`\nFROM `default`.`small_alltypesorc_b`) AS `t0` ON `t`.`cint` = `t0`.`cint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-4":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-4"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-4":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"],"database:":"default","Statistics:":"Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)","columnExprMap:":{"_col0":"ctinyint","_col1":"csmallint","_col10":"cboolean1","_col11":"cboolean2","_col2":"cint","_col3":"cbigint","_col4":"cfloat","_col5":"cdouble","_col6":"cstring1","_col7":"cstring2","_col8":"ctimestamp1","_col9":"ctimestamp2"},"outputColumnNames:":["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"],"Statistics:":"Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col2 (type: int)","1":"_col2 (type: int)"},"OperatorId:":"HASHTABLESINK_10"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["ctinyint","csmallint","cint","cbigint","cfloat","cdouble","cstring1","cstring2","ctimestamp1","ctimestamp2","cboolean1","cboolean2"],"database:":"default","Statistics:":"Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_b","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean)","columnExprMap:":{"_col0":"ctinyint","_col1":"csmallint","_col10":"cboolean1","_col11":"cboolean2","_col2":"cint","_col3":"cbigint","_col4":"cfloat","_col5":"cdouble","_col6":"cstring1","_col7":"cstring2","_col8":"ctimestamp1","_col9":"ctimestamp2"},"outputColumnNames:":["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]"},"Statistics:":"Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_12","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col1":"0:_col1","_col10":"0:_col10","_col11":"0:_col11","_col12":"1:_col0","_col13":"1:_col1","_col14":"1:_col2","_col15":"1:_col3","_col16":"1:_col4","_col17":"1:_col5","_col18":"1:_col6","_col19":"1:_col7","_col2":"0:_col2","_col20":"1:_col8","_col21":"1:_col9","_col22":"1:_col10","_col23":"1:_col11","_col3":"0:_col3","_col4":"0:_col4","_col5":"0:_col5","_col6":"0:_col6","_col7":"0:_col7","_col8":"0:_col8","_col9":"0:_col9"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col2 (type: int)","1":"_col2 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 2:int"],"bigTableValueExpressions:":["col 0:tinyint","col 1:smallint","col 2:int","col 3:bigint","col 4:float","col 5:double","col 6:string","col 7:string","col 8:timestamp","col 9:timestamp","col 10:boolean","col 11:boolean"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"],"Statistics:":"Num rows: 69 Data size: 38280 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_13","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 69 Data size: 38280 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_14"}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[bigint, bigint, bigint, bigint, double, double, string, string, timestamp, timestamp, bigint, bigint]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_15"}}}}}} PREHOOK: query: select * from small_alltypesorc_b c left outer join small_alltypesorc_b cd @@ -339,7 +339,7 @@ from small_alltypesorc_b c left outer join small_alltypesorc_b hd on hd.ctinyint = c.ctinyint POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT `t`.`ctinyint`\nFROM (SELECT `ctinyint`\nFROM `default`.`small_alltypesorc_b`) AS `t`\nLEFT JOIN (SELECT `ctinyint`\nFROM `default`.`small_alltypesorc_b`) AS `t0` ON `t`.`ctinyint` = `t0`.`ctinyint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-4":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-4"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-4":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:hd":{"TableScan":{"alias:":"hd","columns:":["ctinyint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint)","columnExprMap:":{"_col0":"ctinyint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"OperatorId:":"HASHTABLESINK_10"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["ctinyint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_b","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint)","columnExprMap:":{"_col0":"ctinyint"},"outputColumnNames:":["_col0"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0]"},"Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_12","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:tinyint"],"bigTableValueExpressions:":["col 0:tinyint"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_13","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_14"}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[0]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_15"}}}}}} +{"optimizedSQL":"SELECT `t`.`ctinyint`\nFROM (SELECT `ctinyint`\nFROM `default`.`small_alltypesorc_b`) AS `t`\nLEFT JOIN (SELECT `ctinyint`\nFROM `default`.`small_alltypesorc_b`) AS `t0` ON `t`.`ctinyint` = `t0`.`ctinyint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-4":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-4"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-4":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:hd":{"TableScan":{"alias:":"hd","columns:":["ctinyint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint)","columnExprMap:":{"_col0":"ctinyint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"OperatorId:":"HASHTABLESINK_10"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["ctinyint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_b","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint)","columnExprMap:":{"_col0":"ctinyint"},"outputColumnNames:":["_col0"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0]"},"Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_12","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:tinyint"],"bigTableValueExpressions:":["col 0:tinyint"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 900 Data size: 3564 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_13","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 900 Data size: 3564 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_14"}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[0]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_15"}}}}}} PREHOOK: query: select c.ctinyint from small_alltypesorc_b c left outer join small_alltypesorc_b hd @@ -782,7 +782,7 @@ left outer join small_alltypesorc_b hd on hd.ctinyint = c.ctinyint ) t1 POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `ctinyint`, `cint`\nFROM `default`.`small_alltypesorc_b`) AS `t`\nLEFT JOIN (SELECT `cint`\nFROM `default`.`small_alltypesorc_b`) AS `t0` ON `t`.`cint` = `t0`.`cint`\nLEFT JOIN (SELECT `ctinyint`\nFROM `default`.`small_alltypesorc_b`) AS `t1` ON `t`.`ctinyint` = `t1`.`ctinyint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cint (type: int)","columnExprMap:":{"_col0":"cint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["ctinyint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint)","columnExprMap:":{"_col0":"ctinyint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["ctinyint","cint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","table:":"small_alltypesorc_b","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint), cint (type: int)","columnExprMap:":{"_col0":"ctinyint","_col1":"cint"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 2]"},"Statistics:":"Num rows: 30 Data size: 6680 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: int)","1":"_col0 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 2:int"],"bigTableValueExpressions:":["col 0:tinyint"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 33 Data size: 7348 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:tinyint"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 36 Data size: 8082 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[0, 2]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} +{"optimizedSQL":"SELECT COUNT(*) AS `$f0`\nFROM (SELECT `ctinyint`, `cint`\nFROM `default`.`small_alltypesorc_b`) AS `t`\nLEFT JOIN (SELECT `cint`\nFROM `default`.`small_alltypesorc_b`) AS `t0` ON `t`.`cint` = `t0`.`cint`\nLEFT JOIN (SELECT `ctinyint`\nFROM `default`.`small_alltypesorc_b`) AS `t1` ON `t`.`ctinyint` = `t1`.`ctinyint`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-8":{"ROOT STAGE":"TRUE"},"Stage-3":{"DEPENDENT STAGES":"Stage-8"},"Stage-0":{"DEPENDENT STAGES":"Stage-3"}},"STAGE PLANS":{"Stage-8":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:cd":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:hd":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:cd":{"TableScan":{"alias:":"cd","columns:":["cint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"cint (type: int)","columnExprMap:":{"_col0":"cint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_26"}}}}}},"$hdt$_2:hd":{"TableScan":{"alias:":"hd","columns:":["ctinyint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_b","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint)","columnExprMap:":{"_col0":"ctinyint"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"OperatorId:":"HASHTABLESINK_24"}}}}}}}}},"Stage-3":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"c","columns:":["ctinyint","cint"],"database:":"default","Statistics:":"Num rows: 30 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE","table:":"small_alltypesorc_b","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"ctinyint (type: tinyint), cint (type: int)","columnExprMap:":{"_col0":"ctinyint","_col1":"cint"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 2]"},"Statistics:":"Num rows: 30 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_28","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col1 (type: int)","1":"_col0 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 2:int"],"bigTableValueExpressions:":["col 0:tinyint"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 69 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_29","children":{"Map Join Operator":{"condition map:":[{"":"Left Outer Join 0 to 1"}],"keys:":{"0":"_col0 (type: tinyint)","1":"_col0 (type: tinyint)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 0:tinyint"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","One MapJoin Condition IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 2070 Data size: 16560 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"MAPJOIN_30","children":{"Group By Operator":{"aggregations:":["count()"],"Group By Vectorization:":{"aggregators:":["VectorUDAFCountStar(*) -> bigint"],"className:":"VectorGroupByOperator","groupByMode:":"HASH","native:":"false","vectorProcessingMode:":"HASH","projectedOutputColumnNums:":"[0]"},"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_31","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0"},"sort order:":"","Reduce Sink Vectorization:":{"className:":"VectorReduceSinkOperator","native:":"false","nativeConditionsMet:":["hive.vectorized.execution.reducesink.new.enabled IS true","No PTF TopN IS true","No DISTINCT columns IS true","BinarySortableSerDe for keys IS true","LazyBinarySerDe for values IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)","OperatorId:":"RS_32"}}}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"12","includeColumns:":"[0, 2]","dataColumns:":["ctinyint:tinyint","csmallint:smallint","cint:int","cbigint:bigint","cfloat:float","cdouble:double","cstring1:string","cstring2:string","ctimestamp1:timestamp","ctimestamp2:timestamp","cboolean1:boolean","cboolean2:boolean"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[]"}},"Local Work:":{"Map Reduce Local Work":{}},"Reduce Vectorization:":{"enabled:":"false","enableConditionsMet:":["hive.vectorized.execution.reduce.enabled IS true"],"enableConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false"]},"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"GBY_15","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_17"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_33"}}}}}} PREHOOK: query: select count(*) from (select c.ctinyint from small_alltypesorc_b c left outer join small_alltypesorc_b cd diff --git a/ql/src/test/results/clientpositive/vector_outer_join6.q.out b/ql/src/test/results/clientpositive/vector_outer_join6.q.out index ac44beed7f..49a001975b 100644 --- a/ql/src/test/results/clientpositive/vector_outer_join6.q.out +++ b/ql/src/test/results/clientpositive/vector_outer_join6.q.out @@ -130,7 +130,7 @@ POSTHOOK: query: explain vectorization detail formatted select tj1rnum, tj2rnum, tjoin3.rnum as rnumt3 from (select tjoin1_n0.rnum tj1rnum, tjoin2_n0.rnum tj2rnum, tjoin2_n0.c1 tj2c1 from tjoin1_n0 left outer join tjoin2_n0 on tjoin1_n0.c1 = tjoin2_n0.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT `t`.`rnum` AS `tj1rnum`, `t0`.`rnum` AS `tj2rnum`, `t1`.`rnum` AS `rnumt3`\nFROM (SELECT `rnum`, `c1`\nFROM `default`.`tjoin1_n0`) AS `t`\nLEFT JOIN (SELECT `rnum`, `c1`\nFROM `default`.`tjoin2_n0`) AS `t0` ON `t`.`c1` = `t0`.`c1`\nLEFT JOIN (SELECT `rnum`, `c1`\nFROM `default`.`tjoin3`) AS `t1` ON `t0`.`c1` = `t1`.`c1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-5":{"ROOT STAGE":"TRUE"},"Stage-4":{"DEPENDENT STAGES":"Stage-5"},"Stage-0":{"DEPENDENT STAGES":"Stage-4"}},"STAGE PLANS":{"Stage-5":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:tjoin2_n0":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:tjoin2_n0":{"TableScan":{"alias:":"tjoin2_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin2_n0","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}},"$hdt$_2:tjoin3":{"TableScan":{"alias:":"tjoin3","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin3","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}}}}},"Stage-4":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin1_n0","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_16","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"1:_col0","_col4":"2:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"},{"":"Left Outer Join 1 to 2"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col1 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 1:int"],"bigTableValueExpressions:":["col 0:int"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false","One MapJoin Condition IS false"]},"outputColumnNames:":["_col0","_col2","_col4"],"Statistics:":"Num rows: 8 Data size: 818 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_17","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col2 (type: int), _col4 (type: int)","columnExprMap:":{"_col0":"_col0","_col1":"_col2","_col2":"_col4"},"outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1, 2]"},"Statistics:":"Num rows: 8 Data size: 818 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_18","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 8 Data size: 818 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_19"}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[bigint]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_20"}}}}}} +{"optimizedSQL":"SELECT `t`.`rnum` AS `tj1rnum`, `t0`.`rnum` AS `tj2rnum`, `t1`.`rnum` AS `rnumt3`\nFROM (SELECT `rnum`, `c1`\nFROM `default`.`tjoin1_n0`) AS `t`\nLEFT JOIN (SELECT `rnum`, `c1`\nFROM `default`.`tjoin2_n0`) AS `t0` ON `t`.`c1` = `t0`.`c1`\nLEFT JOIN (SELECT `rnum`, `c1`\nFROM `default`.`tjoin3`) AS `t1` ON `t0`.`c1` = `t1`.`c1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-5":{"ROOT STAGE":"TRUE"},"Stage-4":{"DEPENDENT STAGES":"Stage-5"},"Stage-0":{"DEPENDENT STAGES":"Stage-4"}},"STAGE PLANS":{"Stage-5":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:tjoin2_n0":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:tjoin2_n0":{"TableScan":{"alias:":"tjoin2_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin2_n0","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}},"$hdt$_2:tjoin3":{"TableScan":{"alias:":"tjoin3","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin3","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col1 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}}}}},"Stage-4":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin1_n0","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_16","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"1:_col0","_col4":"2:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"},{"":"Left Outer Join 1 to 2"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col1 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 1:int"],"bigTableValueExpressions:":["col 0:int"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false","One MapJoin Condition IS false"]},"outputColumnNames:":["_col0","_col2","_col4"],"Statistics:":"Num rows: 8 Data size: 70 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_17","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col2 (type: int), _col4 (type: int)","columnExprMap:":{"_col0":"_col0","_col1":"_col2","_col2":"_col4"},"outputColumnNames:":["_col0","_col1","_col2"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1, 2]"},"Statistics:":"Num rows: 8 Data size: 70 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_18","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 8 Data size: 70 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_19"}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[bigint]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_20"}}}}}} PREHOOK: query: select tj1rnum, tj2rnum, tjoin3.rnum as rnumt3 from (select tjoin1_n0.rnum tj1rnum, tjoin2_n0.rnum tj2rnum, tjoin2_n0.c1 tj2c1 from tjoin1_n0 left outer join tjoin2_n0 on tjoin1_n0.c1 = tjoin2_n0.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 PREHOOK: type: QUERY @@ -157,7 +157,7 @@ POSTHOOK: query: explain vectorization detail formatted select tj1rnum, tj2rnum as rnumt3 from (select tjoin1_n0.rnum tj1rnum, tjoin2_n0.rnum tj2rnum, tjoin2_n0.c1 tj2c1 from tjoin1_n0 left outer join tjoin2_n0 on tjoin1_n0.c1 = tjoin2_n0.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 POSTHOOK: type: QUERY -{"optimizedSQL":"SELECT `t`.`rnum` AS `tj1rnum`, `t0`.`rnum` AS `rnumt3`\nFROM (SELECT `rnum`, `c1`\nFROM `default`.`tjoin1_n0`) AS `t`\nLEFT JOIN (SELECT `rnum`, `c1`\nFROM `default`.`tjoin2_n0`) AS `t0` ON `t`.`c1` = `t0`.`c1`\nLEFT JOIN (SELECT `c1`\nFROM `default`.`tjoin3`) AS `t1` ON `t0`.`c1` = `t1`.`c1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-5":{"ROOT STAGE":"TRUE"},"Stage-4":{"DEPENDENT STAGES":"Stage-5"},"Stage-0":{"DEPENDENT STAGES":"Stage-4"}},"STAGE PLANS":{"Stage-5":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:tjoin2_n0":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:tjoin2_n0":{"TableScan":{"alias:":"tjoin2_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin2_n0","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}},"$hdt$_2:tjoin3":{"TableScan":{"alias:":"tjoin3","columns:":["c1"],"database:":"default","Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin3","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"c1 (type: int)","columnExprMap:":{"_col0":"c1"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}}}}},"Stage-4":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin1_n0","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_16","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"1:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"},{"":"Left Outer Join 1 to 2"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col0 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 1:int"],"bigTableValueExpressions:":["col 0:int"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false","One MapJoin Condition IS false"]},"outputColumnNames:":["_col0","_col2"],"Statistics:":"Num rows: 8 Data size: 818 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_17","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col2 (type: int)","columnExprMap:":{"_col0":"_col0","_col1":"_col2"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1]"},"Statistics:":"Num rows: 8 Data size: 818 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_18","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 8 Data size: 818 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_19"}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[bigint]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_20"}}}}}} +{"optimizedSQL":"SELECT `t`.`rnum` AS `tj1rnum`, `t0`.`rnum` AS `rnumt3`\nFROM (SELECT `rnum`, `c1`\nFROM `default`.`tjoin1_n0`) AS `t`\nLEFT JOIN (SELECT `rnum`, `c1`\nFROM `default`.`tjoin2_n0`) AS `t0` ON `t`.`c1` = `t0`.`c1`\nLEFT JOIN (SELECT `c1`\nFROM `default`.`tjoin3`) AS `t1` ON `t0`.`c1` = `t1`.`c1`","PLAN VECTORIZATION":{"enabled":true,"enabledConditionsMet":["hive.vectorized.execution.enabled IS true"]},"cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-5":{"ROOT STAGE":"TRUE"},"Stage-4":{"DEPENDENT STAGES":"Stage-5"},"Stage-0":{"DEPENDENT STAGES":"Stage-4"}},"STAGE PLANS":{"Stage-5":{"Map Reduce Local Work":{"Alias -> Map Local Tables:":{"$hdt$_1:tjoin2_n0":{"Fetch Operator":{"limit:":"-1"}},"$hdt$_2:tjoin3":{"Fetch Operator":{"limit:":"-1"}}},"Alias -> Map Local Operator Tree:":{"$hdt$_1:tjoin2_n0":{"TableScan":{"alias:":"tjoin2_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin2_n0","isTempTable:":"false","OperatorId:":"TS_2","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_3","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}},"$hdt$_2:tjoin3":{"TableScan":{"alias:":"tjoin3","columns:":["c1"],"database:":"default","Statistics:":"Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin3","isTempTable:":"false","OperatorId:":"TS_4","children":{"Select Operator":{"expressions:":"c1 (type: int)","columnExprMap:":{"_col0":"c1"},"outputColumnNames:":["_col0"],"Statistics:":"Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_5","children":{"HashTable Sink Operator":{"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col0 (type: int)"},"OperatorId:":"HASHTABLESINK_13"}}}}}}}}},"Stage-4":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"tjoin1_n0","columns:":["rnum","c1"],"database:":"default","Statistics:":"Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE","table:":"tjoin1_n0","TableScan Vectorization:":{"native:":"true","vectorizationSchemaColumns:":"[0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct]"},"isTempTable:":"false","OperatorId:":"TS_0","children":{"Select Operator":{"expressions:":"rnum (type: int), c1 (type: int)","columnExprMap:":{"_col0":"rnum","_col1":"c1"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1]"},"Statistics:":"Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_16","children":{"Map Join Operator":{"columnExprMap:":{"_col0":"0:_col0","_col2":"1:_col0"},"condition map:":[{"":"Left Outer Join 0 to 1"},{"":"Left Outer Join 1 to 2"}],"keys:":{"0":"_col1 (type: int)","1":"_col1 (type: int)","2":"_col0 (type: int)"},"Map Join Vectorization:":{"bigTableKeyExpressions:":["col 1:int"],"bigTableValueExpressions:":["col 0:int"],"className:":"VectorMapJoinOperator","native:":"false","nativeConditionsMet:":["hive.mapjoin.optimized.hashtable IS true","hive.vectorized.execution.mapjoin.native.enabled IS true","No nullsafe IS true","Small table vectorizes IS true","Outer Join has keys IS true","Optimized Table and Supports Key Types IS true"],"nativeConditionsNotMet:":["hive.execution.engine mr IN [tez, spark] IS false","One MapJoin Condition IS false"]},"outputColumnNames:":["_col0","_col2"],"Statistics:":"Num rows: 8 Data size: 70 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"MAPJOIN_17","children":{"Select Operator":{"expressions:":"_col0 (type: int), _col2 (type: int)","columnExprMap:":{"_col0":"_col0","_col1":"_col2"},"outputColumnNames:":["_col0","_col1"],"Select Vectorization:":{"className:":"VectorSelectOperator","native:":"true","projectedOutputColumnNums:":"[0, 1]"},"Statistics:":"Num rows: 8 Data size: 70 Basic stats: COMPLETE Column stats: NONE","OperatorId:":"SEL_18","children":{"File Output Operator":{"compressed:":"false","File Sink Vectorization:":{"className:":"VectorFileSinkOperator","native:":"false"},"Statistics:":"Num rows: 8 Data size: 70 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_19"}}}}}}}}}}],"Execution mode:":"vectorized","Map Vectorization:":{"enabled:":"true","enabledConditionsMet:":["hive.vectorized.use.vectorized.input.format IS true"],"inputFormatFeatureSupport:":"[DECIMAL_64]","featureSupportInUse:":"[DECIMAL_64]","inputFileFormats:":["org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"],"allNative:":"false","usesVectorUDFAdaptor:":"false","vectorized:":"true","rowBatchContext:":{"dataColumnCount:":"3","includeColumns:":"[0, 1]","dataColumns:":["rnum:int","c1:int","c2:int"],"partitionColumnCount:":"0","scratchColumnTypeNames:":"[bigint]"}},"Local Work:":{"Map Reduce Local Work":{}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_20"}}}}}} PREHOOK: query: select tj1rnum, tj2rnum as rnumt3 from (select tjoin1_n0.rnum tj1rnum, tjoin2_n0.rnum tj2rnum, tjoin2_n0.c1 tj2c1 from tjoin1_n0 left outer join tjoin2_n0 on tjoin1_n0.c1 = tjoin2_n0.c1 ) tj left outer join tjoin3 on tj2c1 = tjoin3.c1 PREHOOK: type: QUERY diff --git a/ql/src/test/results/clientpositive/vector_reduce1.q.out b/ql/src/test/results/clientpositive/vector_reduce1.q.out index 99bdfe69f0..eef8e5bc36 100644 --- a/ql/src/test/results/clientpositive/vector_reduce1.q.out +++ b/ql/src/test/results/clientpositive/vector_reduce1.q.out @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n7 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -131,7 +131,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [3] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + @@ -140,7 +140,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -159,10 +159,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_reduce2.q.out b/ql/src/test/results/clientpositive/vector_reduce2.q.out index 4bc7bf559f..c09c445380 100644 --- a/ql/src/test/results/clientpositive/vector_reduce2.q.out +++ b/ql/src/test/results/clientpositive/vector_reduce2.q.out @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n5 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -131,7 +131,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [8, 2, 9] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) sort order: +++ @@ -140,7 +140,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -159,10 +159,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_reduce3.q.out b/ql/src/test/results/clientpositive/vector_reduce3.q.out index 22923ee350..210c0e0cc9 100644 --- a/ql/src/test/results/clientpositive/vector_reduce3.q.out +++ b/ql/src/test/results/clientpositive/vector_reduce3.q.out @@ -121,7 +121,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n2 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -131,7 +131,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [8] - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -140,7 +140,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -159,10 +159,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out b/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out index 1632b31403..b64a6b5491 100644 --- a/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out +++ b/ql/src/test/results/clientpositive/vector_reduce_groupby_decimal.q.out @@ -44,7 +44,7 @@ STAGE PLANS: TableScan alias: decimal_test_n2 filterExpr: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean) - Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6102 Data size: 1368328 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -53,7 +53,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:decimal(20,10)), SelectColumnIsNotNull(col 3:decimal(23,14))) predicate: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean) - Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(cdecimal1) Group By Vectorization: @@ -67,7 +67,7 @@ STAGE PLANS: keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) sort order: ++++ @@ -77,7 +77,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col4 (type: decimal(20,10)) Execution mode: vectorized @@ -100,7 +100,7 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: double), KEY._col2 (type: decimal(20,10)), KEY._col3 (type: decimal(23,14)) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3051 Data size: 720036 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -122,7 +122,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3051 Data size: 720036 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col4 (type: decimal(20,10)) Execution mode: vectorized @@ -143,13 +143,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: decimal(20,10)), KEY.reducesinkkey3 (type: decimal(23,14)), VALUE._col0 (type: decimal(20,10)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 3051 Data size: 720036 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 11800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 11200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 11800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 11200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_reduce_groupby_duplicate_cols.q.out b/ql/src/test/results/clientpositive/vector_reduce_groupby_duplicate_cols.q.out index a735338627..0b1cb11781 100644 --- a/ql/src/test/results/clientpositive/vector_reduce_groupby_duplicate_cols.q.out +++ b/ql/src/test/results/clientpositive/vector_reduce_groupby_duplicate_cols.q.out @@ -67,7 +67,7 @@ STAGE PLANS: TableScan alias: a filterExpr: (one is not null and two is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:one:int, 1:two:int, 2:ROW__ID:struct] @@ -77,7 +77,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:int)) predicate: (one is not null and two is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -92,7 +92,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -104,7 +104,7 @@ STAGE PLANS: keys: _col0 (type: int), _col1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ @@ -114,7 +114,7 @@ STAGE PLANS: native: false nativeConditionsMet: No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.vectorized.execution.reducesink.new.enabled IS false, hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map Vectorization: enabled: true @@ -142,14 +142,14 @@ STAGE PLANS: keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: int), _col1 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_string_concat.q.out b/ql/src/test/results/clientpositive/vector_string_concat.q.out index ff9fad3c00..0fe7aa0ba6 100644 --- a/ql/src/test/results/clientpositive/vector_string_concat.q.out +++ b/ql/src/test/results/clientpositive/vector_string_concat.q.out @@ -119,7 +119,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: over1korc - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 101753 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -130,19 +130,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [7, 13, 12] selectExpressions: StringGroupColConcatStringScalar(col 12:string, val )(children: StringScalarConcatStringGroupCol(val , col 7:string) -> 12:string) -> 13:string, StringGroupColConcatStringScalar(col 14:string, val |)(children: StringScalarConcatStringGroupCol(val |, col 12:string)(children: StringRTrim(col 14:string)(children: StringGroupColConcatStringScalar(col 12:string, val )(children: StringScalarConcatStringGroupCol(val , col 7:string) -> 12:string) -> 14:string) -> 12:string) -> 14:string) -> 12:string - Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 487785 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -330,7 +330,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n0 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -341,7 +341,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [20] selectExpressions: StringGroupConcatColCol(col 18:string, col 19:string)(children: StringGroupColConcatStringScalar(col 19:string, val -)(children: StringScalarConcatStringGroupCol(val Quarter , col 18:string)(children: CastLongToString(col 14:int)(children: CastDoubleToLong(col 16:double)(children: DoubleColAddDoubleScalar(col 17:double, val 1.0)(children: DoubleColDivideDoubleScalar(col 16:double, val 3.0)(children: CastLongToDouble(col 15:int)(children: LongColSubtractLongScalar(col 14:int, val 1)(children: VectorUDFMonthDate(col 12, field MONTH) -> 14:int) -> 15:int) -> 16:double) -> 17:double) -> 16:double) -> 14:int) -> 18:string) -> 19:string) -> 18:string, CastLongToString(col 14:int)(children: VectorUDFYearDate(col 12, field YEAR) -> 14:int) -> 19:string) -> 20:string - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -353,7 +353,7 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -363,7 +363,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -384,7 +384,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 53228 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -406,7 +406,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 53228 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -426,13 +426,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 53228 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 50 - Statistics: Num rows: 50 Data size: 22950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2650 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 50 Data size: 22950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 50 Data size: 2650 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_struct_in.q.out b/ql/src/test/results/clientpositive/vector_struct_in.q.out index 110f01bc9d..749825cece 100644 --- a/ql/src/test/results/clientpositive/vector_struct_in.q.out +++ b/ql/src/test/results/clientpositive/vector_struct_in.q.out @@ -59,7 +59,7 @@ STAGE PLANS: TableScan alias: test_1_n1 filterExpr: (struct(id,lineid)) IN (const struct('two','3'), const struct('three','1'), const struct('one','1'), const struct('five','2'), const struct('six','1'), const struct('eight','1'), const struct('seven','1'), const struct('nine','1'), const struct('ten','1')) (type: boolean) - Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -68,7 +68,7 @@ STAGE PLANS: native: true predicateExpression: FilterStructColumnInList(structExpressions [col 0:string, col 1:string], fieldVectorColumnTypes [BYTES, BYTES], structColumnMap [0, 1]) predicate: (struct(id,lineid)) IN (const struct('two','3'), const struct('three','1'), const struct('one','1'), const struct('five','2'), const struct('six','1'), const struct('eight','1'), const struct('seven','1'), const struct('nine','1'), const struct('ten','1')) (type: boolean) - Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), lineid (type: string) outputColumnNames: _col0, _col1 @@ -76,13 +76,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,7 +178,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n1 - Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -189,13 +189,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 4] selectExpressions: StructColumnInList(structExpressions [col 0:string, col 1:string], fieldVectorColumnTypes [BYTES, BYTES], structColumnMap [0, 1]) -> 4:boolean - Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 346 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 354 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -310,7 +310,7 @@ STAGE PLANS: TableScan alias: test_2_n1 filterExpr: (struct(id,lineid)) IN (const struct(2,3), const struct(3,1), const struct(1,1), const struct(5,2), const struct(6,1), const struct(8,1), const struct(7,1), const struct(9,1), const struct(10,1)) (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -319,7 +319,7 @@ STAGE PLANS: native: true predicateExpression: FilterStructColumnInList(structExpressions [col 0:int, col 1:int], fieldVectorColumnTypes [LONG, LONG], structColumnMap [0, 1]) predicate: (struct(id,lineid)) IN (const struct(2,3), const struct(3,1), const struct(1,1), const struct(5,2), const struct(6,1), const struct(8,1), const struct(7,1), const struct(9,1), const struct(10,1)) (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: int), lineid (type: int) outputColumnNames: _col0, _col1 @@ -327,13 +327,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -429,7 +429,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_2_n1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -440,13 +440,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 4] selectExpressions: StructColumnInList(structExpressions [col 0:int, col 1:int], fieldVectorColumnTypes [LONG, LONG], structColumnMap [0, 1]) -> 4:boolean - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -561,7 +561,7 @@ STAGE PLANS: TableScan alias: test_3 filterExpr: (struct(id,lineid)) IN (const struct('two',3), const struct('three',1), const struct('one',1), const struct('five',2), const struct('six',1), const struct('eight',1), const struct('seven',1), const struct('nine',1), const struct('ten',1)) (type: boolean) - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -570,7 +570,7 @@ STAGE PLANS: native: true predicateExpression: FilterStructColumnInList(structExpressions [col 0:string, col 1:int], fieldVectorColumnTypes [BYTES, LONG], structColumnMap [0, 1]) predicate: (struct(id,lineid)) IN (const struct('two',3), const struct('three',1), const struct('one',1), const struct('five',2), const struct('six',1), const struct('eight',1), const struct('seven',1), const struct('nine',1), const struct('ten',1)) (type: boolean) - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: id (type: string), lineid (type: int) outputColumnNames: _col0, _col1 @@ -578,13 +578,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -680,7 +680,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_3 - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -691,13 +691,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 4] selectExpressions: StructColumnInList(structExpressions [col 0:string, col 1:int], fieldVectorColumnTypes [BYTES, LONG], structColumnMap [0, 1]) -> 4:boolean - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -815,7 +815,7 @@ STAGE PLANS: TableScan alias: test_4 filterExpr: (struct(my_bigint,my_string,my_double)) IN (const struct(1L,'a',1.5D), const struct(1L,'b',-0.5D), const struct(3L,'b',1.5D), const struct(1L,'d',1.5D), const struct(1L,'c',1.5D), const struct(1L,'b',2.5D), const struct(1L,'b',0.5D), const struct(5L,'b',1.5D), const struct(1L,'a',0.5D), const struct(3L,'b',1.5D)) (type: boolean) - Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -824,7 +824,7 @@ STAGE PLANS: native: true predicateExpression: FilterStructColumnInList(structExpressions [col 0:bigint, col 1:string, col 2:double], fieldVectorColumnTypes [LONG, BYTES, DOUBLE], structColumnMap [0, 1, 2]) predicate: (struct(my_bigint,my_string,my_double)) IN (const struct(1L,'a',1.5D), const struct(1L,'b',-0.5D), const struct(3L,'b',1.5D), const struct(1L,'d',1.5D), const struct(1L,'c',1.5D), const struct(1L,'b',2.5D), const struct(1L,'b',0.5D), const struct(5L,'b',1.5D), const struct(1L,'a',0.5D), const struct(3L,'b',1.5D)) (type: boolean) - Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: my_bigint (type: bigint), my_string (type: string), my_double (type: double) outputColumnNames: _col0, _col1, _col2 @@ -832,13 +832,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -937,7 +937,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_4 - Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -948,13 +948,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 5] selectExpressions: StructColumnInList(structExpressions [col 0:bigint, col 1:string, col 2:double], fieldVectorColumnTypes [LONG, BYTES, DOUBLE], structColumnMap [0, 1, 2]) -> 5:boolean - Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_udf3.q.out b/ql/src/test/results/clientpositive/vector_udf3.q.out index 27dde3e226..134c15482f 100644 --- a/ql/src/test/results/clientpositive/vector_udf3.q.out +++ b/ql/src/test/results/clientpositive/vector_udf3.q.out @@ -22,7 +22,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -33,13 +33,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13] selectExpressions: VectorStringRot13(col 6:string) -> 13:string - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2260992 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2260992 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_udf_character_length.q.out b/ql/src/test/results/clientpositive/vector_udf_character_length.q.out index 8e3b48546e..c1892fcabd 100644 --- a/ql/src/test/results/clientpositive/vector_udf_character_length.q.out +++ b/ql/src/test/results/clientpositive/vector_udf_character_length.q.out @@ -58,14 +58,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: character_length(value) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -226,14 +226,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: dest2_n13 - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: character_length(name) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -270,14 +270,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: dest2_n13 - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: character_length(name) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_udf_octet_length.q.out b/ql/src/test/results/clientpositive/vector_udf_octet_length.q.out index 5f9be6aae7..eb11590e76 100644 --- a/ql/src/test/results/clientpositive/vector_udf_octet_length.q.out +++ b/ql/src/test/results/clientpositive/vector_udf_octet_length.q.out @@ -41,14 +41,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: octet_length(value) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -209,14 +209,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: dest2_n10 - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: octet_length(name) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_varchar_4.q.out b/ql/src/test/results/clientpositive/vector_varchar_4.q.out index 0ffb7775f8..76fc2859ec 100644 --- a/ql/src/test/results/clientpositive/vector_varchar_4.q.out +++ b/ql/src/test/results/clientpositive/vector_varchar_4.q.out @@ -147,7 +147,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: vectortab2korc_n1 - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -158,13 +158,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [14, 15, 16, 17, 18, 19, 20] selectExpressions: CastLongToVarChar(col 0:tinyint, maxLength 10) -> 14:varchar(10), CastLongToVarChar(col 1:smallint, maxLength 10) -> 15:varchar(10), CastLongToVarChar(col 2:int, maxLength 20) -> 16:varchar(20), CastLongToVarChar(col 3:bigint, maxLength 30) -> 17:varchar(30), CastFloatToVarChar(col 4:float, maxLength 20) -> 18:varchar(20), CastDoubleToVarChar(col 5:double, maxLength 20) -> 19:varchar(20), CastStringGroupToVarChar(col 8:string, maxLength 50) -> 20:varchar(50) - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out b/ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out index 2ea661224f..65c0112e19 100644 --- a/ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out +++ b/ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out @@ -149,14 +149,14 @@ STAGE PLANS: TableScan alias: a filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: varchar(10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: varchar(10)) @@ -168,14 +168,14 @@ STAGE PLANS: TableScan alias: b filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: varchar(10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -183,11 +183,11 @@ STAGE PLANS: 0 _col1 (type: varchar(10)) 1 _col1 (type: varchar(10)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(10)) Execution mode: vectorized Map Vectorization: @@ -209,10 +209,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: varchar(10)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -260,14 +260,14 @@ STAGE PLANS: TableScan alias: a filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: varchar(10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: varchar(20)) @@ -279,14 +279,14 @@ STAGE PLANS: TableScan alias: b filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: varchar(20)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -294,11 +294,11 @@ STAGE PLANS: 0 _col1 (type: varchar(20)) 1 _col1 (type: varchar(20)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(20)) Execution mode: vectorized Map Vectorization: @@ -320,10 +320,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: varchar(20)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -373,14 +373,14 @@ STAGE PLANS: TableScan alias: b filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 CAST( _col1 AS STRING) (type: string) @@ -392,14 +392,14 @@ STAGE PLANS: TableScan alias: a filterExpr: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: c2 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: varchar(10)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -407,11 +407,11 @@ STAGE PLANS: 0 CAST( _col1 AS STRING) (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: string) Execution mode: vectorized Map Vectorization: @@ -433,10 +433,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out index 154e752fb7..6f3251a748 100644 --- a/ql/src/test/results/clientpositive/vector_varchar_simple.q.out +++ b/ql/src/test/results/clientpositive/vector_varchar_simple.q.out @@ -69,15 +69,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_2_n0 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: varchar(10)), value (type: varchar(20)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: varchar(10)) sort order: + - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: varchar(20)) Execution mode: vectorized @@ -98,13 +98,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE._col0 (type: varchar(20)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -178,15 +178,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: varchar_2_n0 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: varchar(10)), value (type: varchar(20)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: varchar(10)) sort order: - - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: varchar(20)) Execution mode: vectorized @@ -207,13 +207,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: varchar(10)), VALUE._col0 (type: varchar(20)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 940 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -285,7 +285,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -295,13 +295,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2] - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -309,7 +309,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: int) Execution mode: vectorized @@ -330,17 +330,17 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( _col0 AS varchar(25)) (type: varchar(25)) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 872 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 2360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 872 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/vector_when_case_null.q.out b/ql/src/test/results/clientpositive/vector_when_case_null.q.out index 2cdbe38623..a1a4002280 100644 --- a/ql/src/test/results/clientpositive/vector_when_case_null.q.out +++ b/ql/src/test/results/clientpositive/vector_when_case_null.q.out @@ -36,7 +36,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: count_case_groupby_n0 - Statistics: Num rows: 5 Data size: 452 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -47,7 +47,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 7] selectExpressions: IfExprColumnCondExpr(col 1:boolean, col 3:intcol 6:int)(children: col 1:boolean, ConstantVectorExpression(val 1) -> 3:int, IfExprColumnNull(col 4:boolean, col 5:int, null)(children: NotCol(col 1:boolean) -> 4:boolean, ConstantVectorExpression(val 0) -> 5:int) -> 6:int) -> 7:int - Statistics: Num rows: 5 Data size: 452 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) Group By Vectorization: @@ -61,7 +61,7 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 452 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + @@ -71,7 +71,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5 Data size: 452 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -93,10 +93,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_1.q.out b/ql/src/test/results/clientpositive/vectorization_1.q.out index c82252f51d..c62d274816 100644 --- a/ql/src/test/results/clientpositive/vectorization_1.q.out +++ b/ql/src/test/results/clientpositive/vectorization_1.q.out @@ -55,7 +55,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (cbigint < UDFToLong(ctinyint)) or (UDFToLong(cint) > cbigint) or (cboolean1 < 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -65,7 +65,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0)), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterLongColLessLongScalar(col 10:boolean, val 0)) predicate: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (UDFToLong(cint) > cbigint) or (cbigint < UDFToLong(ctinyint)) or (cboolean1 < 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -74,7 +74,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 4, 2, 5, 13, 16, 14] selectExpressions: CastLongToDouble(col 0:tinyint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 14:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2) Group By Vectorization: @@ -86,7 +86,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -94,7 +94,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: tinyint), _col5 (type: int), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -121,14 +121,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), max(VALUE._col4), max(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), count(VALUE._col9) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((_col0 - ((_col1 * _col1) / _col2)) / _col2) (type: double), (((_col0 - ((_col1 * _col1) / _col2)) / _col2) / -26.28D) (type: double), _col3 (type: double), (-1.389D + _col3) (type: double), (_col3 * (-1.389D + _col3)) (type: double), _col4 (type: tinyint), (- (_col3 * (-1.389D + _col3))) (type: double), _col5 (type: int), (CAST( _col5 AS decimal(10,0)) * 79.553) (type: decimal(16,3)), ((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END) (type: double), (10.175D % (- (_col3 * (-1.389D + _col3)))) (type: double), _col9 (type: bigint), (-563 % _col5) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_10.q.out b/ql/src/test/results/clientpositive/vectorization_10.q.out index cb7478d067..e6616d3213 100644 --- a/ql/src/test/results/clientpositive/vectorization_10.q.out +++ b/ql/src/test/results/clientpositive/vectorization_10.q.out @@ -61,7 +61,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a')))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -71,7 +71,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimalColLessEqualDecimalScalar(col 14:decimal(6,2), val -5638.15)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(6,2))), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterExprOrExpr(children: FilterDecimalColEqualDecimalScalar(col 15:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(11,4)), FilterStringColLikeStringScalar(col 6:string, pattern %a)))) predicate: (((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and ((CAST( csmallint AS decimal(11,4)) = 9763215.5639) or (cstring1 like '%a'))) or (cstring2 <= '10')) (type: boolean) - Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 1937820 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -80,13 +80,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 8, 0, 10, 6, 13, 17, 16, 18, 20, 21, 19, 23, 24, 26] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 17:double, DoubleColModuloDoubleScalar(col 18:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 18:double) -> 16:double, DoubleColUnaryMinus(col 5:double) -> 18:double, DoubleColModuloDoubleColumn(col 19:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 21:smallint, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColMultiplyLongColumn(col 3:bigint, col 22:bigint)(children: LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 22:smallint) -> 23:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 25:double)(children: DoubleColAddDoubleColumn(col 5:double, col 24:double)(children: CastLongToDouble(col 1:smallint) -> 24:double) -> 25:double) -> 24:double, DoubleColUnaryMinus(col 25:double)(children: DoubleColUnaryMinus(col 5:double) -> 25:double) -> 26:double - Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9557 Data size: 2261694 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9557 Data size: 1893568 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_11.q.out b/ql/src/test/results/clientpositive/vectorization_11.q.out index e17d80d319..30ce4b013c 100644 --- a/ql/src/test/results/clientpositive/vectorization_11.q.out +++ b/ql/src/test/results/clientpositive/vectorization_11.q.out @@ -43,7 +43,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2381474 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -53,7 +53,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringGroupColEqualStringGroupColumn(col 7:string, col 6:string), FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterStringColLikeStringScalar(col 6:string, pattern %a))) predicate: ((cstring2 = cstring1) or (ctimestamp1 is null and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1190792 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639D) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0D) (type: double), (cdouble * -5638.15D) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -62,13 +62,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 10, 5, 8, 13, 14, 15, 17, 16] selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1:int)(children: col 1:smallint) -> 13:int, DoubleColSubtractDoubleScalar(col 5:double, val 9763215.5639) -> 14:double, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleScalar(col 16:double, val 6981.0)(children: DoubleColUnaryMinus(col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleScalar(col 5:double, val -5638.15) -> 16:double - Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 953272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 953272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_12.q.out b/ql/src/test/results/clientpositive/vectorization_12.q.out index 50eddc16fa..10acf65465 100644 --- a/ql/src/test/results/clientpositive/vectorization_12.q.out +++ b/ql/src/test/results/clientpositive/vectorization_12.q.out @@ -78,7 +78,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (ctimestamp1 is null and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1647554 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -88,7 +88,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10:boolean, col 11:boolean), FilterLongColNotEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint)), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %a), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11:boolean, val 1), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 1:bigint)(children: col 1:smallint)))) predicate: (((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ctimestamp1 is null) (type: boolean) - Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 166 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cboolean1 (type: boolean), cstring1 (type: string), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -97,7 +97,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 10, 6, 5, 13, 16, 14] selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double - Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 166 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), sum(_col5), sum(_col4), sum(_col3), count(_col3), sum(_col0), sum(_col6) Group By Vectorization: @@ -111,7 +111,7 @@ STAGE PLANS: keys: _col3 (type: double), _col0 (type: bigint), _col2 (type: string), _col1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) sort order: ++++ @@ -121,7 +121,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3754 Data size: 888395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double) Execution mode: vectorized Map Vectorization: @@ -149,11 +149,11 @@ STAGE PLANS: keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0D * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) (type: double), ((-6432.0D * _col0) / -6432.0D) (type: double), (- ((-6432.0D * _col0) / -6432.0D)) (type: double), (_col7 / _col8) (type: double), (- (-6432.0D * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col9 (type: bigint), ((_col7 / _col8) / (-6432.0D * _col0)) (type: double), (- (- ((-6432.0D * _col0) / -6432.0D))) (type: double), (((-6432.0D * _col0) / -6432.0D) + (- (-6432.0D * _col0))) (type: double), power(((_col10 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -176,7 +176,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 346 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) Execution mode: vectorized Map Vectorization: @@ -202,10 +202,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: string), null (type: timestamp), KEY.reducesinkkey0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(22,2)), VALUE._col11 (type: bigint), VALUE._col12 (type: double), VALUE._col8 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1877 Data size: 444197 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 386 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_13.q.out b/ql/src/test/results/clientpositive/vectorization_13.q.out index f9c3aeb170..c015933f10 100644 --- a/ql/src/test/results/clientpositive/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/vectorization_13.q.out @@ -80,7 +80,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2028982 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -90,7 +90,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28789.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val -28788.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4)))) predicate: (((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean) - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -99,7 +99,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -113,7 +113,7 @@ STAGE PLANS: keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -123,7 +123,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -151,11 +151,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -178,7 +178,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -204,13 +204,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -412,7 +412,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2028982 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -421,7 +421,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28801.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val -28801.336)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDecimalColLessDecimalScalar(col 14:decimal(11,4), val 9763215.5639)(children: CastLongToDecimal(col 0:tinyint) -> 14:decimal(11,4)))) predicate: (((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639)) or ((cfloat < 3569) and (cdouble <= 10.175D) and (cboolean1 <> 1))) (type: boolean) - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -430,7 +430,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 15, 18] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 901772 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) Group By Vectorization: @@ -444,7 +444,7 @@ STAGE PLANS: keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) sort order: +++++ @@ -454,7 +454,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 2730 Data size: 646063 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2730 Data size: 510974 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -476,11 +476,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 255540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -502,7 +502,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -522,13 +522,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 446640 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 40 - Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 9440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 40 Data size: 13206 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_14.q.out b/ql/src/test/results/clientpositive/vectorization_14.q.out index b1241d0cce..232aa9e2c3 100644 --- a/ql/src/test/results/clientpositive/vectorization_14.q.out +++ b/ql/src/test/results/clientpositive/vectorization_14.q.out @@ -80,7 +80,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((UDFToLong(ctinyint) <= cbigint) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2139070 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -90,7 +90,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 13:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp)), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 13:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float))) predicate: (((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and (UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint))) (type: boolean) - Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 @@ -99,7 +99,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 4, 6, 10, 5, 14, 13, 4, 15] selectExpressions: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 15:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 13:double) -> 16:double) -> 13:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 15:double - Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 606 Data size: 105558 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) Group By Vectorization: @@ -113,7 +113,7 @@ STAGE PLANS: keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ @@ -123,7 +123,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 606 Data size: 143411 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 303 Data size: 52846 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -151,11 +151,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 26432 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -178,7 +178,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) Execution mode: vectorized Map Vectorization: @@ -204,10 +204,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 303 Data size: 71705 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 151 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_15.q.out b/ql/src/test/results/clientpositive/vectorization_15.q.out index 24b9a0b88f..2451088dc0 100644 --- a/ql/src/test/results/clientpositive/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/vectorization_15.q.out @@ -76,7 +76,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -86,7 +86,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %ss%), FilterStringColLikeStringScalar(col 6:string, pattern 10%), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -75), FilterLongColEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -3728.0))) predicate: (((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D)) or (cstring1 like '10%') or (cstring2 like '%ss%')) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 @@ -95,7 +95,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 10, 5, 6, 0, 2, 8, 4, 13, 14, 17, 15, 19] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, CastLongToDouble(col 2:int) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 16:double, CastLongToDouble(col 2:int) -> 18:double) -> 19:double - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2491562 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col8), sum(_col7), count(_col0), min(_col2), sum(_col10), sum(_col9), count(_col4), sum(_col12), sum(_col11), count(_col5) Group By Vectorization: @@ -109,7 +109,7 @@ STAGE PLANS: keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1278652 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) sort order: +++++++ @@ -119,7 +119,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 1278652 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -146,11 +146,11 @@ STAGE PLANS: keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 639332 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), power(((_col7 - ((_col8 * _col8) / _col9)) / CASE WHEN ((_col9 = 1L)) THEN (null) ELSE ((_col9 - 1)) END), 0.5) (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col10 (type: double), (_col2 * 79.553D) (type: double), (33.0 % _col0) (type: float), power(((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END), 0.5) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (-23.0D % _col2) (type: double), (- _col4) (type: tinyint), ((_col14 - ((_col15 * _col15) / _col16)) / CASE WHEN ((_col16 = 1L)) THEN (null) ELSE ((_col16 - 1)) END) (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), power(((_col14 - ((_col15 * _col15) / _col16)) / _col16), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -173,7 +173,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) Execution mode: vectorized Map Vectorization: @@ -198,10 +198,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3072 Data size: 1327460 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_16.q.out b/ql/src/test/results/clientpositive/vectorization_16.q.out index f26ce5ec17..7f831e5a70 100644 --- a/ql/src/test/results/clientpositive/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/vectorization_16.q.out @@ -53,7 +53,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2308074 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -63,7 +63,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -72,7 +72,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -86,7 +86,7 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -96,7 +96,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -124,14 +124,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_17.q.out b/ql/src/test/results/clientpositive/vectorization_17.q.out index 3f15667958..d0c2080d5d 100644 --- a/ql/src/test/results/clientpositive/vectorization_17.q.out +++ b/ql/src/test/results/clientpositive/vectorization_17.q.out @@ -61,7 +61,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cbigint > -23L) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1647550 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -71,7 +71,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimalColGreaterDecimalScalar(col 13:decimal(13,3), val -863.257)(children: CastLongToDecimal(col 2:int) -> 13:decimal(13,3))), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float))) predicate: (((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257)) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and (cbigint > -23L)) (type: boolean) - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 549274 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -80,7 +80,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 14, 17, 19, 20, 22, 18] selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 14:double, DoubleColAddDoubleColumn(col 5:double, col 18:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 17:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double) -> 17:double, DoubleColDivideDoubleColumn(col 5:double, col 18:double)(children: CastLongToDouble(col 2:int) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 20:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 21:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 21:decimal(19,0)) -> 22:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 23:double)(children: DoubleColUnaryMinus(col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 18:double) -> 23:double) -> 18:double - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: float) sort order: ++ @@ -89,7 +89,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -115,10 +115,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1212930 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_2.q.out b/ql/src/test/results/clientpositive/vectorization_2.q.out index fdf9d3bd48..c7aceb82e8 100644 --- a/ql/src/test/results/clientpositive/vectorization_2.q.out +++ b/ql/src/test/results/clientpositive/vectorization_2.q.out @@ -59,7 +59,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15)) or ((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2157324 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -69,7 +69,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8:timestamp, col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern b%), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -5638.14990234375)), FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 13:double, val -10669.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterLongColLessLongScalar(col 2:int, val 359)))) predicate: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean) - Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 719232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), cfloat (type: float), cbigint (type: bigint), ctinyint (type: tinyint), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 @@ -78,7 +78,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 4, 3, 0, 5, 13, 16] selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double - Statistics: Num rows: 4778 Data size: 1130728 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 719232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count(), min(_col3), sum(_col4), count(_col4) Group By Vectorization: @@ -90,7 +90,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -98,7 +98,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -125,14 +125,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), count(VALUE._col6), min(VALUE._col7), sum(VALUE._col8), count(VALUE._col9) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double), ((UDFToDouble(_col0) / _col1) % -563.0D) (type: double), ((UDFToDouble(_col0) / _col1) + 762.0D) (type: double), _col2 (type: double), ((_col3 - ((_col4 * _col4) / _col5)) / _col5) (type: double), (- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) (type: double), (_col2 - (UDFToDouble(_col0) / _col1)) (type: double), _col6 (type: bigint), (- (_col2 - (UDFToDouble(_col0) / _col1))) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / _col5) - 762.0D) (type: double), _col7 (type: tinyint), ((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) (type: double), (_col8 / _col9) (type: double), (((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) - _col2) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_3.q.out b/ql/src/test/results/clientpositive/vectorization_3.q.out index db7d7bafd8..4da5901c97 100644 --- a/ql/src/test/results/clientpositive/vectorization_3.q.out +++ b/ql/src/test/results/clientpositive/vectorization_3.q.out @@ -64,7 +64,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D)) or ((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1276620 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -74,7 +74,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float), FilterDecimalColNotEqualDecimalScalar(col 14:decimal(22,3), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterDoubleColEqualDoubleScalar(col 13:double, val -29071.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 13:double), FilterDecimalColGreaterEqualDecimalScalar(col 15:decimal(8,3), val 79.553)(children: CastLongToDecimal(col 1:smallint) -> 15:decimal(8,3)), FilterTimestampColGreaterTimestampColumn(col 8:timestamp, col 9:timestamp))) predicate: (((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2)) or ((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D))) (type: boolean) - Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 260060 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cint (type: int), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -83,7 +83,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 0, 4, 2, 13, 18, 16, 20, 4, 17, 19, 23] selectExpressions: CastLongToDouble(col 1:smallint) -> 13:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 1:smallint) -> 16:double, CastLongToDouble(col 1:smallint) -> 17:double) -> 18:double, CastLongToDouble(col 0:tinyint) -> 16:double, DoubleColMultiplyDoubleColumn(col 17:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 17:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 17:double, CastLongToDouble(col 2:int) -> 19:double, DoubleColMultiplyDoubleColumn(col 21:double, col 22:double)(children: CastLongToDouble(col 2:int) -> 21:double, CastLongToDouble(col 2:int) -> 22:double) -> 23:double - Statistics: Num rows: 2503 Data size: 592342 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2503 Data size: 260060 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col7), sum(_col6), count(_col1), sum(_col9), sum(_col8), count(_col2), sum(_col2), sum(_col3), count(_col3), sum(_col11), sum(_col10) Group By Vectorization: @@ -95,7 +95,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -103,7 +103,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: double), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: double), _col13 (type: double) Execution mode: vectorized Map Vectorization: @@ -130,14 +130,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), sum(VALUE._col9), sum(VALUE._col10), count(VALUE._col11), sum(VALUE._col12), sum(VALUE._col13) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D) (type: double), power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5)) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) % 79.553D) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) (type: double), power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5) (type: double), (- power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), _col9 (type: double), ((- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) / (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (UDFToDouble(_col10) / _col11) (type: double), (-3728.0D - power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), power(((_col12 - ((_col13 * _col13) / _col11)) / _col11), 0.5) (type: double), ((UDFToDouble(_col10) / _col11) / power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_4.q.out b/ql/src/test/results/clientpositive/vectorization_4.q.out index cd62953fcb..e7df74a0bc 100644 --- a/ql/src/test/results/clientpositive/vectorization_4.q.out +++ b/ql/src/test/results/clientpositive/vectorization_4.q.out @@ -59,7 +59,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((UDFToInteger(csmallint) >= cint) or ((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D)) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -69,7 +69,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterDoubleColGreaterDoubleScalar(col 5:double, val 79.553)), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 3:bigint, val -563), FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessEqualDoubleScalar(col 5:double, val -3728.0)))) predicate: (((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D)) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or (UDFToInteger(csmallint) >= cint)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cdouble (type: double), ctinyint (type: tinyint), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -78,7 +78,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 5, 0, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col3), sum(_col1), count(_col1), min(_col2) Group By Vectorization: @@ -90,7 +90,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -98,7 +98,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -125,14 +125,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), min(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), (_col0 * -563L) (type: bigint), (-3728L + _col0) (type: bigint), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (- power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5)) (type: double), (_col2 / _col3) (type: double), ((_col0 * -563L) % _col0) (type: bigint), (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)) (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3))) (type: double), ((-3728L + _col0) - (_col0 * -563L)) (type: bigint), _col4 (type: tinyint), _col4 (type: tinyint), (UDFToDouble(_col4) * (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_5.q.out b/ql/src/test/results/clientpositive/vectorization_5.q.out index 1396fdcdc8..5fc4353021 100644 --- a/ql/src/test/results/clientpositive/vectorization_5.q.out +++ b/ql/src/test/results/clientpositive/vectorization_5.q.out @@ -53,7 +53,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cboolean2 is not null and (cstring1 like '%b%')) or ((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2454862 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -63,7 +63,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 11:boolean), FilterStringColLikeStringScalar(col 6:string, pattern %b%)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), SelectColumnIsNotNull(col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern a))) predicate: (((UDFToDouble(ctinyint) = cdouble) and ctimestamp2 is not null and (cstring2 like 'a')) or (cboolean2 is not null and (cstring1 like '%b%'))) (type: boolean) - Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7658 Data size: 1529972 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) outputColumnNames: ctinyint, csmallint, cint @@ -71,7 +71,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 9216 Data size: 2180995 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7658 Data size: 1529972 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint) Group By Vectorization: @@ -83,7 +83,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -91,7 +91,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -118,14 +118,14 @@ STAGE PLANS: aggregations: max(VALUE._col0), count(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), max(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: smallint), (UDFToInteger(_col0) * -75) (type: int), _col1 (type: bigint), (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1)) (type: double), (6981 * UDFToInteger(_col0)) (type: int), _col2 (type: smallint), (- _col2) (type: smallint), (197.0D % (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1))) (type: double), _col3 (type: bigint), _col4 (type: tinyint), (- _col4) (type: tinyint), ((- _col4) + _col4) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_6.q.out b/ql/src/test/results/clientpositive/vectorization_6.q.out index 99d917fdfa..847d3b4068 100644 --- a/ql/src/test/results/clientpositive/vectorization_6.q.out +++ b/ql/src/test/results/clientpositive/vectorization_6.q.out @@ -55,7 +55,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((ctinyint <> 0Y) and (((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257))))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2110130 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -65,7 +65,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10:boolean, val 0), FilterLongColGreaterEqualLongColumn(col 11:boolean, col 10:boolean)), FilterExprAndExpr(children: SelectColumnIsNotNull(col 3:bigint), FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %a), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -257.0))))) predicate: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (cbigint is not null and ((cstring2 like '%a') or (cfloat <= -257)))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5951 Data size: 1022000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28D / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -74,13 +74,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 4, 6, 13, 14, 15, 16, 17, 18, 19, 20, 22] selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1:int)(children: col 1:smallint) -> 13:int, LongColUnaryMinus(col 1:smallint) -> 14:smallint, DoubleColUnaryMinus(col 4:float) -> 15:float, DoubleScalarDivideDoubleColumn(val -26.28, col 4:double)(children: col 4:float) -> 16:double, DoubleColMultiplyDoubleScalar(col 4:float, val 359.0) -> 17:float, LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 18:int, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColSubtractLongScalar(col 0:int, val -75)(children: col 0:tinyint) -> 20:int, LongScalarMultiplyLongColumn(val 762, col 21:int)(children: LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 21:int) -> 22:int - Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 11605 Data size: 2746359 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_7.q.out b/ql/src/test/results/clientpositive/vectorization_7.q.out index 008d292ef8..2cf92ad3ff 100644 --- a/ql/src/test/results/clientpositive/vectorization_7.q.out +++ b/ql/src/test/results/clientpositive/vectorization_7.q.out @@ -67,7 +67,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((ctinyint <> 0Y) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -77,7 +77,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28815.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0)))) predicate: (((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -86,7 +86,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -95,7 +95,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -121,13 +121,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -289,7 +289,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((ctinyint <> 0Y) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D)))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3019778 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -298,7 +298,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 0:tinyint, val 0), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28792.315)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0)))) predicate: (((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and ((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 1342196 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -307,7 +307,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 14, 15, 16, 17, 19, 20, 18, 21, 23] selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 14:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 15:int, LongColUnaryMinus(col 1:smallint) -> 16:smallint, LongColUnaryMinus(col 0:tinyint) -> 17:tinyint, LongColAddLongScalar(col 18:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 18:tinyint) -> 19:int, LongColMultiplyLongColumn(col 3:bigint, col 18:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 18:smallint) -> 20:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 18:int, LongColUnaryMinus(col 0:tinyint) -> 21:tinyint, LongColModuloLongColumn(col 22:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 22:tinyint) -> 23:tinyint - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) sort order: +++++++++++++++ @@ -316,7 +316,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -336,13 +336,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 5461 Data size: 1292362 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5461 Data size: 923616 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 - Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 5900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 4380 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_8.q.out b/ql/src/test/results/clientpositive/vectorization_8.q.out index b9b0c8af17..5dbd0544db 100644 --- a/ql/src/test/results/clientpositive/vectorization_8.q.out +++ b/ql/src/test/results/clientpositive/vectorization_8.q.out @@ -63,7 +63,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cstring2 is not null and (UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D)) or (cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2983078 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -73,7 +73,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 10.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 16.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0))) predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 742850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -82,7 +82,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, DoubleColAddDoubleColumn(col 22:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 22:float) -> 23:float) -> 22:double - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -91,7 +91,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -117,13 +117,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -272,7 +272,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cstring2 is not null and (UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D)) or (cfloat < -6432) or (cboolean1 is not null and (cdouble = 988888.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2983078 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -281,7 +281,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNotNull(col 7:string), FilterDoubleColLessEqualDoubleScalar(col 13:double, val 12.503)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 13:double, val 11.998)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double)), FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: SelectColumnIsNotNull(col 10:boolean), FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0))) predicate: ((cboolean1 is not null and (cdouble = 988888.0D)) or (cfloat < -6432) or (cstring2 is not null and (UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 742850 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 @@ -290,7 +290,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 15, 17, 19, 16, 18, 20, 22] selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 15:double, DoubleColAddDoubleColumn(col 16:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 16:float) -> 17:float, DoubleColAddDoubleColumn(col 16:double, col 18:double)(children: DoubleColUnaryMinus(col 5:double) -> 16:double, CastLongToDouble(col 3:bigint) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 5:double) -> 16:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 18:float, DoubleColUnaryMinus(col 4:float) -> 20:float, DoubleColAddDoubleColumn(col 21:double, col 23:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 21:double, DoubleColAddDoubleColumn(col 22:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 22:float) -> 23:float) -> 22:double - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) sort order: ++++++++++++++ @@ -299,7 +299,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -319,13 +319,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3059 Data size: 557250 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_9.q.out b/ql/src/test/results/clientpositive/vectorization_9.q.out index f26ce5ec17..7f831e5a70 100644 --- a/ql/src/test/results/clientpositive/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/vectorization_9.q.out @@ -53,7 +53,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2308074 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -63,7 +63,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) predicate: (((cdouble >= -1.389D) or (cstring1 < 'a')) and (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 @@ -72,7 +72,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6, 5, 8, 13] selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 769522 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) Group By Vectorization: @@ -86,7 +86,7 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) sort order: +++ @@ -96,7 +96,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 303516 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) Execution mode: vectorized Map Vectorization: @@ -124,14 +124,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 151758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 307406 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out b/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out index c2f6710c6a..d274278eec 100644 --- a/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out +++ b/ql/src/test/results/clientpositive/vectorization_decimal_date.q.out @@ -31,7 +31,7 @@ STAGE PLANS: TableScan alias: date_decimal_test filterExpr: (cint is not null and cdouble is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 1651260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2101500 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Filter Operator @@ -40,7 +40,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:double)) predicate: (cdouble is not null and cint is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 1651260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdate (type: date), cint (type: int), cdecimal (type: decimal(20,10)) outputColumnNames: _col0, _col1, _col2 @@ -48,19 +48,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 0, 3] - Statistics: Num rows: 12288 Data size: 1651260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 1340 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 1340 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_limit.q.out b/ql/src/test/results/clientpositive/vectorization_limit.q.out index 1d5db091de..73951e930e 100644 --- a/ql/src/test/results/clientpositive/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_limit.q.out @@ -20,18 +20,18 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint), _col1 (type: double) sort order: ++ - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -51,13 +51,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 7 - Statistics: Num rows: 7 Data size: 1652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 7 Data size: 1652 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -106,7 +106,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -116,7 +116,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 @@ -124,7 +124,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double), _col2 (type: smallint) sort order: +++ @@ -133,7 +133,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -159,13 +159,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -226,7 +226,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -238,7 +238,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 13] selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 1.0) -> 13:double - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1), count(_col1) Group By Vectorization: @@ -252,7 +252,7 @@ STAGE PLANS: keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -262,7 +262,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -290,11 +290,11 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: tinyint), (_col1 / _col2) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -317,7 +317,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -343,13 +343,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -409,7 +409,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -420,7 +420,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -432,7 +432,7 @@ STAGE PLANS: keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -442,7 +442,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -469,13 +469,13 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -536,22 +536,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) outputColumnNames: ctinyint, cdouble - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(DISTINCT cdouble) keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 104204 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 104204 Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: true enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true @@ -568,7 +568,7 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -591,7 +591,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -617,13 +617,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -713,7 +713,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -723,7 +723,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ctinyint) Group By Vectorization: @@ -737,7 +737,7 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -747,7 +747,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -775,7 +775,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -798,7 +798,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized Map Vectorization: @@ -824,13 +824,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 4720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out b/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out index b4fe31a0a9..04f2b5e083 100644 --- a/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out +++ b/ql/src/test/results/clientpositive/vectorization_nested_udf.q.out @@ -18,7 +18,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -30,7 +30,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13] selectExpressions: FuncAbsLongToLong(col 0:tinyint) -> 13:int - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) Group By Vectorization: @@ -42,7 +42,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -50,7 +50,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -77,10 +77,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_numeric_overflows.q.out b/ql/src/test/results/clientpositive/vectorization_numeric_overflows.q.out index 35a8eefac6..d7df3739bc 100644 --- a/ql/src/test/results/clientpositive/vectorization_numeric_overflows.q.out +++ b/ql/src/test/results/clientpositive/vectorization_numeric_overflows.q.out @@ -124,7 +124,7 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((cint1 - 2) > 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -133,7 +133,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 13:int, val 0)(children: LongColSubtractLongScalarChecked(col 4:int, val 2) -> 13:int) predicate: ((cint1 - 2) > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint1 (type: int), (cint1 - 2) (type: int) outputColumnNames: _col0, _col1 @@ -142,7 +142,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [4, 13] selectExpressions: LongColSubtractLongScalarChecked(col 4:int, val 2) -> 13:int - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -151,7 +151,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Map Vectorization: @@ -171,10 +171,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -229,7 +229,7 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((cint2 + 2) < 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -238,7 +238,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColLessLongScalar(col 13:int, val 0)(children: LongColAddLongScalarChecked(col 5:int, val 2) -> 13:int) predicate: ((cint2 + 2) < 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint2 (type: int), (cint2 + 2) (type: int) outputColumnNames: _col0, _col1 @@ -247,7 +247,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 13] selectExpressions: LongColAddLongScalarChecked(col 5:int, val 2) -> 13:int - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -256,7 +256,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Map Vectorization: @@ -276,10 +276,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -332,7 +332,7 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((cint2 * 2) < 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -341,7 +341,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColLessLongScalar(col 13:int, val 0)(children: LongColMultiplyLongScalarChecked(col 5:int, val 2) -> 13:int) predicate: ((cint2 * 2) < 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint2 (type: int), (cint2 * 2) (type: int) outputColumnNames: _col0, _col1 @@ -350,7 +350,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 13] selectExpressions: LongColMultiplyLongScalarChecked(col 5:int, val 2) -> 13:int - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -359,7 +359,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Map Vectorization: @@ -379,10 +379,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -435,7 +435,7 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((ctinyint1 - 2Y) > 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -444,7 +444,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 13:tinyint, val 0)(children: LongColSubtractLongScalarChecked(col 0:tinyint, val 2) -> 13:tinyint) predicate: ((ctinyint1 - 2Y) > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint1 (type: tinyint), (ctinyint1 - 2Y) (type: tinyint) outputColumnNames: _col0, _col1 @@ -453,7 +453,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 13] selectExpressions: LongColSubtractLongScalarChecked(col 0:tinyint, val 2) -> 13:tinyint - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -462,7 +462,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint) Execution mode: vectorized Map Vectorization: @@ -482,10 +482,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: tinyint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -540,7 +540,7 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((ctinyint2 + 2Y) < 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -549,7 +549,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColLessLongScalar(col 13:tinyint, val 0)(children: LongColAddLongScalarChecked(col 1:tinyint, val 2) -> 13:tinyint) predicate: ((ctinyint2 + 2Y) < 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint2 (type: tinyint), (ctinyint2 + 2) (type: int) outputColumnNames: _col0, _col1 @@ -558,7 +558,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 13] selectExpressions: LongColAddLongScalarChecked(col 1:tinyint, val 2) -> 13:int - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -567,7 +567,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Map Vectorization: @@ -587,10 +587,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -643,7 +643,7 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((csmallint2 * 2S) < 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -652,7 +652,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColLessLongScalar(col 13:smallint, val 0)(children: LongColMultiplyLongScalarChecked(col 3:smallint, val 2) -> 13:smallint) predicate: ((csmallint2 * 2S) < 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint2 (type: smallint), (csmallint2 * 2) (type: int) outputColumnNames: _col0, _col1 @@ -661,7 +661,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [3, 13] selectExpressions: LongColMultiplyLongScalarChecked(col 3:smallint, val 2) -> 13:int - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + @@ -670,7 +670,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Execution mode: vectorized Map Vectorization: @@ -690,10 +690,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -735,27 +735,27 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((csmallint2 * 2S) < 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((csmallint2 * 2S) < 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint2 (type: smallint), (csmallint2 * 2) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int) Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), VALUE._col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -815,27 +815,27 @@ STAGE PLANS: TableScan alias: parquettable filterExpr: ((t1 - t2) < 50) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((t1 - t2) < 50) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t1 (type: tinyint), t2 (type: tinyint), (t1 - t2) (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: tinyint) sort order: - - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: tinyint) Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: tinyint), KEY.reducesinkkey0 (type: tinyint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -884,7 +884,7 @@ STAGE PLANS: TableScan alias: parquettable filterExpr: ((i1 - i2) < 50) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -893,7 +893,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColLessLongScalar(col 5:int, val 50)(children: LongColSubtractLongColumnChecked(col 2:int, col 3:int) -> 5:int) predicate: ((i1 - i2) < 50) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i1 (type: int), i2 (type: int), (i1 - i2) (type: int) outputColumnNames: _col0, _col1, _col2 @@ -902,7 +902,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 3, 5] selectExpressions: LongColSubtractLongColumnChecked(col 2:int, col 3:int) -> 5:int - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: - @@ -911,7 +911,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int) Execution mode: vectorized Map Vectorization: @@ -931,10 +931,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1086,7 +1086,7 @@ STAGE PLANS: TableScan alias: test_overflow filterExpr: ((csmallint1 pmod 16385S) > 0) (type: boolean) - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -1095,7 +1095,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColGreaterLongScalar(col 13:smallint, val 0)(children: PosModLongToLong(col 2, divisor 16385) -> 13:smallint) predicate: ((csmallint1 pmod 16385S) > 0) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint1 (type: tinyint), ctinyint2 (type: tinyint), csmallint1 (type: smallint), csmallint2 (type: smallint), cint1 (type: int), cint2 (type: int), cbigint1 (type: bigint), cbigint2 (type: bigint), cfloat1 (type: float), cfloat2 (type: float), cdouble1 (type: double), cdouble2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 @@ -1103,7 +1103,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -1112,7 +1112,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: tinyint), _col2 (type: smallint), _col3 (type: smallint), _col4 (type: int), _col5 (type: int), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: float), _col9 (type: float), _col10 (type: double), _col11 (type: double) Execution mode: vectorized Map Vectorization: @@ -1132,10 +1132,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: smallint), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: bigint), VALUE._col6 (type: bigint), VALUE._col7 (type: float), VALUE._col8 (type: float), VALUE._col9 (type: double), VALUE._col10 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out index 53500f1678..d42c2459d8 100644 --- a/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out +++ b/ql/src/test/results/clientpositive/vectorization_offset_limit.q.out @@ -18,21 +18,21 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToDouble(cbigint) < cdouble) and (cint > 0)) (type: boolean) - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 20400 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint), cdouble (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1365 Data size: 323031 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1365 Data size: 16320 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 2 Offset of rows: 3 - Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -86,7 +86,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -95,7 +95,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:tinyint) predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) outputColumnNames: _col0, _col1, _col2 @@ -103,7 +103,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: double) sort order: ++ @@ -112,7 +112,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: smallint) Execution mode: vectorized @@ -133,14 +133,14 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 Offset of rows: 10 - Statistics: Num rows: 3 Data size: 708 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 708 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_parquet_projection.q.out b/ql/src/test/results/clientpositive/vectorization_parquet_projection.q.out index ccc31b7f2f..b59d9b59fe 100644 --- a/ql/src/test/results/clientpositive/vectorization_parquet_projection.q.out +++ b/ql/src/test/results/clientpositive/vectorization_parquet_projection.q.out @@ -132,14 +132,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_project_test - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 20328 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), m1 (type: map) outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 20328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 20328 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -280,22 +280,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_project_test - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) outputColumnNames: cint - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -317,10 +317,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -365,22 +365,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_project_test - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 20240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: m1['color'] (type: string) outputColumnNames: _col0 - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 20240 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 20240 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 22 Data size: 44 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 20240 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Map Vectorization: enabled: true @@ -398,10 +398,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 10120 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 10120 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -467,17 +467,17 @@ STAGE PLANS: TableScan alias: parquet_nullsplit filterExpr: (len = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -498,10 +498,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -543,20 +543,20 @@ STAGE PLANS: TableScan alias: parquet_nullsplit filterExpr: (len = '99') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (len = '99') (type: boolean) - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -575,10 +575,10 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_part_project.q.out b/ql/src/test/results/clientpositive/vectorization_part_project.q.out index 50052fde38..8471e6408d 100644 --- a/ql/src/test/results/clientpositive/vectorization_part_project.q.out +++ b/ql/src/test/results/clientpositive/vectorization_part_project.q.out @@ -64,15 +64,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_part - Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1592 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (cdouble + 2.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized Map Vectorization: @@ -92,13 +92,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 54496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 - Statistics: Num rows: 10 Data size: 2720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 2720 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out index 9e85a26ba6..d0fe2acb89 100644 --- a/ql/src/test/results/clientpositive/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/vectorization_pushdown.q.out @@ -18,22 +18,22 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cbigint (type: bigint) outputColumnNames: cbigint - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(cbigint), count(cbigint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -54,14 +54,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (UDFToDouble(_col0) / _col1) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/vectorized_bucketmapjoin1.q.out index eb46ac407d..61aacca403 100644 --- a/ql/src/test/results/clientpositive/vectorized_bucketmapjoin1.q.out +++ b/ql/src/test/results/clientpositive/vectorized_bucketmapjoin1.q.out @@ -115,10 +115,10 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -183,10 +183,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -251,10 +251,10 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/vectorized_case.q.out b/ql/src/test/results/clientpositive/vectorized_case.q.out index 3262fdcc2e..ba706120a8 100644 --- a/ql/src/test/results/clientpositive/vectorized_case.q.out +++ b/ql/src/test/results/clientpositive/vectorized_case.q.out @@ -49,7 +49,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (csmallint) IN (418S, 12205S, 10583S) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -59,7 +59,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColumnInList(col 1:smallint, values [418, 12205, 10583]) predicate: (csmallint) IN (418S, 12205S, 10583S) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -68,13 +68,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 17, 21] selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 16:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprStringScalarStringScalar(col 15:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean) -> 16:string) -> 17:string, IfExprColumnCondExpr(col 15:boolean, col 18:stringcol 20:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 15:boolean, ConstantVectorExpression(val a) -> 18:string, IfExprStringScalarStringScalar(col 19:boolean, val b, val c)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 19:boolean) -> 20:string) -> 21:string - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -195,7 +195,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (csmallint) IN (418S, 12205S, 10583S) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36700 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -205,7 +205,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColumnInList(col 1:smallint, values [418, 12205, 10583]) predicate: (csmallint) IN (418S, 12205S, 10583S) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN ('b') ELSE (null) END (type: string), CASE WHEN ((csmallint = 418S)) THEN ('a') WHEN ((csmallint = 12205S)) THEN (null) ELSE ('c') END (type: string) outputColumnNames: _col0, _col1, _col2 @@ -214,13 +214,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 18, 24] selectExpressions: IfExprColumnCondExpr(col 13:boolean, col 14:stringcol 17:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 13:boolean, ConstantVectorExpression(val a) -> 14:string, IfExprColumnNull(col 15:boolean, col 16:string, null)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 15:boolean, ConstantVectorExpression(val b) -> 16:string) -> 17:string) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 23:string)(children: LongColEqualLongScalar(col 1:smallint, val 418) -> 19:boolean, ConstantVectorExpression(val a) -> 20:string, IfExprNullColumn(col 21:boolean, null, col 22)(children: LongColEqualLongScalar(col 1:smallint, val 12205) -> 21:boolean, ConstantVectorExpression(val c) -> 22:string) -> 23:string) -> 24:string - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2600 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 2600 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -274,7 +274,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -286,7 +286,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 14] selectExpressions: IfExprLongScalarLongScalar(col 14:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongScalarLongScalar(col 15:boolean, val 1, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1) Group By Vectorization: @@ -298,7 +298,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -306,7 +306,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -333,10 +333,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -389,7 +389,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -401,7 +401,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 14] selectExpressions: IfExprLongColumnLongScalar(col 14:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 13:int, val 0)(children: LongColModuloLongScalar(col 2:int, val 2) -> 13:int) -> 14:boolean) -> 13:int, IfExprLongColumnLongScalar(col 15:boolean, col 2:int, val 0)(children: LongColEqualLongScalar(col 14:int, val 1)(children: LongColModuloLongScalar(col 2:int, val 2) -> 14:int) -> 15:boolean) -> 14:int - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1) Group By Vectorization: @@ -413,7 +413,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -421,7 +421,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -448,10 +448,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -516,7 +516,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n3 - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:member:decimal(10,0)/DECIMAL_64, 1:attr:decimal(10,0)/DECIMAL_64, 2:ROW__ID:struct] @@ -528,13 +528,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6] selectExpressions: IfExprCondExprCondExpr(col 3:boolean, col 7:decimal(11,0)col 8:decimal(11,0))(children: Decimal64ColEqualDecimal64Scalar(col 0:decimal(10,0)/DECIMAL_64, decimal64Val 1, decimalVal 1) -> 3:boolean, ConvertDecimal64ToDecimal(col 4:decimal(11,0)/DECIMAL_64)(children: Decimal64ColAddDecimal64Scalar(col 1:decimal(10,0)/DECIMAL_64, decimal64Val 1, decimalVal 1) -> 4:decimal(11,0)/DECIMAL_64) -> 7:decimal(11,0), ConvertDecimal64ToDecimal(col 5:decimal(11,0)/DECIMAL_64)(children: Decimal64ColAddDecimal64Scalar(col 1:decimal(10,0)/DECIMAL_64, decimal64Val 2, decimalVal 2) -> 5:decimal(11,0)/DECIMAL_64) -> 8:decimal(11,0)) -> 6:decimal(11,0) - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -593,7 +593,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n3 - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:member:decimal(10,0)/DECIMAL_64, 1:attr:decimal(10,0)/DECIMAL_64, 2:ROW__ID:struct] @@ -605,13 +605,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8] selectExpressions: IfExprDecimal64ScalarDecimal64Column(col 6:boolean, decimal64Val 1, decimalVal 1, col 7:decimal(1,0)/DECIMAL_64)(children: Decimal64ColEqualDecimal64Scalar(col 0:decimal(10,0)/DECIMAL_64, decimal64Val 1, decimalVal 1) -> 6:boolean, Decimal64ColAddDecimal64Scalar(col 1:decimal(10,0)/DECIMAL_64, decimal64Val 2, decimalVal 2) -> 7:decimal(11,0)/DECIMAL_64) -> 8:decimal(11,0)/DECIMAL_64 - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -670,7 +670,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_1_n3 - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:member:decimal(10,0)/DECIMAL_64, 1:attr:decimal(10,0)/DECIMAL_64, 2:ROW__ID:struct] @@ -682,13 +682,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [8] selectExpressions: IfExprDecimal64ColumnDecimal64Scalar(col 6:boolean, col 7:decimal(11,0)/DECIMAL_64, decimal64Val 2, decimalVal 2)(children: Decimal64ColEqualDecimal64Scalar(col 0:decimal(10,0)/DECIMAL_64, decimal64Val 1, decimalVal 1) -> 6:boolean, Decimal64ColAddDecimal64Scalar(col 1:decimal(10,0)/DECIMAL_64, decimal64Val 1, decimalVal 1) -> 7:decimal(11,0)/DECIMAL_64) -> 8:decimal(11,0)/DECIMAL_64 - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -765,7 +765,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_2_n3 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:member:bigint, 1:attr:bigint, 2:ROW__ID:struct] @@ -777,13 +777,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [6] selectExpressions: IfExprCondExprCondExpr(col 3:boolean, col 4:bigintcol 5:bigint)(children: LongColEqualLongScalar(col 0:bigint, val 1) -> 3:boolean, LongColAddLongScalar(col 1:bigint, val 1) -> 4:bigint, LongColAddLongScalar(col 1:bigint, val 2) -> 5:bigint) -> 6:bigint - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -842,7 +842,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_2_n3 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:member:bigint, 1:attr:bigint, 2:ROW__ID:struct] @@ -854,13 +854,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: IfExprNullCondExpr(col 3:boolean, null, col 4:bigint)(children: LongColEqualLongScalar(col 0:bigint, val 1) -> 3:boolean, LongColAddLongScalar(col 1:bigint, val 2) -> 4:bigint) -> 5:bigint - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -919,7 +919,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_2_n3 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:member:bigint, 1:attr:bigint, 2:ROW__ID:struct] @@ -931,13 +931,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5] selectExpressions: IfExprCondExprNull(col 3:boolean, col 4:bigint, null)(children: LongColEqualLongScalar(col 0:bigint, val 1) -> 3:boolean, LongColAddLongScalar(col 1:bigint, val 1) -> 4:bigint) -> 5:bigint - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_casts.q.out b/ql/src/test/results/clientpositive/vectorized_casts.q.out index cf77aeebe7..83447622a5 100644 --- a/ql/src/test/results/clientpositive/vectorized_casts.q.out +++ b/ql/src/test/results/clientpositive/vectorized_casts.q.out @@ -163,7 +163,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1684250 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct] @@ -173,7 +173,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 250) -> 13:bigint) predicate: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 842180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToBoolean(ctinyint) (type: boolean), UDFToBoolean(csmallint) (type: boolean), UDFToBoolean(cint) (type: boolean), UDFToBoolean(cbigint) (type: boolean), UDFToBoolean(cfloat) (type: boolean), UDFToBoolean(cdouble) (type: boolean), cboolean1 (type: boolean), UDFToBoolean((cbigint * 0L)) (type: boolean), UDFToBoolean(ctimestamp1) (type: boolean), UDFToBoolean(cstring1) (type: boolean), UDFToInteger(ctinyint) (type: int), UDFToInteger(csmallint) (type: int), cint (type: int), UDFToInteger(cbigint) (type: int), UDFToInteger(cfloat) (type: int), UDFToInteger(cdouble) (type: int), UDFToInteger(cboolean1) (type: int), UDFToInteger(ctimestamp1) (type: int), UDFToInteger(cstring1) (type: int), UDFToInteger(substr(cstring1, 1, 1)) (type: int), UDFToByte(cfloat) (type: tinyint), UDFToShort(cfloat) (type: smallint), UDFToLong(cfloat) (type: bigint), UDFToDouble(ctinyint) (type: double), UDFToDouble(csmallint) (type: double), UDFToDouble(cint) (type: double), UDFToDouble(cbigint) (type: double), UDFToDouble(cfloat) (type: double), cdouble (type: double), UDFToDouble(cboolean1) (type: double), UDFToDouble(ctimestamp1) (type: double), UDFToDouble(cstring1) (type: double), UDFToDouble(substr(cstring1, 1, 1)) (type: double), UDFToFloat(cint) (type: float), UDFToFloat(cdouble) (type: float), CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), CAST( CAST( ctimestamp1 AS DATE) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp), CAST( ctinyint AS STRING) (type: string), CAST( csmallint AS STRING) (type: string), CAST( cint AS STRING) (type: string), CAST( cbigint AS STRING) (type: string), CAST( cfloat AS STRING) (type: string), CAST( cdouble AS STRING) (type: string), CAST( cboolean1 AS STRING) (type: string), CAST( (cbigint * 0L) AS STRING) (type: string), CAST( ctimestamp1 AS STRING) (type: string), cstring1 (type: string), CAST( CAST( cstring1 AS CHAR(10)) AS STRING) (type: string), CAST( CAST( cstring1 AS varchar(10)) AS STRING) (type: string), UDFToFloat(UDFToInteger(cfloat)) (type: float), UDFToDouble((cint * 2)) (type: double), CAST( sin(cfloat) AS STRING) (type: string), (UDFToDouble(UDFToFloat(cint)) + UDFToDouble(cboolean1)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55, _col56, _col57, _col58, _col59, _col60, _col61, _col62 @@ -182,13 +182,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [13, 14, 15, 16, 17, 18, 10, 20, 19, 21, 0, 1, 2, 3, 22, 23, 10, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 4, 5, 35, 36, 37, 38, 39, 5, 41, 43, 45, 47, 48, 49, 51, 54, 55, 8, 56, 57, 26, 58, 59, 60, 61, 62, 63, 64, 65, 6, 67, 68, 69, 70, 66, 73] selectExpressions: CastLongToBooleanViaLongToLong(col 0:tinyint) -> 13:boolean, CastLongToBooleanViaLongToLong(col 1:smallint) -> 14:boolean, CastLongToBooleanViaLongToLong(col 2:int) -> 15:boolean, CastLongToBooleanViaLongToLong(col 3:bigint) -> 16:boolean, CastDoubleToBooleanViaDoubleToLong(col 4:float) -> 17:boolean, CastDoubleToBooleanViaDoubleToLong(col 5:double) -> 18:boolean, CastLongToBooleanViaLongToLong(col 19:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 19:bigint) -> 20:boolean, CastTimestampToBoolean(col 8:timestamp) -> 19:boolean, CastStringToBoolean(col 6) -> 21:boolean, CastDoubleToLong(col 4:float) -> 22:int, CastDoubleToLong(col 5:double) -> 23:int, CastTimestampToLong(col 8:timestamp) -> 24:int, CastStringToLong(col 6:string) -> 25:int, CastStringToLong(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 27:int, CastDoubleToLong(col 4:float) -> 28:tinyint, CastDoubleToLong(col 4:float) -> 29:smallint, CastDoubleToLong(col 4:float) -> 30:bigint, CastLongToDouble(col 0:tinyint) -> 31:double, CastLongToDouble(col 1:smallint) -> 32:double, CastLongToDouble(col 2:int) -> 33:double, CastLongToDouble(col 3:bigint) -> 34:double, CastLongToDouble(col 10:boolean) -> 35:double, CastTimestampToDouble(col 8:timestamp) -> 36:double, CastStringToDouble(col 6:string) -> 37:double, CastStringToDouble(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 38:double, CastLongToFloatViaLongToDouble(col 2:int) -> 39:float, CastMillisecondsLongToTimestamp(col 0:tinyint) -> 41:timestamp, CastMillisecondsLongToTimestamp(col 1:smallint) -> 43:timestamp, CastMillisecondsLongToTimestamp(col 2:int) -> 45:timestamp, CastMillisecondsLongToTimestamp(col 3:bigint) -> 47:timestamp, CastDoubleToTimestamp(col 4:float) -> 48:timestamp, CastDoubleToTimestamp(col 5:double) -> 49:timestamp, CastMillisecondsLongToTimestamp(col 10:boolean) -> 51:timestamp, CastMillisecondsLongToTimestamp(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 54:timestamp, CastDateToTimestamp(col 52:date)(children: CastTimestampToDate(col 8:timestamp) -> 52:date) -> 55:timestamp, CastStringToTimestamp(col 6:string) -> 56:timestamp, CastStringToTimestamp(col 26:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 26:string) -> 57:timestamp, CastLongToString(col 0:tinyint) -> 26:string, CastLongToString(col 1:smallint) -> 58:string, CastLongToString(col 2:int) -> 59:string, CastLongToString(col 3:bigint) -> 60:string, CastFloatToString(col 4:float) -> 61:string, CastDoubleToString(col 5:double) -> 62:string, CastBooleanToStringViaLongToString(col 10:boolean) -> 63:string, CastLongToString(col 52:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 52:bigint) -> 64:string, CastTimestampToString(col 8:timestamp) -> 65:string, CastStringGroupToString(col 66:char(10))(children: CastStringGroupToChar(col 6:string, maxLength 10) -> 66:char(10)) -> 67:string, CastStringGroupToString(col 66:varchar(10))(children: CastStringGroupToVarChar(col 6:string, maxLength 10) -> 66:varchar(10)) -> 68:string, CastLongToFloatViaLongToDouble(col 52:int)(children: CastDoubleToLong(col 4:float) -> 52:int) -> 69:float, CastLongToDouble(col 52:int)(children: LongColMultiplyLongScalar(col 2:int, val 2) -> 52:int) -> 70:double, CastDoubleToString(col 71:double)(children: FuncSinDoubleToDouble(col 4:float) -> 71:double) -> 66:string, DoubleColAddDoubleColumn(col 71:double, col 72:double)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 71:float, CastLongToDouble(col 10:boolean) -> 72:double) -> 73:double - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 16362860 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 16362860 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_context.q.out b/ql/src/test/results/clientpositive/vectorized_context.q.out index 1c0715ba71..c483a6f0ee 100644 --- a/ql/src/test/results/clientpositive/vectorized_context.q.out +++ b/ql/src/test/results/clientpositive/vectorized_context.q.out @@ -120,14 +120,14 @@ STAGE PLANS: TableScan alias: household_demographics filterExpr: hd_demo_sk is not null (type: boolean) - Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: hd_demo_sk is not null (type: boolean) - Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 24300 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -136,14 +136,14 @@ STAGE PLANS: TableScan alias: store filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 615730 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 615730 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s_store_sk (type: int), s_city (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6075 Data size: 615632 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 615730 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -155,14 +155,14 @@ STAGE PLANS: TableScan alias: store_sales filterExpr: (ss_store_sk is not null and ss_hdemo_sk is not null) (type: boolean) - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 72744 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (ss_hdemo_sk is not null and ss_store_sk is not null) (type: boolean) - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 72744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ss_store_sk (type: int), ss_hdemo_sk (type: int), ss_net_profit (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6075 Data size: 72736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 72744 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -170,7 +170,7 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col2 - Statistics: Num rows: 6682 Data size: 80009 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 48444 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -178,17 +178,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col5 - Statistics: Num rows: 7350 Data size: 88009 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 615574 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 7350 Data size: 88009 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6075 Data size: 615574 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 10208 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 1100 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 10208 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out index d857cb029b..595bbc0faf 100644 --- a/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_date_funcs.q.out @@ -258,7 +258,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: date_udf_flight_orc - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 5280 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -269,13 +269,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] selectExpressions: VectorUDFUnixTimeStampTimestamp(col 1:timestamp) -> 3:bigint, VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 4:int, VectorUDFMonthTimestamp(col 1:timestamp, field MONTH) -> 5:int, VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 6:int, VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 7:int, VectorUDFDayOfWeekTimestamp(col 1:timestamp, field DAY_OF_WEEK) -> 8:int, VectorUDFWeekOfYearTimestamp(col 1:timestamp, field WEEK_OF_YEAR) -> 9:int, CastTimestampToDate(col 1:timestamp) -> 10:date, VectorUDFDateTimestamp(col 1:timestamp) -> 11:date, VectorUDFDateAddColScalar(col 1:timestamp, val 2) -> 12:date, VectorUDFDateSubColScalar(col 1:timestamp, val 2) -> 13:date, VectorUDFDateDiffColScalar(col 1:timestamp, val 2000-01-01) -> 14:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 15:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 16:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 17:int, VectorUDFDateDiffColScalar(col 1:timestamp, val 2007-03-14) -> 18:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 19:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 20:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 21:int - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 5280 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 5280 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -546,7 +546,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: date_udf_flight_orc - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -557,13 +557,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8, 9, 0, 0, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] selectExpressions: VectorUDFUnixTimeStampDate(col 0) -> 3:bigint, VectorUDFYearDate(col 0, field YEAR) -> 4:int, VectorUDFMonthDate(col 0, field MONTH) -> 5:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 6:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 7:int, VectorUDFDayOfWeekDate(col 0, field DAY_OF_WEEK) -> 8:int, VectorUDFWeekOfYearDate(col 0, field WEEK_OF_YEAR) -> 9:int, VectorUDFDateAddColScalar(col 0:date, val 2) -> 10:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 11:date, VectorUDFDateDiffColScalar(col 0:date, val 2000-01-01) -> 12:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 13:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 14:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 15:int, VectorUDFDateDiffColScalar(col 0:date, val 2007-03-14) -> 16:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 17:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 18:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 19:int - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -838,7 +838,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: date_udf_flight_orc - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 12672 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -849,13 +849,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 0, 5, 6, 7, 8, 9, 10, 4, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24] selectExpressions: LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 3:int, VectorUDFYearDate(col 0, field YEAR) -> 4:int) -> 5:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFMonthTimestamp(col 1:timestamp, field MONTH) -> 3:int, VectorUDFMonthDate(col 0, field MONTH) -> 4:int) -> 6:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 3:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 4:int) -> 7:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 3:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 4:int) -> 8:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFDayOfWeekTimestamp(col 1:timestamp, field DAY_OF_WEEK) -> 3:int, VectorUDFDayOfWeekDate(col 0, field DAY_OF_WEEK) -> 4:int) -> 9:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFWeekOfYearTimestamp(col 1:timestamp, field WEEK_OF_YEAR) -> 3:int, VectorUDFWeekOfYearDate(col 0, field WEEK_OF_YEAR) -> 4:int) -> 10:boolean, LongColEqualLongColumn(col 3:date, col 0:date)(children: CastTimestampToDate(col 1:timestamp) -> 3:date) -> 4:boolean, LongColEqualLongColumn(col 3:date, col 0:date)(children: VectorUDFDateTimestamp(col 1:timestamp) -> 3:date, col 0:date) -> 11:boolean, LongColEqualLongColumn(col 3:date, col 12:date)(children: VectorUDFDateAddColScalar(col 1:timestamp, val 2) -> 3:date, VectorUDFDateAddColScalar(col 0:date, val 2) -> 12:date) -> 13:boolean, LongColEqualLongColumn(col 3:date, col 12:date)(children: VectorUDFDateSubColScalar(col 1:timestamp, val 2) -> 3:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 12:date) -> 14:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val 2000-01-01) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val 2000-01-01) -> 12:int) -> 15:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 16:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 17:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 18:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val 2007-03-14) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val 2007-03-14) -> 12:int) -> 19:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 20:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 21:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 22:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 0:date, val 2000-01-01) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 23:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 0:date, val 2007-03-14) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 24:boolean - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 12672 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 12672 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1102,7 +1102,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: date_udf_flight_orc - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -1113,19 +1113,19 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 3, 4, 6, 7, 9] selectExpressions: VectorUDFDateAddColScalar(col 0:date, val 2) -> 3:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 4:date, VectorUDFDateDiffColCol(col 0:date, col 5:date)(children: VectorUDFDateAddColScalar(col 0:date, val 2) -> 5:date) -> 6:int, VectorUDFDateDiffColCol(col 0:date, col 5:date)(children: VectorUDFDateSubColScalar(col 0:date, val 2) -> 5:date) -> 7:int, VectorUDFDateDiffColCol(col 5:date, col 8:date)(children: VectorUDFDateAddColScalar(col 0:date, val 2) -> 5:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 8:date) -> 9:int - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 10 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 10 Data size: 960 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1222,7 +1222,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: date_udf_flight_orc - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE TableScan Vectorization: native: true Select Operator @@ -1232,7 +1232,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: min(fl_date), max(fl_date), count(fl_date), count() Group By Vectorization: @@ -1244,7 +1244,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -1252,7 +1252,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: date), _col1 (type: date), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1273,7 +1273,7 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -1295,7 +1295,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: date), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -1315,10 +1315,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out index 1c292d46b5..3dcfb41d68 100644 --- a/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out +++ b/ql/src/test/results/clientpositive/vectorized_distinct_gby.q.out @@ -36,22 +36,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: dtest - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) outputColumnNames: a - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(DISTINCT a), count(DISTINCT a) bucketGroup: true keys: a (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: true enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true @@ -67,10 +67,10 @@ STAGE PLANS: aggregations: sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -111,21 +111,21 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(DISTINCT _col0), count(DISTINCT _col0), sum(DISTINCT _col2), sum(DISTINCT _col1) keys: _col0 (type: int), _col2 (type: double), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 601608 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: double) sort order: +++ - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 601608 Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: true enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true @@ -141,14 +141,14 @@ STAGE PLANS: aggregations: sum(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), sum(DISTINCT KEY._col0:2._col0), sum(DISTINCT KEY._col0:3._col0) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), (UDFToDouble(_col0) / _col1) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out index e9429a8b14..4590357511 100644 --- a/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_mapjoin.q.out @@ -27,14 +27,14 @@ STAGE PLANS: TableScan alias: t1 filterExpr: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE HashTable Sink Operator keys: 0 _col0 (type: int) @@ -46,7 +46,7 @@ STAGE PLANS: TableScan alias: t2 filterExpr: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -55,7 +55,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 2:int) predicate: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 @@ -63,7 +63,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2] - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -78,7 +78,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0, _col1 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 @@ -87,7 +87,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2] selectExpressions: LongColAddLongColumn(col 0:int, col 1:int) -> 2:int - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2) Group By Vectorization: @@ -99,7 +99,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3, 4] mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -107,7 +107,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), _col3 (type: bigint), _col4 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -130,14 +130,14 @@ STAGE PLANS: aggregations: count(VALUE._col0), max(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), (UDFToDouble(_col3) / _col4) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_mapjoin3.q.out b/ql/src/test/results/clientpositive/vectorized_mapjoin3.q.out index 8d47d1c77c..c55eaffd49 100644 --- a/ql/src/test/results/clientpositive/vectorized_mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/vectorized_mapjoin3.q.out @@ -137,7 +137,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -145,7 +145,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Map Vectorization: @@ -172,10 +172,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -194,14 +194,14 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -227,13 +227,13 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 633 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 633 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -312,7 +312,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -320,7 +320,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Map Vectorization: @@ -347,10 +347,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -369,14 +369,14 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (int_col_1 is not null and decimal0801_col is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -402,13 +402,13 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 633 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 633 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -487,7 +487,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -495,7 +495,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized Map Vectorization: @@ -522,10 +522,10 @@ STAGE PLANS: aggregations: max(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -544,14 +544,14 @@ STAGE PLANS: TableScan alias: t1 filterExpr: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean) - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 576 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: int) @@ -577,13 +577,13 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 633 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 5 Data size: 633 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out index 3959d475d4..75f5597dee 100644 --- a/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_math_funcs.q.out @@ -117,7 +117,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (((cbigint % 500) = 0) and (sin(cfloat) >= -1.0D)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 293580 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -126,7 +126,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 500) -> 13:bigint), FilterDoubleColGreaterEqualDoubleScalar(col 14:double, val -1.0)(children: FuncSinDoubleToDouble(col 4:float) -> 14:double)) predicate: (((cbigint % 500) = 0) and (sin(cfloat) >= -1.0D)) (type: boolean) - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 48960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cdouble (type: double), round(cdouble, 2) (type: double), floor(cdouble) (type: bigint), ceil(cdouble) (type: bigint), rand() (type: double), rand(98007) (type: double), exp(ln(cdouble)) (type: double), ln(cdouble) (type: double), ln(cfloat) (type: double), log10(cdouble) (type: double), log2(cdouble) (type: double), log2((cdouble - 15601.0D)) (type: double), log2(cfloat) (type: double), log2(cbigint) (type: double), log2(cint) (type: double), log2(csmallint) (type: double), log2(ctinyint) (type: double), log(2, cdouble) (type: double), power(log2(cdouble), 2) (type: double), power(log2(cdouble), 2) (type: double), sqrt(cdouble) (type: double), sqrt(cbigint) (type: double), bin(cbigint) (type: string), hex(cdouble) (type: string), conv(cbigint, 10, 16) (type: string), abs(cdouble) (type: double), abs(ctinyint) (type: int), (cint pmod 3) (type: int), sin(cdouble) (type: double), asin(cdouble) (type: double), cos(cdouble) (type: double), acos(cdouble) (type: double), atan(cdouble) (type: double), degrees(cdouble) (type: double), radians(cdouble) (type: double), cdouble (type: double), cbigint (type: bigint), (- cdouble) (type: double), sign(cdouble) (type: double), sign(cbigint) (type: double), cos(((- sin(log(cdouble))) + 3.14159D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40 @@ -135,13 +135,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 14, 13, 15, 16, 17, 19, 18, 20, 21, 22, 24, 23, 25, 26, 27, 28, 29, 31, 32, 30, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 5, 3, 47, 48, 49, 50] selectExpressions: RoundWithNumDigitsDoubleToDouble(col 5, decimalPlaces 2) -> 14:double, FuncFloorDoubleToLong(col 5:double) -> 13:bigint, FuncCeilDoubleToLong(col 5:double) -> 15:bigint, FuncRandNoSeed -> 16:double, FuncRand -> 17:double, FuncExpDoubleToDouble(col 18:double)(children: FuncLnDoubleToDouble(col 5:double) -> 18:double) -> 19:double, FuncLnDoubleToDouble(col 5:double) -> 18:double, FuncLnDoubleToDouble(col 4:float) -> 20:double, FuncLog10DoubleToDouble(col 5:double) -> 21:double, FuncLog2DoubleToDouble(col 5:double) -> 22:double, FuncLog2DoubleToDouble(col 23:double)(children: DoubleColSubtractDoubleScalar(col 5:double, val 15601.0) -> 23:double) -> 24:double, FuncLog2DoubleToDouble(col 4:float) -> 23:double, FuncLog2LongToDouble(col 3:bigint) -> 25:double, FuncLog2LongToDouble(col 2:int) -> 26:double, FuncLog2LongToDouble(col 1:smallint) -> 27:double, FuncLog2LongToDouble(col 0:tinyint) -> 28:double, FuncLogWithBaseDoubleToDouble(col 5:double) -> 29:double, FuncPowerDoubleToDouble(col 30:double)(children: FuncLog2DoubleToDouble(col 5:double) -> 30:double) -> 31:double, FuncPowerDoubleToDouble(col 30:double)(children: FuncLog2DoubleToDouble(col 5:double) -> 30:double) -> 32:double, FuncSqrtDoubleToDouble(col 5:double) -> 30:double, FuncSqrtLongToDouble(col 3:bigint) -> 33:double, FuncBin(col 3:bigint) -> 34:string, VectorUDFAdaptor(hex(cdouble)) -> 35:string, VectorUDFAdaptor(conv(cbigint, 10, 16)) -> 36:string, FuncAbsDoubleToDouble(col 5:double) -> 37:double, FuncAbsLongToLong(col 0:tinyint) -> 38:int, PosModLongToLong(col 2, divisor 3) -> 39:int, FuncSinDoubleToDouble(col 5:double) -> 40:double, FuncASinDoubleToDouble(col 5:double) -> 41:double, FuncCosDoubleToDouble(col 5:double) -> 42:double, FuncACosDoubleToDouble(col 5:double) -> 43:double, FuncATanDoubleToDouble(col 5:double) -> 44:double, FuncDegreesDoubleToDouble(col 5:double) -> 45:double, FuncRadiansDoubleToDouble(col 5:double) -> 46:double, DoubleColUnaryMinus(col 5:double) -> 47:double, FuncSignDoubleToDouble(col 5:double) -> 48:double, FuncSignLongToDouble(col 3:bigint) -> 49:double, FuncCosDoubleToDouble(col 51:double)(children: DoubleColAddDoubleScalar(col 50:double, val 3.14159)(children: DoubleColUnaryMinus(col 51:double)(children: FuncSinDoubleToDouble(col 50:double)(children: FuncLnDoubleToDouble(col 5:double) -> 50:double) -> 51:double) -> 50:double) -> 51:double) -> 50:double - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 1724272 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2048 Data size: 1724272 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out b/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out index c1f2d54057..1e0941ad4d 100644 --- a/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out +++ b/ql/src/test/results/clientpositive/vectorized_parquet_types.q.out @@ -141,7 +141,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n2 - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 10780 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -152,13 +152,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 10] selectExpressions: VectorUDFAdaptor(hex(cbinary)) -> 12:string - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 13772 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 13772 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -232,7 +232,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n2 - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6402 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -243,13 +243,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [7, 12, 8, 13, 10, 14] selectExpressions: StringLength(col 7:char(5)) -> 12:int, StringLength(col 8:varchar(10)) -> 13:int, FuncSignDecimalToLong(col 10:decimal(4,2)) -> 14:int - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6666 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6666 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -340,7 +340,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_types_n2 - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4906 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -351,7 +351,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 0, 2, 5, 3, 4, 10, 12] selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 12:double - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 4906 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(_col1), min(_col2), count(_col3), sum(_col4), count(_col4), sum(_col7), sum(_col5), count(_col5), max(_col6) Group By Vectorization: @@ -365,7 +365,7 @@ STAGE PLANS: keys: _col0 (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + @@ -375,7 +375,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: decimal(4,2)) Execution mode: vectorized Map Vectorization: @@ -397,11 +397,11 @@ STAGE PLANS: keys: KEY._col0 (type: tinyint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: tinyint), _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), (_col4 / _col5) (type: double), power(((_col6 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double), _col9 (type: decimal(4,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -423,7 +423,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: decimal(4,2)) Execution mode: vectorized Map Vectorization: @@ -443,10 +443,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), VALUE._col0 (type: int), VALUE._col1 (type: smallint), VALUE._col2 (type: bigint), VALUE._col3 (type: double), VALUE._col4 (type: double), VALUE._col5 (type: decimal(4,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -540,7 +540,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_type_nodict - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 10780 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -551,13 +551,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 10] selectExpressions: VectorUDFAdaptor(hex(cbinary)) -> 12:string - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 13772 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 13772 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -631,7 +631,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_type_nodict - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6402 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -642,13 +642,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [7, 12, 8, 13, 10, 14] selectExpressions: StringLength(col 7:char(5)) -> 12:int, StringLength(col 8:varchar(10)) -> 13:int, FuncSignDecimalToLong(col 10:decimal(4,2)) -> 14:int - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6666 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 6666 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -718,19 +718,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: parquet_type_nodict - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: timestamp) outputColumnNames: t - Statistics: Num rows: 22 Data size: 242 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 22 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: max(t), min(t) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: timestamp), _col1 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -751,10 +751,10 @@ STAGE PLANS: aggregations: max(VALUE._col0), min(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out index 59aed714a8..323d8d9fdc 100644 --- a/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out +++ b/ql/src/test/results/clientpositive/vectorized_shufflejoin.q.out @@ -23,35 +23,35 @@ STAGE PLANS: TableScan alias: t1 filterExpr: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: t2 filterExpr: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Map Vectorization: enabled: false enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false @@ -67,16 +67,16 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -97,7 +97,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), _col3 (type: bigint), _col4 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -118,11 +118,11 @@ STAGE PLANS: aggregations: count(VALUE._col0), max(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), count(VALUE._col4) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), (UDFToDouble(_col3) / _col4) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -144,7 +144,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double) Execution mode: vectorized Map Vectorization: @@ -164,10 +164,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out index 1ae72349f7..41509892df 100644 --- a/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_string_funcs.q.out @@ -57,17 +57,17 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: (((cbigint % 237) = 0) and (length(substr(cstring1, 1, 2)) <= 2) and (cstring1 like '%')) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1816546 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((cbigint % 237) = 0) and (cstring1 like '%') and (length(substr(cstring1, 1, 2)) <= 2)) (type: boolean) - Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 151470 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: substr(cstring1, 1, 2) (type: string), substr(cstring1, 2) (type: string), lower(cstring1) (type: string), upper(cstring1) (type: string), upper(cstring1) (type: string), length(cstring1) (type: int), trim(cstring1) (type: string), ltrim(cstring1) (type: string), rtrim(cstring1) (type: string), concat(cstring1, cstring2) (type: string), concat('>', cstring1) (type: string), concat(cstring1, '<') (type: string), concat(substr(cstring1, 1, 2), substr(cstring2, 1, 2)) (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 2265088 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1024 Data size: 242332 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1024 Data size: 2265088 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_timestamp.q.out b/ql/src/test/results/clientpositive/vectorized_timestamp.q.out index da869ce3d3..32b6b9fbce 100644 --- a/ql/src/test/results/clientpositive/vectorized_timestamp.q.out +++ b/ql/src/test/results/clientpositive/vectorized_timestamp.q.out @@ -39,14 +39,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_n2 - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ts (type: timestamp) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -116,7 +116,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_n2 - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ts:timestamp, 1:ROW__ID:struct] @@ -127,7 +127,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(ts), max(ts) Group By Vectorization: @@ -139,7 +139,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -147,7 +147,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: timestamp), _col1 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -174,14 +174,14 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: timestamp), _col1 (type: timestamp), (_col1 - _col0) (type: interval_day_time) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -223,7 +223,7 @@ STAGE PLANS: TableScan alias: test_n2 filterExpr: (ts) IN (TIMESTAMP'0001-01-01 00:00:00', TIMESTAMP'0002-02-02 00:00:00') (type: boolean) - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ts:timestamp, 1:ROW__ID:struct] @@ -233,7 +233,7 @@ STAGE PLANS: native: true predicateExpression: FilterTimestampColumnInList(col 0:timestamp, values [0001-01-02 16:00:00.0, 0002-02-03 16:00:00.0]) predicate: (ts) IN (TIMESTAMP'0001-01-01 00:00:00', TIMESTAMP'0002-02-02 00:00:00') (type: boolean) - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ts (type: timestamp) outputColumnNames: _col0 @@ -241,13 +241,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,7 +304,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_n2 - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ts:timestamp, 1:ROW__ID:struct] @@ -315,7 +315,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ts), count(ts) Group By Vectorization: @@ -327,7 +327,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1] mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -335,7 +335,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -362,14 +362,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: (_col0 / _col1) (type: double), CAST( (_col0 / _col1) AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -410,7 +410,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_n2 - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:ts:timestamp, 1:ROW__ID:struct] @@ -422,7 +422,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 2, 5] selectExpressions: CastTimestampToDouble(col 0:timestamp) -> 2:double, DoubleColMultiplyDoubleColumn(col 3:double, col 4:double)(children: CastTimestampToDouble(col 0:timestamp) -> 3:double, CastTimestampToDouble(col 0:timestamp) -> 4:double) -> 5:double - Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col1), count(_col0) Group By Vectorization: @@ -434,7 +434,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2] mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -442,7 +442,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -469,14 +469,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: ((_col0 - ((_col1 * _col1) / _col2)) / _col2) (type: double), ((_col0 - ((_col1 * _col1) / _col2)) / _col2) (type: double), ((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END) (type: double), power(((_col0 - ((_col1 * _col1) / _col2)) / _col2), 0.5) (type: double), power(((_col0 - ((_col1 * _col1) / _col2)) / _col2), 0.5) (type: double), power(((_col0 - ((_col1 * _col1) / _col2)) / _col2), 0.5) (type: double), power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out b/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out index 4da63b18c4..556a0da1dd 100644 --- a/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out +++ b/ql/src/test/results/clientpositive/vectorized_timestamp_funcs.q.out @@ -253,7 +253,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_string - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 4356 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -264,7 +264,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 6, 7, 8, 9, 10, 11, 12, 0, 1, 3, 13, 14, 15, 16, 17] selectExpressions: VectorUDFUnixTimeStampTimestamp(col 1:timestamp) -> 5:bigint, VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 6:int, VectorUDFMonthTimestamp(col 1:timestamp, field MONTH) -> 7:int, VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 8:int, VectorUDFWeekOfYearTimestamp(col 1:timestamp, field WEEK_OF_YEAR) -> 9:int, VectorUDFHourTimestamp(col 1:timestamp, field HOUR_OF_DAY) -> 10:int, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 11:int, VectorUDFSecondTimestamp(col 1:timestamp, field SECOND) -> 12:int, IfExprTimestampColumnScalar(col 0:boolean, col 1:timestamp, val 1319-01-25 08:31:57.778) -> 13:timestamp, IfExprTimestampScalarColumn(col 0:boolean, val 2000-12-18 00:42:30.0005, col 1:timestamp) -> 14:timestamp, IfExprTimestampColumnColumn(col 0:boolean, col 1:timestampcol 3:timestamp) -> 15:timestamp, IfExprColumnNull(col 0:boolean, col 1:timestamp, null)(children: col 0:boolean, col 1:timestamp) -> 16:timestamp, IfExprNullColumn(col 0:boolean, null, col 3)(children: col 0:boolean, col 3:timestamp) -> 17:timestamp - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 16836 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + @@ -273,7 +273,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 16836 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int), _col9 (type: boolean), _col10 (type: timestamp), _col11 (type: timestamp), _col12 (type: timestamp), _col13 (type: timestamp), _col14 (type: timestamp), _col15 (type: timestamp), _col16 (type: timestamp) Execution mode: vectorized Map Vectorization: @@ -293,10 +293,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: boolean), VALUE._col8 (type: timestamp), VALUE._col9 (type: timestamp), VALUE._col10 (type: timestamp), VALUE._col11 (type: timestamp), VALUE._col12 (type: timestamp), VALUE._col13 (type: timestamp), VALUE._col14 (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 16836 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 16836 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -446,7 +446,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_string - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1017 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -457,7 +457,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [5, 7, 8, 9, 6, 11, 10, 13, 14] selectExpressions: VectorUDFUnixTimeStampString(col 2:string) -> 5:bigint, VectorUDFYearDate(col 6, field YEAR)(children: CastStringToDate(col 2:string) -> 6:date) -> 7:int, VectorUDFMonthDate(col 6, field MONTH)(children: CastStringToDate(col 2:string) -> 6:date) -> 8:int, VectorUDFDayOfMonthDate(col 6, field DAY_OF_MONTH)(children: CastStringToDate(col 2:string) -> 6:date) -> 9:int, VectorUDFDayOfMonthString(col 2:string, fieldStart 8, fieldLength 2) -> 6:int, VectorUDFWeekOfYearDate(col 10, field WEEK_OF_YEAR)(children: CastStringToDate(col 2:string) -> 10:date) -> 11:int, VectorUDFHourTimestamp(col 12:timestamp, field HOUR_OF_DAY)(children: CastStringToTimestamp(col 2:string) -> 12:timestamp) -> 10:int, VectorUDFMinuteTimestamp(col 12:timestamp, field MINUTE)(children: CastStringToTimestamp(col 2:string) -> 12:timestamp) -> 13:int, VectorUDFSecondTimestamp(col 12:timestamp, field SECOND)(children: CastStringToTimestamp(col 2:string) -> 12:timestamp) -> 14:int - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + @@ -466,7 +466,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int) Execution mode: vectorized Map Vectorization: @@ -486,10 +486,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -623,7 +623,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_string - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 3097 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -634,7 +634,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [7, 6, 8, 9, 11, 10, 14, 15, 16] selectExpressions: LongColEqualLongColumn(col 5:bigint, col 6:bigint)(children: VectorUDFUnixTimeStampTimestamp(col 1:timestamp) -> 5:bigint, VectorUDFUnixTimeStampString(col 2:string) -> 6:bigint) -> 7:boolean, LongColEqualLongColumn(col 5:int, col 8:int)(children: VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 5:int, VectorUDFYearDate(col 6, field YEAR)(children: CastStringToDate(col 2:string) -> 6:date) -> 8:int) -> 6:boolean, LongColEqualLongColumn(col 5:int, col 9:int)(children: VectorUDFMonthTimestamp(col 1:timestamp, field MONTH) -> 5:int, VectorUDFMonthDate(col 8, field MONTH)(children: CastStringToDate(col 2:string) -> 8:date) -> 9:int) -> 8:boolean, LongColEqualLongColumn(col 5:int, col 10:int)(children: VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 5:int, VectorUDFDayOfMonthDate(col 9, field DAY_OF_MONTH)(children: CastStringToDate(col 2:string) -> 9:date) -> 10:int) -> 9:boolean, LongColEqualLongColumn(col 5:int, col 10:int)(children: VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 5:int, VectorUDFDayOfMonthString(col 2:string, fieldStart 8, fieldLength 2) -> 10:int) -> 11:boolean, LongColEqualLongColumn(col 5:int, col 12:int)(children: VectorUDFWeekOfYearTimestamp(col 1:timestamp, field WEEK_OF_YEAR) -> 5:int, VectorUDFWeekOfYearDate(col 10, field WEEK_OF_YEAR)(children: CastStringToDate(col 2:string) -> 10:date) -> 12:int) -> 10:boolean, LongColEqualLongColumn(col 5:int, col 12:int)(children: VectorUDFHourTimestamp(col 1:timestamp, field HOUR_OF_DAY) -> 5:int, VectorUDFHourTimestamp(col 13:timestamp, field HOUR_OF_DAY)(children: CastStringToTimestamp(col 2:string) -> 13:timestamp) -> 12:int) -> 14:boolean, LongColEqualLongColumn(col 5:int, col 12:int)(children: VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 5:int, VectorUDFMinuteTimestamp(col 13:timestamp, field MINUTE)(children: CastStringToTimestamp(col 2:string) -> 13:timestamp) -> 12:int) -> 15:boolean, LongColEqualLongColumn(col 5:int, col 12:int)(children: VectorUDFSecondTimestamp(col 1:timestamp, field SECOND) -> 5:int, VectorUDFSecondTimestamp(col 13:timestamp, field SECOND)(children: CastStringToTimestamp(col 2:string) -> 13:timestamp) -> 12:int) -> 16:boolean - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1872 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: boolean) sort order: + @@ -643,7 +643,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1872 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean) Execution mode: vectorized Map Vectorization: @@ -663,10 +663,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: boolean), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1872 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 1872 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -800,7 +800,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_wrong - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 309 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -811,7 +811,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 4, 5, 6, 3, 8, 7, 10, 11] selectExpressions: VectorUDFUnixTimeStampString(col 0:string) -> 2:bigint, VectorUDFYearDate(col 3, field YEAR)(children: CastStringToDate(col 0:string) -> 3:date) -> 4:int, VectorUDFMonthDate(col 3, field MONTH)(children: CastStringToDate(col 0:string) -> 3:date) -> 5:int, VectorUDFDayOfMonthDate(col 3, field DAY_OF_MONTH)(children: CastStringToDate(col 0:string) -> 3:date) -> 6:int, VectorUDFDayOfMonthString(col 0:string, fieldStart 8, fieldLength 2) -> 3:int, VectorUDFWeekOfYearDate(col 7, field WEEK_OF_YEAR)(children: CastStringToDate(col 0:string) -> 7:date) -> 8:int, VectorUDFHourTimestamp(col 9:timestamp, field HOUR_OF_DAY)(children: CastStringToTimestamp(col 0:string) -> 9:timestamp) -> 7:int, VectorUDFMinuteTimestamp(col 9:timestamp, field MINUTE)(children: CastStringToTimestamp(col 0:string) -> 9:timestamp) -> 10:int, VectorUDFSecondTimestamp(col 9:timestamp, field SECOND)(children: CastStringToTimestamp(col 0:string) -> 9:timestamp) -> 11:int - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: bigint) sort order: + @@ -820,7 +820,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int) Execution mode: vectorized Map Vectorization: @@ -840,10 +840,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: int), VALUE._col1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: int), VALUE._col7 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -916,7 +916,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_string - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -926,7 +926,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() Group By Vectorization: @@ -938,7 +938,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -946,7 +946,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: timestamp), _col1 (type: timestamp), _col2 (type: bigint), _col3 (type: bigint) Execution mode: vectorized Map Vectorization: @@ -967,10 +967,10 @@ STAGE PLANS: aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1023,7 +1023,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_string - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -1033,7 +1033,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(ctimestamp1) Group By Vectorization: @@ -1045,7 +1045,7 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -1053,7 +1053,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double) Execution mode: vectorized Map Vectorization: @@ -1074,14 +1074,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: round(_col0, 3) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1142,7 +1142,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc_string - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -1153,7 +1153,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [1, 5, 8] selectExpressions: CastTimestampToDouble(col 1:timestamp) -> 5:double, DoubleColMultiplyDoubleColumn(col 6:double, col 7:double)(children: CastTimestampToDouble(col 1:timestamp) -> 6:double, CastTimestampToDouble(col 1:timestamp) -> 7:double) -> 8:double - Statistics: Num rows: 52 Data size: 3179 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 52 Data size: 2080 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) Group By Vectorization: @@ -1165,7 +1165,7 @@ STAGE PLANS: projectedOutputColumnNums: [0, 1, 2, 3] mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: @@ -1173,7 +1173,7 @@ STAGE PLANS: native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) Execution mode: vectorized Map Vectorization: @@ -1194,14 +1194,14 @@ STAGE PLANS: aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: round((_col0 / _col1), 0) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) BETWEEN 8.97077295279421E19D AND 8.97077295279422E19D (type: boolean), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) BETWEEN 8.97077295279421E19D AND 8.97077295279422E19D (type: boolean), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) BETWEEN 9.20684592523616E19D AND 9.20684592523617E19D (type: boolean), round(power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5), 3) (type: double), round(power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5), 3) (type: double), round(power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5), 3) (type: double), round(power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5), 3) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out b/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out index e67855c743..4505e71d7f 100644 --- a/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out +++ b/ql/src/test/results/clientpositive/vectorized_timestamp_ints_casts.q.out @@ -49,7 +49,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1684250 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -58,7 +58,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 250) -> 13:bigint) predicate: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 842180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 @@ -67,13 +67,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [15, 17, 19, 21, 22, 23, 25, 27, 8, 28, 30] selectExpressions: CastMillisecondsLongToTimestamp(col 0:tinyint) -> 15:timestamp, CastMillisecondsLongToTimestamp(col 1:smallint) -> 17:timestamp, CastMillisecondsLongToTimestamp(col 2:int) -> 19:timestamp, CastMillisecondsLongToTimestamp(col 3:bigint) -> 21:timestamp, CastDoubleToTimestamp(col 4:float) -> 22:timestamp, CastDoubleToTimestamp(col 5:double) -> 23:timestamp, CastMillisecondsLongToTimestamp(col 10:boolean) -> 25:timestamp, CastMillisecondsLongToTimestamp(col 13:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 13:bigint) -> 27:timestamp, CastStringToTimestamp(col 6:string) -> 28:timestamp, CastStringToTimestamp(col 29:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 29:string) -> 30:timestamp - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -210,7 +210,7 @@ STAGE PLANS: TableScan alias: alltypesorc filterExpr: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 1684250 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Filter Operator @@ -219,7 +219,7 @@ STAGE PLANS: native: true predicateExpression: FilterLongColEqualLongScalar(col 13:bigint, val 0)(children: LongColModuloLongScalar(col 3:bigint, val 250) -> 13:bigint) predicate: ((cbigint % 250) = 0) (type: boolean) - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 842180 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: CAST( ctinyint AS TIMESTAMP) (type: timestamp), CAST( csmallint AS TIMESTAMP) (type: timestamp), CAST( cint AS TIMESTAMP) (type: timestamp), CAST( cbigint AS TIMESTAMP) (type: timestamp), CAST( cfloat AS TIMESTAMP) (type: timestamp), CAST( cdouble AS TIMESTAMP) (type: timestamp), CAST( cboolean1 AS TIMESTAMP) (type: timestamp), CAST( (cbigint * 0L) AS TIMESTAMP) (type: timestamp), ctimestamp1 (type: timestamp), CAST( cstring1 AS TIMESTAMP) (type: timestamp), CAST( substr(cstring1, 1, 1) AS TIMESTAMP) (type: timestamp) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 @@ -228,13 +228,13 @@ STAGE PLANS: native: true projectedOutputColumnNums: [14, 15, 16, 17, 18, 19, 20, 21, 8, 22, 24] selectExpressions: CastLongToTimestamp(col 0:tinyint) -> 14:timestamp, CastLongToTimestamp(col 1:smallint) -> 15:timestamp, CastLongToTimestamp(col 2:int) -> 16:timestamp, CastLongToTimestamp(col 3:bigint) -> 17:timestamp, CastDoubleToTimestamp(col 4:float) -> 18:timestamp, CastDoubleToTimestamp(col 5:double) -> 19:timestamp, CastLongToTimestamp(col 10:boolean) -> 20:timestamp, CastLongToTimestamp(col 13:bigint)(children: LongColMultiplyLongScalar(col 3:bigint, val 0) -> 13:bigint) -> 21:timestamp, CastStringToTimestamp(col 6:string) -> 22:timestamp, CastStringToTimestamp(col 23:string)(children: StringSubstrColStartLen(col 6:string, start 0, length 1) -> 23:string) -> 24:timestamp - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 6144 Data size: 1453997 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6144 Data size: 2703360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/view_cbo.q.out b/ql/src/test/results/clientpositive/view_cbo.q.out index fb5ca67883..b64f7f7327 100644 --- a/ql/src/test/results/clientpositive/view_cbo.q.out +++ b/ql/src/test/results/clientpositive/view_cbo.q.out @@ -19,22 +19,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), key (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), count(_col2) keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) - Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: double), _col4 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -43,12 +43,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) mode: mergepartial outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 151500 Basic stats: COMPLETE Column stats: COMPLETE pruneGroupingSetId: true Select Operator expressions: _col1 (type: string), _col0 (type: string), (_col3 / _col4) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -63,7 +63,7 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: double) Execution mode: vectorized @@ -71,13 +71,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 750 Data size: 139500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -667,22 +667,22 @@ STAGE PLANS: alias: src properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -691,11 +691,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 2L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -708,41 +708,41 @@ STAGE PLANS: Map Operator Tree: TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) TableScan Union - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint), _col3 (type: bigint) Reduce Operator Tree: Group By Operator @@ -750,17 +750,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((_col2 * 2) = _col3) and (_col2 > 0L)) (type: boolean) - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 7298 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 41 Data size: 7298 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -773,22 +773,22 @@ STAGE PLANS: alias: src properties: insideView TRUE - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -797,11 +797,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), 1L (type: bigint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 48500 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: diff --git a/ql/src/test/results/clientpositive/windowing_gby2.q.out b/ql/src/test/results/clientpositive/windowing_gby2.q.out index 670c701837..82665be243 100644 --- a/ql/src/test/results/clientpositive/windowing_gby2.q.out +++ b/ql/src/test/results/clientpositive/windowing_gby2.q.out @@ -19,22 +19,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ws - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), c_int (type: int) outputColumnNames: key, c_int - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(c_int) keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -43,11 +43,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint) outputColumnNames: _col1 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -63,13 +63,13 @@ STAGE PLANS: key expressions: 0 (type: int), _col1 (type: bigint) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: bigint) outputColumnNames: _col1 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -90,14 +90,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -149,22 +149,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: ws - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3306 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(key) (type: int), value (type: string), c_int (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3306 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col1), sum(_col2) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -173,7 +173,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -189,14 +189,14 @@ STAGE PLANS: key expressions: _col1 (type: string), _col2 (type: bigint) sort order: ++ Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -216,14 +216,14 @@ STAGE PLANS: name: avg window function: GenericUDAFAverageEvaluatorDouble window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 1176 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: avg_window_0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -278,22 +278,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: cbo_t3 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3382 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), (UDFToFloat(c_int) - c_float) (type: float), (UDFToDouble(c_float) / UDFToDouble(c_int)) (type: double), c_int (type: int), ((UDFToDouble(c_float) / UDFToDouble(c_int)) - UDFToDouble(c_int)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 3382 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col2), sum(_col3), max(_col4), sum(_col5) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double), _col3 (type: double), _col4 (type: int), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: @@ -302,7 +302,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -318,14 +318,14 @@ STAGE PLANS: key expressions: _col0 (type: string), _col2 (type: double) sort order: +- Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: double), _col4 (type: int), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: int), VALUE._col3 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -346,11 +346,11 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int), _col1 (type: string), _col3 (type: double), _col4 (type: int), _col5 (type: double) outputColumnNames: rank_window_0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -366,14 +366,14 @@ STAGE PLANS: key expressions: lower(_col1) (type: string), _col3 (type: double) sort order: ++ Map-reduce partition columns: lower(_col1) (type: string) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE value expressions: rank_window_0 (type: int), _col1 (type: string), _col4 (type: int), _col5 (type: double) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col2 (type: string), KEY.reducesinkkey1 (type: double), VALUE._col4 (type: int), VALUE._col5 (type: double) outputColumnNames: _col0, _col2, _col4, _col5, _col6 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1005 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -394,11 +394,11 @@ STAGE PLANS: window function: GenericUDAFDenseRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1005 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: dense_rank_window_1 (type: int), _col0 (type: int), _col5 (type: int), _col6 (type: double) outputColumnNames: dense_rank_window_1, _col0, _col5, _col6 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1005 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -414,14 +414,14 @@ STAGE PLANS: key expressions: _col5 (type: int), _col6 (type: double) sort order: ++ Map-reduce partition columns: _col5 (type: int) - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1005 Basic stats: COMPLETE Column stats: COMPLETE value expressions: dense_rank_window_1 (type: int), _col0 (type: int) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col1, _col6, _col7 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -442,14 +442,14 @@ STAGE PLANS: window function: GenericUDAFPercentRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), percent_rank_window_2 (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -507,36 +507,36 @@ STAGE PLANS: TableScan alias: ws filterExpr: value is not null (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 1767 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 1581 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string), c_int (type: int), c_boolean (type: boolean) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 1581 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 1581 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: int), _col2 (type: boolean) TableScan alias: wr filterExpr: cstring1 is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 899146 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: cstring1 is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9174 Data size: 671296 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int), cstring1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9174 Data size: 671296 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9174 Data size: 671296 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reduce Operator Tree: Join Operator @@ -546,13 +546,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 36 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col3), sum(_col1) keys: _col2 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -568,7 +568,7 @@ STAGE PLANS: key expressions: _col0 (type: boolean) sort order: + Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 13516 Data size: 3198793 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: @@ -577,11 +577,11 @@ STAGE PLANS: keys: KEY._col0 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: bigint), _col2 (type: bigint) outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false table: @@ -597,14 +597,14 @@ STAGE PLANS: key expressions: 0 (type: int), (UDFToDouble(_col1) / UDFToDouble(_col2)) (type: double) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -625,14 +625,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6758 Data size: 1599396 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/windowing_navfn.q.out b/ql/src/test/results/clientpositive/windowing_navfn.q.out index 8c73534d70..d3809326bf 100644 --- a/ql/src/test/results/clientpositive/windowing_navfn.q.out +++ b/ql/src/test/results/clientpositive/windowing_navfn.q.out @@ -59,15 +59,15 @@ STAGE PLANS: TableScan alias: src filterExpr: (key = '238') (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key = '238') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int) sort order: + Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: PTF Operator @@ -89,14 +89,14 @@ STAGE PLANS: window function: GenericUDAFRowNumberEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: row_number_window_0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/windowing_streaming.q.out b/ql/src/test/results/clientpositive/windowing_streaming.q.out index 42609480bc..d1837abc34 100644 --- a/ql/src/test/results/clientpositive/windowing_streaming.q.out +++ b/ql/src/test/results/clientpositive/windowing_streaming.q.out @@ -62,18 +62,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5694 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5694 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12662 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -94,14 +94,14 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12662 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), rank_window_0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 2652 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -133,19 +133,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: part - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5694 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 5694 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.8 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12662 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -166,17 +166,17 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 26 Data size: 12662 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (rank_window_0 < 4) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 3896 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), rank_window_0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -334,18 +334,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: alltypesorc - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: ctinyint (type: tinyint), cdouble (type: double) sort order: ++ Map-reduce partition columns: ctinyint (type: tinyint) - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.8 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double) outputColumnNames: _col0, _col5 - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3403280 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -366,17 +366,17 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 3403280 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (rank_window_0 < 5) (type: boolean) - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 1121976 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: tinyint), _col5 (type: double), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat -- 2.14.3 (Apple Git-98)